Predicción De Divisas Svm

Soporte de Máquinas Vectoriales: Aplicaciones Financieras Listadas en orden de citas por año, las más altas en la parte superior. Última actualización Septiembre de 2006. PANG, Bo, Lillian LEE y Shivakumar VAITHYANATHAN, 2002. Puntualiza la Clasificación de Sentimiento usando Técnicas de Aprendizaje de Máquinas. En: EMNLP 02: Actas de la Conferencia ACL-02 sobre métodos empíricos en el procesamiento del lenguaje natural - Volumen 10. Páginas 79 - 86. Citado por 154 (36.66 / año) Resumen: Consideramos el problema de clasificar los documentos no por tema, sino por el sentimiento general, p. Determinar si una revisión es positiva o negativa. Usando revisiones de películas como datos, encontramos que las técnicas estándar de aprendizaje de máquinas superan definitivamente las líneas de base producidas por humanos. Sin embargo, los tres métodos de aprendizaje que empleamos (Naive Bayes, clasificación máxima de entropía y máquinas de vectores de soporte) no funcionan tan bien en la clasificación de sentimientos como en la categorización tópica tradicional. Concluimos examinando factores que hacen que el problema de clasificación de sentimientos sea más difícil. Encontró que, utilizando las revisiones de películas como datos, las técnicas estándar de aprendizaje automático superaban definitivamente las líneas de base producidas por los seres humanos. Sin embargo, también encontraron que los tres métodos de aprendizaje de la máquina que empleaban (Naive Bayes, clasificación máxima de entropía y máquinas de vectores de soporte) no funcionaron tanto en la clasificación de sentimientos como en la categorización tópica tradicional. VAN GESTEL, Tony, y col. . 2001. Predicción de series temporales financieras utilizando máquinas de vectores de soporte de mínimos cuadrados dentro del marco de pruebas. IEEE Transacciones en Redes Neuronales. Volumen 12, Número 4, Julio 2001, Páginas 809-821. El marco de evidencia bayesiano se aplica en este trabajo a la regresión de la máquina de vector de apoyo de mínimos cuadrados (LS-SVM) para inferir modelos no lineales para predecir una serie temporal financiera y la volatilidad relacionada. En el primer nivel de inferencia, un marco estadístico está relacionado con la formulación LS-SVM que permite incluir la volatilidad variable en el tiempo del mercado mediante una elección apropiada de varios hiperparámetros. Los hiperparámetros del modelo se deducen en el segundo nivel de inferencia. Los hiperparámetros inferidos, relacionados con la volatilidad, se utilizan para construir un modelo de volatilidad dentro del marco de evidencia. La comparación de modelos se realiza en el tercer nivel de inferencia para ajustar automáticamente los parámetros de la función del kernel y seleccionar las entradas relevantes. La formulación LS-SVM permite derivar expresiones analíticas en el espacio de rasgos y las expresiones prácticas se obtienen en el espacio dual reemplazando al producto interno por la función del núcleo relacionada usando el teorema de Mercers. Los resultados de predicción un paso adelante obtenidos sobre la predicción de la tasa semanal de billetes de 90 días y los precios de cierre diarios de DAX30 muestran que se pueden hacer predicciones significativas de signos de muestra con respecto a la prueba de Pesaran-Timmerman, (LS-SVM) para predecir la tasa semanal de T-bill de 90 días y los precios de cierre diarios de DAX30. TAY, Francis E. H. y Lijuan CAO, 2001. Aplicación de máquinas vectoriales de apoyo en la previsión de series temporales financieras. Omega: La Revista Internacional de Ciencias de la Gestión. Volumen 29, Número 4, Agosto 2001, páginas 309 - 317. Este artículo trata de la aplicación de una técnica de red neuronal novedosa, la máquina vectorial de apoyo (SVM), en la predicción de series temporales financieras. El objetivo de este trabajo es examinar la viabilidad de SVM en la predicción de series de tiempo financiero comparándola con una red neuronal de múltiples capas de retroproyección (BP). Cinco contratos de futuros reales que se recopilan del Mercado Mercantil de Chicago se utilizan como los conjuntos de datos. El experimento muestra que la SVM supera a la red neural de BP con base en los criterios del error cuadrático medio normalizado (NMSE), el error absoluto medio (MAE), la simetría direccional (DS) y la simetría direccional ponderada (WDS). Dado que no existe una forma estructurada de elegir los parámetros libres de las MVS, se investiga la variabilidad en el rendimiento con respecto a los parámetros libres en este estudio. El análisis de los resultados experimentales demostró que es ventajoso aplicar SVMs a las series de tiempo financiero previstas. Se descubrió que una SVM superó a una red neuronal de múltiples capas de retroproyección (BP) en cinco contratos de futuros reales del Chicago Mercantile Market. TAY, Francis E. H. y L. J. CAO, 2002. Máquinas de vectores de soporte modificadas en la predicción de series temporales financieras. Neurocomputing. Volumen 48, números 1-4, octubre de 2002, páginas 847-861. Citado por 54 (12.86 / año) Resumen: Este artículo propone una versión modificada de máquinas vectoriales de apoyo, denominadas C-ascending support vector machine, para modelar series temporales no estacionarias financieras. Las máquinas de vectores de soporte ascendentes C se obtienen mediante una simple modificación de la función de riesgo regularizada en máquinas de vectores de soporte, con lo que los errores 949 insensibles recientes son penalizados más intensamente que los errores distantes 949-insensibles. Este procedimiento se basa en el conocimiento previo de que en la serie de tiempo financiero no estacionario la dependencia entre las variables de entrada y la variable de salida cambia gradualmente a lo largo del tiempo, específicamente, los últimos datos pasados ​​podrían proporcionar información más importante que los datos del pasado lejano. En el experimento, las máquinas C-ascending vector de soporte se ponen a prueba utilizando tres futuros reales recogidos en el mercado mercantil de Chicago. Se muestra que las máquinas de vectores de apoyo en C con los datos de muestra realmente ordenados predicen consistentemente mejor que las máquinas de vectores de soporte estándar, con el peor rendimiento cuando se usan los datos de muestra ordenados de forma inversa. Además, las máquinas de vectores de apoyo en cascada C usan menos vectores de soporte que los de las máquinas de vectores de soporte estándar, dando como resultado una representación más dispersa de máquinas vectoriales de soporte de C orientadas a solución, que penalizan errores 949 recientes más sensibles que distantes 949-errores insensibles, y encontraron que pronostican mejor que SVMs estándar en tres futuros verdaderos recogidos del mercado mercantil de Chicago. HUANG, Zan, et al. . 2004. Análisis de calificación crediticia con máquinas vectoriales de apoyo y redes neuronales: un estudio comparativo de mercado. Sistemas de Soporte a la Decisión . Volumen 37, Número 4 (Septiembre 2004), Páginas 543-558. Citado por 21 (9.55 / año) Resumen: El análisis de calificación crediticia empresarial ha atraído muchos intereses de investigación en la literatura. Estudios recientes han demostrado que los métodos de Inteligencia Artificial (IA) alcanzaron un mejor rendimiento que los métodos estadísticos tradicionales. Este artículo presenta una técnica de aprendizaje de máquina relativamente nueva, máquinas de vector de apoyo (SVM), al problema en el intento de proporcionar un modelo con mejor poder explicativo. Utilizamos la red neural de retropropagación (BNN) como referencia y obtuvimos una precisión de predicción de alrededor de 80 para los métodos BNN y SVM para los mercados de Estados Unidos y Taiwán. Sin embargo, sólo se observó una ligera mejora de la SVM. Otra dirección de la investigación es mejorar la interpretabilidad de los modelos basados ​​en la IA. Se aplicaron los resultados de la investigación reciente en la interpretación de modelos de redes neuronales y se obtuvo la importancia relativa de las variables financieras de entrada de los modelos de red neuronal. En base a estos resultados, se realizó un análisis comparativo de mercado sobre las diferencias de factores determinantes en los mercados de Estados Unidos y Taiwán. Aplicó las redes neuronales de retropropagación y las SVM a la predicción de la calificación crediticia corporativa para los mercados de Estados Unidos y Taiwán y encontró que los resultados eran comparables (Ambos fueron superiores a la regresión logística), con el SVM un poco mejor. CAO, Lijuan, 2003. Apoyo a los expertos de máquinas de vectores para la previsión de series de tiempo. Neurocomputing. Volumen 51, abril de 2003, páginas 321-339. Citado por 29 (9.08 / año) Resumen: Este artículo propone el uso de los expertos en máquinas de vector de soporte (SVMs) para la predicción de series de tiempo. Los expertos generalizados SVMs tienen una arquitectura de red neuronal en dos etapas. En la primera etapa, el mapa de características autoorganizables (SOM) se utiliza como un algoritmo de agrupación para dividir todo el espacio de entrada en varias regiones disjuntas. En la partición se adopta una arquitectura estructurada en árbol para evitar el problema de predeterminar el número de regiones particionadas. Luego, en la segunda etapa, se construyen SVMs múltiples, también llamados expertos SVM, que se ajustan mejor a las regiones particionadas, encontrando la función de núcleo más adecuada y los parámetros libres óptimos de SVMs. Los datos de las manchas solares, los conjuntos de datos A, C y D de Santa Fe y los dos conjuntos de datos de construcción se evalúan en el experimento. La simulación muestra que los expertos de SVMs logran una mejora significativa en el rendimiento de generalización en comparación con los modelos de SVMs individuales. Además, los expertos en SVM también convergen más rápido y usan menos vectores de soporte. Demostró que su método de expertos SVM logró una mejora significativa sobre los modelos SVM únicos cuando se aplicó al conjunto de datos de Santa Fe C (tasas de cambio de alta frecuencia entre el franco suizo y el Dólar estadounidense). KIM, Kyoung-jae, 2003. Previsiones de series de tiempo financieras utilizando máquinas de vectores de apoyo. Neurocomputing. Volumen 55, Ediciones 1-2 (Septiembre 2003), Páginas 307-319. Las máquinas vectoriales de apoyo (SVMs) son métodos prometedores para la predicción de series cronológicas financieras porque utilizan una función de riesgo consistente en el error empírico y un término regularizado que se deriva de la minimización del riesgo estructural principio. Este estudio aplica SVM a la predicción del índice de precios de las acciones. Además, este estudio examina la viabilidad de la aplicación de SVM en el pronóstico financiero, comparándolo con las redes neuronales de retropropagación y el razonamiento basado en casos. Los resultados experimentales muestran que la SVM proporciona una alternativa prometedora a la predicción del mercado de valores. Se encontró que las SVMs superaron las redes neuronales de retropropagación y el razonamiento basado en casos cuando se utilizó para pronosticar el índice diario de precios de las acciones de Corea. SHIN Kyung-Shik, Taik Soo LEE y Hyun-jung KIM, 2005. Una aplicación de máquinas de vectores de apoyo en el modelo de predicción de bancarrota. Sistemas Expertos con Aplicaciones . Volumen 28, Número 1, enero de 2005, páginas 127-135. Citado por 8 (6.67 / año) Resumen: Este estudio investiga la eficacia de la aplicación de máquinas de vectores de soporte (SVM) al problema de predicción de quiebra. Aunque es un hecho bien conocido que la red neural de propagación posterior (BPN) funciona bien en tareas de reconocimiento de patrones, el método tiene algunas limitaciones en que es un arte encontrar una estructura de modelo apropiada y una solución óptima. Además, se necesita cargar la mayor cantidad de entrenamiento posible en la red para buscar los pesos de la red. Por otro lado, dado que SVM capta las características geométricas del espacio de características sin derivar pesos de las redes a partir de los datos de entrenamiento, es capaz de extraer la solución óptima con el pequeño tamaño del conjunto de entrenamiento. En este estudio, mostramos que el clasificador propuesto del enfoque SVM supera a BPN al problema de la predicción de quiebra corporativa. Los resultados demuestran que la precisión y el rendimiento de generalización de SVM es mejor que el de BPN a medida que el tamaño del conjunto de entrenamiento se hace más pequeño. También examinamos el efecto de la variabilidad en el rendimiento con respecto a varios valores de parámetros en SVM. Además, investigar y resumir los varios puntos superiores del algoritmo SVM en comparación con BPN. Demostrado que los SVMs mejor que las redes neuronales de retroprotección cuando se aplica a la predicción de quiebra corporativa. CAO, L. J. y Francis E. H. TAY, 2003. Máquina Vector de Soporte con Parámetros Adaptativos en la Previsión Financiera de Series de Tiempo. IEEE Transacciones en Redes Neuronales. Volumen 14, Número 6, noviembre de 2003, páginas 1506-1518. Un nuevo tipo de máquina de aprendizaje llamada máquina vectorial de soporte (SVM) ha estado recibiendo un interés creciente en áreas que van desde su aplicación original en el reconocimiento de patrones hasta otras aplicaciones como la estimación de regresión debido a su notable generalización actuación. Este artículo trata de la aplicación de SVM en la predicción de series temporales financieras. La viabilidad de la aplicación de SVM en la predicción financiera se examina primero comparándola con la red neuronal de múltiples capas de retroproyección (BP) y la red neural de la función de base radial regularizada (RBF). La variabilidad en el rendimiento de SVM con respecto a los parámetros libres se investiga experimentalmente. Los parámetros adaptativos se proponen entonces incorporando la no estaciona - riedad de las series de tiempo financiero en SVM. Cinco contratos de futuros reales recopilados del Mercado Mercantil de Chicago se utilizan como conjuntos de datos. La simulación muestra que entre los tres métodos, SVM supera a la red neural BP en el pronóstico financiero, y hay un rendimiento de generalización comparable entre SVM y la red regularizada RNF neural. Además, los parámetros libres de SVM tienen un gran efecto en el rendimiento de generalización. SVM con parámetros adaptativos puede lograr un mayor rendimiento de generalización y utilizar menos vectores de soporte que el SVM estándar en la predicción financiera. Utilizó una SVM, una red neuronal de back-propagation (BP) multicapa y una red neural de función radial regularizada (RBF) para predecir Cinco contratos de futuros reales recogidos del Mercado Mercantil de Chicago. Los resultados mostraron que la SVM y la red regularizada RBF neural eran comparables y ambos superaron a la red neural de la PA. CAO, Lijuan y Francis E. H. TAY, 2001. Pronóstico Financiero Usando Máquinas de Vector de Apoyo. Aplicaciones de amplificación de computación neural. Volumen 10, Número 2 (Mayo 2001), Páginas 184-192. El uso de Máquinas de Soporte Vectorial (SVMs) se estudia en el pronóstico financiero comparándolo con un perceptron de múltiples capas entrenado por el algoritmo de Propagación Trasera (BP). Los SVMs pronostican mejor que BP basándose en los criterios de error de cuadratura media normalizada (NMSE), error promedio absoluto (MAE), simetría direccional (DS), corrección de la tendencia hacia arriba (CP) y corrección hacia abajo (CD). El índice de precios diario SampP 500 se utiliza como conjunto de datos. Dado que no existe una forma estructurada para elegir los parámetros libres de SVMs, el error de generalización con respecto a los parámetros libres de SVMs se investiga en este experimento. Como se ilustra en el experimento, tienen poco impacto en la solución. El análisis de los resultados experimentales demuestra que es ventajoso aplicar SVMs para pronosticar la serie de tiempo financiero. Se encontró que los SVMs predicen el índice de precios diario SampP 500 mejor que un perceptron multi-capa entrenado por el algoritmo Back Propagation (BP). MIN, Jae H. y Young-Chan LEE, 2005. Predicción de bancarrota utilizando la máquina vectorial de soporte con la elección óptima de los parámetros de la función del núcleo. Sistemas Expertos con Aplicaciones . Volumen 28, Número 4, Mayo de 2005, páginas 603-614. La predicción de quiebra ha atraído muchos intereses de investigación en literatura anterior, y estudios recientes han demostrado que las técnicas de aprendizaje mecánico alcanzaron un mejor rendimiento que las estadísticas tradicionales. En este trabajo se aplican las máquinas vectoriales de apoyo (SVMs) al problema de la predicción de bancarrota en un intento de sugerir un nuevo modelo con mejor poder explicativo y estabilidad. Para servir a este propósito, utilizamos una técnica de búsqueda de cuadrícula utilizando 5 veces la validación cruzada para averiguar los valores óptimos de los parámetros de la función del núcleo de SVM. Además, para evaluar la precisión predictiva de SVM, comparamos su rendimiento con los de análisis discriminante múltiple (MDA), análisis de regresión logística (Logit) y redes neuronales de retropropilación (BPNs) totalmente conectadas y de tres capas. Los resultados de los experimentos demuestran que la SVM supera a los otros métodos. Se descubrió que, cuando se aplicaban a la predicción de bancarrota, las SVM superaban el análisis discriminante múltiple (MDA), el análisis de regresión logística (Logit) y las redes neuronales de retropropilación (BPNs). ABRAHAM, Ajith, Ninan Sajith PHILIP y P. SARATCHANDRAN, 2003. Modelando el comportamiento caótico de índices bursátiles usando paradigmas inteligentes. Neural, Cálculo Cálculo Paralelo Científico. Volumen 11, páginas 143-160. Citado por 10 (4,55 / año) Resumen: Se ha establecido ampliamente el uso de sistemas inteligentes para predicciones bursátiles. En este artículo, investigamos cómo el comportamiento aparentemente caótico de los mercados de valores podría estar bien representado utilizando varios paradigmas conexionistas y técnicas de computación blanda. Para demostrar las diferentes técnicas, se consideró el índice Nasdaq-100 de Nasdaq Stock Market SM y el índice de acciones SP CNX NIFTY. Se analizaron los valores del índice principal del Nasdaq 100 de 7 años y los valores del índice NIFTY de 4 años. Este trabajo investiga el desarrollo de una técnica confiable y eficiente para modelar el comportamiento aparentemente caótico de los mercados de valores. Se consideró una red neuronal artificial entrenada utilizando el algoritmo de Levenberg-Marquardt, Máquina de Vector de Soporte (SVM), modelo neurofuzzy de Takagi-Sugeno y una Red Neural de Impulso de Diferencia (DBNN). Este trabajo explica brevemente cómo los diferentes paradigmas conexionistas pueden ser formulados usando diferentes métodos de aprendizaje y luego investiga si pueden proporcionar el nivel de rendimiento requerido, que son suficientemente buenos y robustos para proporcionar un modelo de predicción confiable para los índices bursátiles. Aplicaron cuatro técnicas diferentes, una red neural artificial entrenada usando el algoritmo de Levenberg-Marquardt, una máquina de vector de apoyo, una red neural de aumento de la diferencia y un Takagi-Sugeno El sistema de inferencia fuzzy aprendido usando un algoritmo de red neuronal (modelo neuro-fuzzy) a la predicción del índice Nasdaq-100 del Nasdaq Stock Market y el índice de acciones SP CNX NIFTY. Ninguna técnica fue claramente superior, pero absurdamente, tratan de predecir el valor absoluto de los índices, en lugar de usar retornos de registros. YANG, Haiqin, Laiwan CHAN y Irwin KING, 2002. Regresión de la máquina del vector de la ayuda para la predicción volátil del mercado de acción. En: Ingeniería de Datos Inteligente y Aprendizaje Automatizado: IDEAL 2002. Editado por Hujun Yin, et al. . Páginas 391 - 396, Springer. Recientemente, se ha introducido la Regresión Vectorial de Apoyo (SVR) para resolver problemas de regresión y predicción. En este artículo, aplicamos SVR a las tareas de predicción financiera. En particular, los datos financieros suelen ser ruidosos y el riesgo asociado es variable en el tiempo. Por lo tanto, nuestro modelo SVR es una extensión de la SVR estándar que incorpora la adaptación de los márgenes. Al variar los márgenes de la RVS, podríamos reflejar el cambio en la volatilidad de los datos financieros. Además, hemos analizado el efecto de los márgenes asimétricos para permitir la reducción del riesgo a la baja. Nuestros resultados experimentales muestran que el uso de la desviación estándar para calcular un margen variable da un buen resultado predictivo en la predicción del Índice de Hang Seng. Se trata de variar los márgenes en la regresión SVM para reflejar el cambio en la volatilidad de los datos financieros y también analizó el Efecto de los márgenes asimétricos para permitir la reducción del riesgo a la baja. El primer enfoque produjo el error total más bajo al predecir el precio de cierre diario del índice Hang Seng de Hong Kong (HSI). HUANG, W. Y. NAKAMORI y S. Y. WANG, 2005. Predicción de la dirección del mercado de valores con la máquina de vector de apoyo. Computadoras Investigación Operativa. Volumen 32, Número 10, páginas 2513-2522. (SVM) es un tipo muy específico de algoritmos de aprendizaje caracterizados por el control de capacidad de la función de decisión, el uso de las funciones del núcleo y la escasez de la solución . En este artículo, investigamos la previsibilidad de la dirección del movimiento financiero con SVM mediante la predicción de la dirección de movimiento semanal del índice NIKKEI 225. Para evaluar la capacidad de predicción de SVM, comparamos su desempeño con los de Análisis Discriminante Lineal, Análisis Discriminante Cuadrático y Redes Neuronales de Backpropagación Elman. Los resultados del experimento muestran que la SVM supera a los otros métodos de clasificación. Además, proponemos un modelo de combinación mediante la integración de SVM con los otros métodos de clasificación. El modelo combinado se desempeña mejor entre todos los métodos de pronóstico comparado con la capacidad de SVMs, Análisis Discriminante Lineal, Análisis Discriminante Cuadrático y Redes Neuronales de Backpropagación Elman para pronosticar la dirección de movimiento semanal del índice NIKKEI 225 y encontró que el SVM superó a todos los otros métodos de clasificación . Mejor aún era una combinación ponderada de los modelos. TRAFALIS, Theodore B. y Huseyin INCE, 2000. Apoyo a la máquina vectorial para la regresión y aplicaciones a la previsión financiera. En: IJCNN 2000: Actas de la Conferencia Conjunta Internacional IEEE-INNS-ENNS sobre Redes Neuronales: Volumen 6 editado por Shun-Ichi Amari, et al. . Página 6348, IEEE Computer Society. El propósito principal de este trabajo es comparar la máquina de vectores de soporte (SVM) desarrollada por Vapnik con otras técnicas como las redes de Backpropagation y Radial Basis Function (RBF) para aplicaciones de pronóstico financiero. La teoría del algoritmo SVM se basa en la teoría del aprendizaje estadístico. El entrenamiento de SVM conduce a un problema de programación cuadrática (QP). Los resultados computacionales preliminares para la predicción del precio de las acciones también se presentan con SVMs compartidas con redes Backpropagation y Radial Base Function (RBF) al predecir los precios de las acciones diarias de IBM, Yahoo y America Online. Curiosamente, utilizando el SVM para la regresión que forwent un conjunto de validación, establecer epsilon a cero, C fijo y repetido el experimento para varios ajustes fijos del parámetro kernel, sigma, dando lugar a varios resultados. CAO, Lijuan y Qingming GU, 2002. Máquinas dinámicas del vector de la ayuda para la predicción no estacionaria de la serie de tiempo. Análisis inteligente de datos. Volumen 6, Número 1, páginas 67-83. Este artículo propone una versión modificada de máquinas vectoriales de apoyo (MVS), denominadas máquinas dinámicas de soporte vectorial (DSVM), para modelar series temporales no estacionarias. Las DSVM se obtienen mediante la incorporación del conocimiento del dominio del problema - no estacionariedad de series de tiempo en SVMs. A diferencia de las SVM estándar que utilizan valores fijos de la constante de regularización y el tamaño del tubo en todos los puntos de datos de entrenamiento, las DSVM utilizan una constante de regularización exponencialmente creciente y un tamaño de tubo exponencialmente decreciente para tratar con cambios estructurales en los datos. La constante de regularización dinámica y el tamaño del tubo se basan en el conocimiento previo de que en la serie temporal no estacionaria los puntos de datos recientes podrían proporcionar información más importante que puntos de datos lejanos. En el experimento, las DSVMs se evalúan utilizando conjuntos de datos simulados y reales. La simulación muestra que las DSVM generalizan mejor que las SVM estándar en la predicción de series temporales no estacionarias. Otra ventaja de esta modificación es que las DSVM utilizan menos vectores de soporte, lo que da como resultado una representación más dispersa de la solución. Incorporan el conocimiento previo de que las series temporales financieras son no estacionarias en sus máquinas vectoriales dinámicas de soporte (DSVMs) y usan una constante de regularización exponencialmente creciente Un tamaño de tubo que disminuye exponencialmente para hacer frente a cambios estructurales en los datos sobre la suposición de que los puntos de datos recientes podrían proporcionar información más importante que puntos de datos lejanos. Concluyen que las DSVM generalizan mejor que las SVM estándar en la predicción de series temporales no estacionarias, mientras que también utilizan menos vectores de soporte, resultando en una representación más dispersa de la solución. TAY, Francis E. H. y L. J. CAO, 2002. 949-Máquinas de vectores descendentes de apoyo para la previsión de series de tiempo financieras. Neural Processing Letters 15 (2): 179 - 195. Este artículo propone una versión modificada de máquinas vectoriales de apoyo (SVM), denominadas 949-máquinas de vectores de apoyo descendentes (949-DSVM), para modelar series temporales financieras no estacionarias. Los 949-DSVMs se obtienen incorporando el problema de dominio 8211 no estacionariedad de series de tiempo financiero en SVMs. A diferencia de los SVM estándar que utilizan un tubo constante en todos los puntos de datos de entrenamiento, los 949-DSVMs utilizan un tubo adaptativo para hacer frente a los cambios en la estructura de los datos. El experimento muestra que el 949-DSVMs generalizar mejor que el estándar SVMs en la previsión Series temporales financieras no estacionarias. Otra ventaja de esta modificación es que los 949-DSVM convergen a menos vectores de soporte, dando como resultado una más escasa representación de la solución. Incorporó el conocimiento del dominio de problema de no estacionariedad de series de tiempo financiero en SVMs usando un tubo adaptativo en su denominado Epsilon-descendientes máquinas de soporte vectorial (epsilon-DSVMs). Los experimentos mostraron que los epsilon-DSVMs generalizan mejor que los SVM estándar en la predicción de series temporales financieras no estacionarias y también convergen a menos vectores de soporte, resultando en una representación más escasa de la solución. DEBNATH, Sandip y C. Lee GILES, 2005. Un Modelo de Aprendizaje Basado en la Extracción de Artículos de Noticias para Encontrar Sentencias Explicativas para Eventos. En: K-CAP 821705: Actas de la III Conferencia Internacional sobre Captura de Conocimiento. Páginas 189-190. Citado por 2 (1.67 / año) Resumen: La información sobre metadatos desempeña un papel crucial en el aumento de la eficiencia y la archivabilidad de la organización de documentos. Los metadatos de noticias incluyen DateLine. ByLine. HeadLine y muchos otros. Encontramos que la información de HeadLine es útil para adivinar el tema del artículo de noticias. Particularmente para artículos de noticias financieras, encontramos que HeadLine puede ser especialmente útil para localizar oraciones explicativas para cualquier evento importante, tales como cambios significativos en los precios de las acciones. En este artículo exploramos un enfoque de aprendizaje basado en el vector de soporte para extraer automáticamente los metadatos de HeadLine. Encontramos que la exactitud de clasificación de encontrar el HeadLine s mejora si DateLine s se identifican primero. A continuación, utilizamos el HeadLine extraído s para iniciar un patrón de coincidencia de palabras clave para encontrar las oraciones responsables de tema de la historia. Usando este tema y un modelo de lenguaje simple es posible localizar cualquier oración explicativa para cualquier cambio significativo de precios. Se ha diseñado un nuevo enfoque para extraer los metadatos de noticias HeadLines usando SVMs y usarlos para encontrar temas de la historia para obtener una explicación basada en oraciones para un stock cambio de precio. Van GESTEL, Tony, et al. . 2003. Un acercamiento de la máquina del vector de la ayuda a la calificación de crédito. Banco en Financiewezen. Volumen 2, marzo, páginas 73-82. Citado por 5 (1.56 / año) Resumen: Impulsados ​​por la necesidad de asignar capital de manera rentable y por los recientemente sugeridos reglamentos de Basilea II, las instituciones financieras están cada vez más obligadas a construir modelos de calificación crediticia que evalúen el riesgo de incumplimiento de sus clientela. Se han sugerido muchas técnicas para abordar este problema. Support Vector Machines (SVMs) es una nueva técnica prometedora que ha emanado recientemente de diferentes dominios como las estadísticas aplicadas, las redes neuronales y el aprendizaje automático. En este trabajo, experimentamos con máquinas vectoriales de soporte de mínimos cuadrados (LS-SVMs), una versión recientemente modificada de SVMs, e informamos de resultados significativamente mejores cuando se contrastan con las técnicas clásicasparadas cuatro metodologías, mínimos cuadrados ordinarios (OLS) OLR), el Multilayer Perceptron (MLP) y los mínimos cuadrados soportan las máquinas vectoriales (LS-SVMs) cuando se aplican a la puntuación de crédito. La metodología SVM arrojó resultados significativos y consistentemente mejores que los métodos de clasificación lineal clásica. FAN, Alan y Marimuthu PALANISWAMI, 2000. Selección de los predictores de quiebra utilizando un enfoque de máquina vectorial de apoyo. IJCNN 2000: Actas de la Conferencia Internacional Conjunta IEEE-INNS-ENNS sobre Redes Neuronales, Volumen 6. Editado por Shun-Ichi Amari et al. . Página 6354. Citado por 9 (1.45 / año) Resumen: El enfoque de redes neuronales convencionales se ha encontrado útil para predecir la angustia corporativa de los estados financieros. En este artículo, hemos adoptado un enfoque de Soporte Técnico de Vectores para el problema. Se muestra una nueva forma de seleccionar los predictores de quiebra, utilizando el criterio basado en la distancia euclidiana calculado dentro del núcleo SVM. Se realiza un estudio comparativo utilizando tres modelos clásicos de socorro corporativo y un modelo alternativo basado en el enfoque SVM. Utilice SVMs para seleccionar los predictores de quiebra y proporcione un estudio comparativo. TAY, Francis Eng Hock y Li Juan CAO, 2001. Mejora de la previsión de las series de tiempo financiero mediante la combinación de Máquinas de Soporte Vectorial con mapa de características auto-organizadas. Análisis inteligente de datos. Volumen 5, Número 4, Páginas 339-354. Se propone una arquitectura de red neuronal en dos etapas construida mediante la combinación de Máquinas de Soporte Vectorial (SVMs) con un mapa de características autoorganizadoras (SOM) para la previsión de series temporales financieras. En la primera etapa, SOM se utiliza como un algoritmo de agrupación para dividir todo el espacio de entrada en varias regiones disjuntas. En la partición se adopta una arquitectura estructurada en árbol para evitar el problema de predeterminar el número de regiones particionadas. Luego, en la segunda etapa, se construyen SVMs múltiples, también llamados expertos SVM, que mejor se ajustan a cada región particionada, mediante la búsqueda de la función de kernel más apropiada y los parámetros de aprendizaje óptimos de SVMs. En el experimento se utilizan el tipo de cambio de Santa Fe y cinco contratos de futuros reales. Se muestra que el método propuesto alcanza un rendimiento de predicción significativamente más alto y una velocidad de convergencia más rápida en comparación con un SVM único modelo combinado SVMs con un mapa de característica autoorganizadora (SOM) y probó el modelo en el tipo de cambio de Santa Fe y cinco contratos de futuros reales . Mostraron que su método propuesto alcanza un rendimiento de predicción significativamente más alto y una velocidad de convergencia más rápida en comparación con un solo modelo SVM. SANSOM, D. C. T. DOWNS y T. K. SAHA, 2003. Evaluación de la herramienta de predicción basada en la máquina vectorial de soporte en la previsión de precios de la electricidad para participantes del mercado eléctrico nacional de Australia. Journal of Electrical Electronics Engineering, Australia. Vol. 22, No. 3, páginas 227 - 234. En este artículo presentamos un análisis de los resultados de un estudio sobre predicción de precios de electricidad al por mayor (spot) utilizando Redes Neuronales (NNs) y Máquinas de Vector de Apoyo (SVM, por sus siglas en inglés). Los cambios frecuentes en la reglamentación de los mercados de la electricidad y la rápida evolución de las estrategias de fijación de precios de los participantes en los mercados (licitaciones) hacen que la reconversión eficiente sea crucial para mantener la exactitud de los modelos de previsión de precios de la electricidad. The efficiency of NN and SVM retraining for price forecasting was evaluated using Australian National Electricity Market (NEM), New South Wales regional data over the period from September 1998 to December 1998. The analysis of the results showed that SVMs with one unique solution, produce more consistent forecasting accuracies and so require less time to optimally train than NNs which can result in a solution at any of a large number of local minima. The SVM and NN forecasting accuracies were found to be very similar. evaluated utilising Neural Networks (NNs) and Support Vector Machines (SVM) for wholesale (spot) electricity price forecasting. The SVM required less time to optimally train than the NN, whilst the SVM and NN forecasting accuracies were found to be very similar. ABRAHAM, Ajith and Andy AUYEUNG, 2003. Integrating Ensemble of Intelligent Systems for Modeling Stock Indices. In: Proceedings of 7th International Work Conference on Artificial and Natural Neural Networks, Part II . Lecture Notes in Computer Science, Volume 2687, Jose Mira and Jose R. Alverez (Eds.), Springer Verlag, Germany, pp. 774-781, 2003. Cited by 3 (0.94/year) Abstract: The use of intelligent systems for stock market predictions has been widely established. In this paper, we investigate how the seemingly chaotic behavior of stock markets could be well-represented using ensemble of intelligent paradigms. To demonstrate the proposed technique, we considered Nasdaq-100 index of Nasdaq Stock Market SM and the SampP CNX NIFTY stock index. The intelligent paradigms considered were an artificial neural network trained using Levenberg-Marquardt algorithm, support vector machine, Takagi-Sugeno neuro-fuzzy model and a difference boosting neural network. The different paradigms were combined using two different ensemble approaches so as to optimize the performance by reducing the different error measures. The first approach is based on a direct error measure and the second method is based on an evolutionary algorithm to search the optimal linear combination of the different intelligent paradigms. Experimental results reveal that the ensemble techniques performed better than the individual methods and the direct ensemble approach seems to work well for the problem considered. considered an artificial neural network trained using Levenberg-Marquardt algorithm, a support vector machine, a Takagi-Sugeno neuro-fuzzy model and a difference boosting neural network for predicting the NASDAQ-100 Index of The Nasdaq Stock Market and the SP CNX NIFTY stock index. They concluded that an ensemble of the intelligent paradigms performed better than the individual methods. YANG, Haiqin, et al. . 2004. Financial Time Series Prediction Using Non-fixed and Asymmetrical Margin Setting with Momentum in Support Vector Regression. In: Neural Information Processing: Research and Development . edited by Jagath Chandana Rajapakse and Lipo Wang, Springer-Verlag. Cited by 2 (0.91/year) Abstract: Recently, Support Vector Regression (SVR) has been applied to financial time series prediction. The financial time series usually contains the characteristics of small sample size, high noise and non-stationary. Especially the volatility of the time series is time-varying and embeds some valuable information about the series. Previously, we had proposed to use the volatility in the data to adaptively change the width of the margin in SVR. We have noticed that up margin and down margin would not necessary be the same, and we also observed that their choice would affect the upside risk, downside risk and as well as the overall prediction performance. In this work, we introduce a novel approach to adopt the momentum in the asymmetrical margins setting. We applied and compared this method to predict the Hang Seng Index and Dow Jones Industrial Average. used SVMs for regression with non-fixed and asymmetrical margin settings, this time with momentum, to predict the Hang Seng Index and Dow Jones Industrial Average. PAI, Ping-Feng and Chih-Sheng LIN, 2005. A hybrid ARIMA and support vector machines model in stock price forecasting. Omega . Volume 33, Issue 6, December 2005, Pages 497-505. Cited by 1 (0.84/year) Abstract: Traditionally, the autoregressive integrated moving average (ARIMA) model has been one of the most widely used linear models in time series forecasting. However, the ARIMA model cannot easily capture the nonlinear patterns. Support vector machines (SVMs), a novel neural network technique, have been successfully applied in solving nonlinear regression estimation problems. Therefore, this investigation proposes a hybrid methodology that exploits the unique strength of the ARIMA model and the SVMs model in forecasting stock prices problems. Real data sets of stock prices were used to examine the forecasting accuracy of the proposed model. The results of computational tests are very promising. proposed a hybrid ARIMA and support vector machine model for stock price forecasting, and results looked very promising. ABRAHAM, Ajith, et al. . 2002. Performance Analysis of Connectionist Paradigms for Modeling Chaotic Behavior of Stock Indices. In: Second international workshop on Intelligent systems design and application . edited by Ajith Abraham, et al. . pages 181--186. Cited by 3 (0.71/year) Abstract: The use of intelligent systems for stock market predictions has been widely established. In this paper, we investigate how the seemingly chaotic behavior of stock markets could be well represented using several connectionist paradigms and soft computing techniques. To demonstrate the different techniques, we considered Nasdaq-100 index of Nasdaq Stock MarketTM and the SP CNX NIFTY stock index. We analyzed 7 years Nasdaq 100 main index values and 4 years NIFTY index values. This paper investigates the development of a reliable and efficient technique to model the seemingly chaotic behavior of stock markets. We considered an artificial neural network trained using Levenberg-Marquardt algorithm, Support Vector Machine (SVM), Takagi-Sugeno neuro-fuzzy model and a Difference Boosting Neural Network (DBNN). This paper briefly explains how the different connectionist paradigms could be formulated using different learning methods and then investigates whether they can provide the required level of performance, which are sufficiently good and robust so as to provide a reliable forecast model for stock market indices. Experiment results reveal that all the connectionist paradigms considered could represent the stock indices behavior very accurately. analysed the performance of an artificial neural network trained using Levenberg-Marquardt algorithm, Support Vector Machine (SVM), Takagi-Sugeno neuro-fuzzy model and a Difference Boosting Neural Network (DBNN) when predicting the NASDAQ-100 Index of The Nasdaq Stock Market and the SP CNX NIFTY stock index. YANG, Haiqin, I. KING and Laiwan CHAN, 2002. Non-fixed and asymmetrical margin approach to stock market prediction using Support Vector Regression. In: ICONIP 02. Proceedings of the 9th International Conference on Neural Information Processing. Volume 3 . edited by Lipo Wang, et al. . pages 1398--1402. Cited by 3 (0.71/year) Abstract: Recently, support vector regression (SVR) has been applied to financial time series prediction. Typical characteristics of financial time series are non-stationary and noisy in nature. The volatility, usually time-varying, of the time series is therefore some valuable information about the series. Previously, we had proposed to use the volatility to adaptively change the width of the margin of SVR. We have noticed that upside margin and downside margin do not necessary be the same, and we have observed that their choice would affect the upside risk, downside risk and as well as the overall prediction result. In this paper, we introduce a novel approach to adapt the asymmetrical margins using momentum. We applied and compared this method to predict the Hang Seng Index and Dow Jones Industrial Average. used SVM regression with a non-fixed and asymmetrical margin, this time adapting the asymmetrical margins using momentum, and applied it to predicting the Hang Seng Index and the Dow Jones Industrial Average. GAVRISHCHAKA, Valeriy V. and Supriya B. GANGULI, 2003. Volatility forecasting from multiscale and high-dimensional market data. Neurocomputing . Volume 55, Issues 1-2 (September 2003), Pages 285-305. Cited by 2 (0.63/year) Abstract: Advantages and limitations of the existing volatility models for forecasting foreign-exchange and stock market volatility from multiscale and high-dimensional data have been identified. Support vector machines (SVM) have been proposed as a complimentary volatility model that is capable of effectively extracting information from multiscale and high-dimensional market data. SVM-based models can handle both long memory and multiscale effects of inhomogeneous markets without restrictive assumptions and approximations required by other models. Preliminary results with foreign-exchange data suggest that SVM can effectively work with high-dimensional inputs to account for volatility long-memory and multiscale effects. Advantages of the SVM-based models are expected to be of the utmost importance in the emerging field of high-frequency finance and in multivariate models for portfolio risk management. used SVMs for forecasting the volatility of foreign-exchange data. Their preliminary benchmark tests indicated that SVMs can perform significantly better than or comparable to both naive and GARCH(1,1) models. P201REZ-CRUZ, Fernando, Julio A. AFONSO-RODR205GUEZ and Javier GINER, 2003. Estimating GARCH models using support vector machines. Quantitative Finance . Volume 3, Number 3 (June 2003), Pages 163-172. Cited by 2 (0.63/year) Abstract: Support vector machines (SVMs) are a new nonparametric tool for regression estimation. We will use this tool to estimate the parameters of a GARCH model for predicting the conditional volatility of stock market returns. GARCH models are usually estimated using maximum likelihood (ML) procedures, assuming that the data are normally distributed. In this paper, we will show that GARCH models can be estimated using SVMs and that such estimates have a higher predicting ability than those obtained via common ML methods. used SVMs for regression to estimate the parameters of a GARCH model for predicting the conditional volatility of stock market returns and showed that such estimates have a higher predicting ability than those obtained via common maximum likelihood (ML) methods. Van GESTEL, T. et al. . 2003. Bankruptcy prediction with least squares support vector machine classifiers. In: 2003 IEEE International Conference on Computational Intelligence for Financial Engineering: Proceedings . pages 1-8. Cited by 2 (0.63/year) Abstract: Classification algorithms like linear discriminant analysis and logistic regression are popular linear techniques for modelling and predicting corporate distress. These techniques aim at finding an optimal linear combination of explanatory input variables, such as, e. g. solvency and liquidity ratios, in order to analyse, model and predict corporate default risk. Recently, performant kernel based nonlinear classification techniques, like support vector machines, least squares support vector machines and kernel fisher discriminant analysis, have been developed. Basically, these methods map the inputs first in a nonlinear way to a high dimensional kernel-induced feature space, in which a linear classifier is constructed in the second step. Practical expressions are obtained in the so-called dual space by application of Mercers theorem. In this paper, we explain the relations between linear and nonlinear kernel based classification and illustrate their performance on predicting bankruptcy of mid-cap firms in Belgium and the Netherlands. used least squares support vector machine classifiers for predicting bankruptcy of mid-cap firms in Belgium and the Netherlands. CAO, L. J. and W. K. CHONG, 2002. Feature extraction in support vector machine: a comparison of PCA, XPCA and ICA. ICONIP 02: Proceedings of the 9th International Conference on Neural Information Processing, Volume 2 . edited by Lipo Wang, et al. . pages 1001-1005. Cited by 2 (0.48/year) Abstract: Recently, support vector machine (SVM) has become a popular tool in time series forecasting. In developing a successful SVM forecaster, feature extraction is the first important step. This paper proposes the applications of principal component analysis (PCA), kernel principal component analysis (KPCA) and independent component analysis (ICA) to SVM for feature extraction. PCA linearly transforms the original inputs into uncorrelated features. KPCA is a nonlinear PCA developed by using the kernel method. In ICA, the original inputs are linearly transformed into statistically independent features. By examining the sunspot data and one real futures contract, the experiment shows that SVM by feature extraction using PCA, KPCA or ICA can perform better than that without feature extraction. Furthermore, there is better generalization performance in KPCA and ICA feature extraction than PCA feature extraction. considered the application of principal component analysis (PCA), kernel principal component analysis (KPCA) and independent component analysis (ICA) to SVMs for feature extraction. By examining the sunspot data and one real futures contract, they showed that SVM by feature extraction using PCA, KPCA or ICA can perform better than that without feature extraction. Furthermore, they found that there is better generalization performance in KPCA and ICA feature extraction than PCA feature extraction. CAO, L. J. and Francis E. H. TAY, 2000. Feature Selection for Support Vector Machines in Financial Time Series Forecasting. In: Intelligent Data Engineering and Automated Learning - IDEAL 2000: Data Mining, Financial Engineering, and Intelligent Agents . edited by Kwong Sak Leung, Lai-Wan Chan and Helen Meng, pages 268-273. Cited by 3 (0.48/year) Abstract: This paper deals with the application of saliency analysis to Support Vector Machines (SVMs) for feature selection. The importance of feature is ranked by evaluating the sensitivity of the network output to the feature input in terms of the partial derivative. A systematic approach to remove irrelevant features based on the sensitivity is developed. Five futures contracts are examined in the experiment. Based on the Simulation results, it is shown that that saliency analysis is effective in SVMs for identifying important features. dealt with the application of saliency analysis to feature selection for SVMs. Five futures contracts were examined and they concluded that saliency analysis is effective in SVMs for identifying important features. ZHOU, Dianmin, Feng GAO and Xiaohong GUAN, 2004. Application of accurate online support vector regression in energy price forecast. WCICA 2004: Fifth World Congress on Intelligent Control and Automation, Volume 2 . pages 1838-1842. Cited by 1 (0.45/year) Abstract: Energy price is the most important indicator in electricity markets and its characteristics are related to the market mechanism and the change versus the behaviors of market participants. It is necessary to build a real-time price forecasting model with adaptive capability. In this paper, an accurate online support vector regression (AOSVR) method is applied to update the price forecasting model. Numerical testing results show that the method is effective in forecasting the prices of the electric-power markets. applied an accurate online support vector regression (AOSVR) to forecasting the prices of the electric-power markets, results showed that it was effective. FAN, A. and M. PALANISWAMI, 2001. Stock selection using support vector machines. IJCNN01: International Joint Conference on Neural Networks, Volume 3 . Pages 1793-1798. Cited by 2 (0.38/year) Abstract: We used the support vector machines (SVM) in a classification approach to beat the market. Given the fundamental accounting and price information of stocks trading on the Australian Stock Exchange, we attempt to use SVM to identify stocks that are likely to outperform the market by having exceptional returns. The equally weighted portfolio formed by the stocks selected by SVM has a total return of 208 over a five years period, significantly outperformed the benchmark of 71. We also give a new perspective with a class sensitivity tradeoff, whereby the output of SVM is interpreted as a probability measure and ranked, such that the stocks selected can be fixed to the top 25used SVMs for classification for stock selection on the Australian Stock Exchange and significantly outperformed the benchmark. Van GESTEL, Tony, et al. . 2000. Volatility Tube Support Vector Machines. Neural Network World . Vol. 10, number 1, pp. 287-297. Cited by 2 (0.32/year) Abstract: In Support Vector Machines (SVM8217s), a non-linear model is estimated based on solving a Quadratic Programming (QP) problem. The quadratic cost function consists of a maximum likelihood cost term with constant variance and a regularization term. By specifying a difference inclusion on the noise variance model, the maximum likelihood term is adopted for the case of heteroskedastic noise, which arises in financial time series. The resulting Volatility Tube SVM8217s are applied on the 1-day ahead prediction of the DAX30 stock index. The influence of todays closing prices of the New York Stock Exchange on the prediction of tomorrow8217s DAX30 closing price is analyzed. developed the Volatility Tube SVM and applied it to 1-day ahead prediction of the DAX30 stock index, and significant positive out-of-sample results were obtained. CAO, Li Juan, Kok Seng CHUA and Lim Kian GUAN, 2003. Combining KPCA with support vector machine for time series forecasting. In: 2003 IEEE International Conference on Computational Intelligence for Financial Engineering . pages 325-329. Cited by 1 (0.31/year) Abstract: Recently, support vector machine (SVM) has become a popular tool in time series forecasting. In developing a successful SVM forecaster, the first important step is feature extraction. This paper applies kernel principal component analysis (KPCA) to SVM for feature extraction. KPCA is a nonlinear PCA developed by using the kernel method. It firstly transforms the original inputs into a high dimensional feature space and then calculates PCA in the high dimensional feature space. By examining the sunspot data and one real futures contract, the experiment shows that SVM by feature forms much better than that extraction using KPCA per without feature extraction. In comparison with PCA, there is also superior performance in KPCA. applied kernel principal component analysis (KPCA) to SVM for feature extraction. The authors examined sunspot data and one real futures contract, and found such feature extraction enhanced performance and also that KPCA was superior to PCA. YANG, Haiqin, 2003. Margin Variations in Support Vector Regression for the Stock Market Prediction. Degree of Master of Philosophy Thesis, Department of Computer Science Engineering, The Chinese University of Hong Kong, June 2003. Cited by 1 (0.31/year) Abstract: Support Vector Regression (SVR) has been applied successfully to financial time series prediction recently. In SVR, the 949-insensitive loss function is usually used to measure the empirical risk. The margin in this loss function is fixed and symmetrical. Typically, researchers have used methods such as crossvalidation or random selection to select a suitable 949 for that particular data set. In addition, financial time series are usually embedded with noise and the associated risk varies with time. Using a fixed and symmetrical margin may have more risk inducing bad results and may lack the ability to capture the information of stock market promptly. In order to improve the prediction accuracy and to consider reducing the downside risk, we extend the standard SVR by varying the margin. By varying the width of the margin, we can reflect the change of volatility in the financial data by controlling the symmetry of margins, we are able to reduce the downside risk. Therefore, we focus on the study of setting the width of the margin and also the study of its symmetry property. For setting the width of margin, the Momentum (also including asymmetrical margin control) and Generalized Autoregressive Conditional Heteroskedasticity (GARCH) models are considered. Experiments are performed on two indices: Hang Seng Index (HSI) and Dow Jones Industrial Average (DJIA) for the Momentum method and three indices: Nikkei225, DJIA and FTSE100, for GARCH models, respectively. The experimental results indicate that these methods improve the predictive performance comparing with the standard SVR and benchmark model. On the study of the symmetry property, we give a sufficient condition to prove that the predicted value is monotone decreasing to the increase of the up margin. Therefore, we can reduce the predictive downside risk, or keep it zero, by increasing the up margin. An algorithm is also proposed to test the validity of this condition, such that we may know the changing trend of predictive downside risk by only running this algorithm on the training data set without performing actual prediction procedure. Experimental results also validate our analysis. employs SVMs for regression and varys the width of the margin to reflect the change of volatility and controls the symmetry of margins to reduce the downside risk. Results were positive. CALVO, Rafael A. and Ken WILLIAMS, 2002. Automatic Categorization of Announcements on the Australian Stock Exchange. Cited by 1 (0.24/year) Abstract: This paper compares the performance of several machine learning algorithms for the automatic categorization of corporate announcements in the Australian Stock Exchange (ASX) Signal G data stream. The article also describes some of the applications that the categorization of corporate announcements may enable. We have performed tests on two categorization tasks: market sensitivity, which indicates whether an announcement will have an impact on the market, and report type, which classifies each announcement into one of the report categories defined by the ASX. We have tried Neural Networks, a Na239ve Bayes classifier, and Support Vector Machines and achieved good resultspared the performance of neural networks, a na ve bayes classifier, and SVMs for the automatic categorization of corporate announcements in the Australian Stock Exchange (ASX) Signal G data stream. The results were all good, but with the SVM underperforming the other two models. AHMED, A. H.M. T. 2000. Forecasting of foreign exchange rate time series using support vector regression. 3rd year project. Computer Science Department, University of Manchester. Cited by 1 (0.16/year)used support vector regression for forecasting a foreign exchange rate time series. GUESDE, Bazile, 2000. Predicting foreign exchange rates with support vector regression machines. MSc thesis. Computer Science Department, University of Manchester. Cited by 1 (0.16/year) Abstract: This thesis investigates how Support Vector Regression can be applied to forecasting foreign exchange rates. At first we introduce the reader to this non linear kernel based regression and demonstrate how it can be used for time series prediction. Then we define a predictive framework and apply it to the Canadian exchange rates. But the non-stationarity in the data, which we here define as a drift in the map of the dynamics, forces us to present and use the typical learning processes for catching different dynamics. Our implementation of these solutions include Clusters of Volatility and competing experts. Finally those experts are used in a financial vote trading system and substantial profits are achieved. Through out the thesis we hope the reader will be intrigued by the results of our analysis and be encouraged in other dircetions for further research. used SVMs for regression to predict the Canadian exchange rate, wisely recognised the problem of nonstationarity, dealt with it using experts and claimed that substantial profits were achieved. BAO, Yu-Kun, et al. . 2005. Forecasting Stock Composite Index by Fuzzy Support Vector Machines Regression. Proceedings of 2005 International Conference on Machine Learning and Cybernetics, Volume 6 . pages 3535-3540. not cited (0/year) Abstract: Financial time series forecasting methods such as exponential smoothing are commonly used for prediction on stock composition index (SCI) and have made great contribution in practice, but efforts on looking for superior forecasting method are still made by practitioners and academia. This paper deals with the application of a novel neural network technique, fuzzy support vector machines regression (FSVMR), in SCI forecasting. The objective of this paper is not only to examine the feasibility of FSVMR in SCI forecasting but presents our efforts on improving the accuracy of FSVMR in terms of data pre-processing, kernel function selection and parameters selection. A data set from Shanghai Stock Exchange is used for the experiment to test the validity of FSVMR. The experiment shows FSVMR a better method in SCI forecasting. used fuzzy support vector machines regression (FSVMR) to forecast a data set from the Shanghai Stock Exchange with positive results. CHEN, Kuan-Yu and Chia-Hui HO, 2005. An Improved Support Vector Regression Modeling for Taiwan Stock Exchange Market Weighted Index Forecasting. ICNNB 05: International Conference on Neural Networks and Brain, 2005, Volume 3 not cited (0/year) Abstract: This study applies a novel neural network technique, Support Vector Regression (SVR), to Taiwan Stock Exchange Market Weighted Index (TAIEX) forecasting. To build an effective SVR model, SVRs parameters must be set carefully. This study proposes a novel approach, known as GA-SVR, which searches for SVRs optimal parameters using real value genetic algorithms. The experimental results demonstrate that SVR outperforms the ANN and RW models based on the Normalized Mean Square Error (NMSE), Mean Square Error (MSE) and Mean Absolute Percentage Error (MAPE). Moreover, in order to test the importance and understand the features of SVR model, this study examines the effects of the number of input node. used an SVM for regression for forecasting the Taiwan Stock Exchange Market Weighted Index (TAIEX). The results demonstrated that the SVR outperformed the ANN and RW models. CHEN, Wun-Hwa and Jen-Ying SHIH, 2006. A study of Taiwan39s issuer credit rating systems using support vector machines. Expert Systems with Applications . Volume 30, Issue 3, April 2006, Pages 427-435. not cited (0/year) By providing credit risk information, credit rating systems benefit most participants in financial markets, including issuers, investors, market regulators and intermediaries. In this paper, we propose an automatic classification model for issuer credit ratings, a type of fundamental credit rating information, by applying the support vector machine (SVM) method. This is a novel classification algorithm that is famous for dealing with high dimension classifications. We also use three new variables: stock market information, financial support by the government, and financial support by major shareholders to enhance the effectiveness of the classification. Previous research has seldom considered these variables. The data period of the input variables used in this study covers three years, while most previous research has only considered one year. We compare our SVM model with the back propagation neural network (BP), a well-known credit rating classification method. Our experiment results show that the SVM classification model performs better than the BP model. The accuracy rate (84.62) is also higher than previous research. used an SVM to classify Taiwans issuer credit ratings and found that it performed better than the back propagation neural network (BP) model. CHEN, Wun-Hua, Jen-Ying SHIH and Soushan WU, 2006. Comparison of support-vector machines and back propagation neural networks in forecasting the six major Asian stock markets. International Journal of Electronic Finance . Volume, Issue 1, pages 49-67. not cited (0/year) Abstract: Recently, applying the novel data mining techniques for financial time-series forecasting has received much research attention. However, most researches are for the US and European markets, with only a few for Asian markets. This research applies Support-Vector Machines (SVMs) and Back Propagation (BP) neural networks for six Asian stock markets and our experimental results showed the superiority of both models, compared to the early researchespared SVMs and back propagation (BP) neural networks when forecasting the six major Asian stock markets. Both models perform better than the benchmark AR (1) model in the deviation measurement criteria, whilst SVMs performed better than the BP model in four out of six markets. GAVRISHCHAKA, Valeriy V. and Supriya BANERJEE, 2006. Support Vector Machine as an Efficient Framework for Stock Market Volatility Forecasting. Computational Management Science . Volume 3, Number 2 (April 2006), Pages 147-160. not cited (0/year) Abstract: Advantages and limitations of the existing models for practical forecasting of stock market volatility have been identified. Support vector machine (SVM) have been proposed as a complimentary volatility model that is capable to extract information from multiscale and high-dimensional market data. Presented results for SP500 index suggest that SVM can efficiently work with high-dimensional inputs to account for volatility long-memory and multiscale effects and is often superior to the main-stream volatility models. SVM-based framework for volatility forecasting is expected to be important in the development of the novel strategies for volatility trading, advanced risk management systems, and other applications dealing with multi-scale and high-dimensional market data. used SVMs for forecasting stock market volatility with positive results. HOVSEPIAN, K. and P. ANSELMO, 2005. Heuristic Solutions to Technical Issues Associated with Clustered Volatility Prediction using Support Vector Machines. ICNNampB3905: International Conference on Neural Networks and Brain, 2005, Volume 3 . Pages 1656-1660. not cited (0/year) Abstract: We outline technological issues and our fimdings for the problem of prediction of relative volatility bursts in dynamic time-series utilizing support vector classifiers (SVC). The core approach used for prediction has been applied successfully to detection of relative volatility clusters. In applying it to prediction, the main issue is the selection of the SVC training/testing set. We describe three selection schemes and experimentally compare their performances in order to propose a method for training the SVC for the prediction problem. In addition to performing cross-validation experiments, we propose an improved variation to sliding window experiments utilizing the output from SVCs decision function. Together with these experiments, we show that accurate and robust prediction of volatile bursts can be achieved with our approach. used SVMs for classification to predict relative volatility clusters and achieved accurate and robust results. INCE, H. and T. B. TRAFALIS, 2004. Kernel principal component analysis and support vector machines for stock price prediction. Proceedings of the 2004 IEEE International Joint Conference on Neural Networks, Volume 3 . pages 2053-2058. not cited (0/year) Abstract: Financial time series are complex, non-stationary and deterministically chaotic. Technical indicators are used with principal component analysis (PCA) in order to identify the most influential inputs in the context of the forecasting model. Neural networks (NN) and support vector regression (SVR) are used with different inputs. Our assumption is that the future value of a stock price depends on the financial indicators although there is no parametric model to explain this relationship. This relationship comes from technical analysis. Comparison shows that SVR and MLP networks require different inputs. The MLP networks outperform the SVR technique. found that MLP neural networks outperform support vector regression when applied to stock price prediction. KAMRUZZAMAN, Joarder, Ruhul A SARKER and Iftekhar AHMAD, 2003. SVM Based Models for Predicting Foreign Currency Exchange Rates. Proceedings of the Third IEEE International Conference on Data Mining (ICDM03) . Pages 557-560. not cited (0/year) Abstract: Support vector machine (SVM) has appeared as a powerful tool for forecasting forex market and demonstrated better performance over other methods, e. g. neural network or ARIMA based model. SVM-based forecasting model necessitates the selection of appropriate kernel function and values of free parameters: regularization parameter and varepsilon - insensitive loss function. In this paper, we investigate the effect of different kernel functions, namely, linear, polynomial, radial basis and spline on prediction error measured by several widely used performance metrics. The effect of regularization parameter is also studied. The prediction of six different foreign currency exchange rates against Australian dollar has been performed and analyzed. Some interesting results are presented. investigated the effect of different kernel functions and the regularization parameter when using SVMs to predict six different foreign currency exchange rates against the Australian dollar. investigated comprehensible credit scoring models using rule extraction from SVMs. NALBANTOV, Georgi, Rob BAUER and Ida SPRINKHUIZEN-KUYPER, 2006. Equity Style Timing Using Support Vector Regressions. to appear in Applied Financial Economics . not cited (0/year) Abstract: The disappointing performance of value and small cap strategies shows that style consistency may not provide the long-term benefits often assumed in the literature. In this study we examine whether the short-term variation in the U. S. size and value premium is predictable. We document style-timing strategies based on technical and (macro-)economic predictors using a recently developed artificial intelligence tool called Support Vector Regressions (SVR). SVR are known for their ability to tackle the standard problem of overfitting, especially in multivariate settings. Our findings indicate that both premiums are predictable under fair levels of transaction costs and various forecasting horizons. used SVMs for regression for equity style timing with positive results. ONGSRITRAKUL, P. and N. SOONTHORNPHISAJ, 2003. Apply decision tree and support vector regression to predict the gold price. Proceedings of the International Joint Conference on Neural Networks, 2003, Volume 4 . Pages 2488-2492. not cited (0/year) Abstract: Recently, support vector regression (SVR) was proposed to resolve time series prediction and regression problems. In this paper, we demonstrate the use of SVR techniques for predicting the cost of gold by using factors that have an effect on gold to estimate its price. We apply a decision tree algorithm for the feature selection task and then perform the regression process using forecasted indexes. Our experimental results show that the combination of the decision tree and SVR leads to a better performance. applied a decision tree algorithm for feature selection and then performed support vector regression to predict the gold price, their results were positive. Van GESTEL, Tony, et al. . 2005. Linear and non-linear credit scoring by combining logistic regression and support vector machines, Journal of Credit Risk . Vol. 1, No. 4, Fall 2005, Pages 31-60. not cited (0/year) Abstract: The Basel II capital accord encourages banks to develop internal rating models that are financially intuitive, easily interpretable and optimally predictive for default. Standard linear logistic models are very easily readable but have limited model flexibility. Advanced neural network and support vector machine models (SVMs) are less straightforward to interpret but can capture more complex multivariate non-linear relations. A gradual approach that balances the interpretability and predictability requirements is applied here to rate banks. First, a linear model is estimated it is then improved by identifying univariate non-linear ratio transformations that emphasize distressed conditions and finally SVMs are added to capture remaining multivariate non-linear relations. apply linear and non-linear credit scoring by combining logistic regression and SVMs. YANG, Haiqin, et al. . 2004. Outliers Treatment in Support Vector Regression for Financial Time Series Prediction. Neural Information Processing: 11th International Conference, ICONIP 2004, Calcutta, India, November 2004, Proceedings not cited (0/year) Abstract: Recently, the Support Vector Regression (SVR) has been applied in the financial time series prediction. The financial data are usually highly noisy and contain outliers. Detecting outliers and deflating their influence are important but hard problems. In this paper, we propose a novel 8220two-phase8221 SVR training algorithm to detect outliers and reduce their negative impact. Our experimental results on three indices: Hang Seng Index, NASDAQ, and FSTE 100 index show that the proposed 8220two-phase8221 algorithm has improvement on the prediction. proposed a novel two-phase SVR training procedure to detect and deflate the influence of outliers. The method was tested on the Hang Seng Index, NASDAQ and FSTE 100 index and results were positive. However, its not clear why the significance of outliers (such as market crashes) should be understated. YU, Lean, Shouyang WANG and Kin Keung LAI, 2005. Mining Stock Market Tendency Using GA-Based Support Vector Machines. Internet and Network Economics: First International Workshop, WINE 2005, Hong Kong, China, December 15-17, 2005, Proceedings (Lecture Notes in Computer Science) edited by Xiaotie Deng and Yinyu Ye, pages 336-345. not cited (0/year) Abstract: In this study, a hybrid intelligent data mining methodology, genetic algorithm based support vector machine (GASVM) model, is proposed to explore stock market tendency. In this hybrid data mining approach, GA is used for variable selection in order to reduce the model complexity of SVM and improve the speed of SVM, and then the SVM is used to identify stock market movement direction based on the historical data. To evaluate the forecasting ability of GASVM, we compare its performance with that of conventional methods (e. g. statistical models and time series models) and neural network models. The empirical results reveal that GASVM outperforms other forecasting models, implying that the proposed approach is a promising alternative to stock market tendency exploration. applied a random walk (RW) model, an autoregressive integrated moving average (ARIMA) model, an individual back-propagation neural network (BPNN) model, an individual SVM model and a genetic algorithm-based SVM (GASVM) to the task of predicting the direction of change in the daily SP500 stock price index and found that their proposed GASVM model performed the best. HARLAND, Zac, 2002. Using Support Vector Machines to Trade Aluminium on the LME.. Proceedings of the Ninth International Conference, Forecasting Financial Markets: Advances For Exchange Rates, Interest Rates and Asset Management . edited by C. Dunis and M. Dempster. not listed Abstract: This paper describes and evaluates the use of support vector regression to trade the three month Aluminium futures contract on the London Metal Exchange, over the period June 1987 to November 1999. The Support Vector Machine is a machine learning method for classification and regression and is fast replacing neural networks as the tool of choice for prediction and pattern recognition tasks, primarily due to their ability to generalise well on unseen data. The algorithm is founded on ideas derived from statistical learning theory and can be understood intuitively within a geometric framework. In this paper we use support vector regression to develop a number of trading submodels that when combined, result in a final model that exhibits above-average returns on out of sample data, thus providing some evidence that the aluminium futures price is less than efficient. Whether these inefficiencies will continue into the future is unknown. used an ensemble of SVMs for regression to trade the three month Aluminium futures contract on the London Metal Exchange with positive results. Van GESTEL, T. et al. . 2005. Credit rating systems by combining linear ordinal logistic regression and fixed-size least squares support vector machines, Workshop on Machine Learning in Finance, NIPS 2005 Conference, Whistler (British Columbia, Canada), Dec. 9.not listeddeveloped credit rating systems by combining linear ordinal logistic regression and fixed-size least squares SVMs. Machine Learning and Its Application in Forex Markets WORKING MODEL In the last post we covered Machine learning (ML) concept in brief. In this post we explain some more ML terms, and then frame rules for a forex strategy using the SVM algorithm in R. To use ML in trading, we start with historical data (stock price/forex data) and add indicators to build a model in R/Python/Java. We then select the right Machine learning algorithm to make the predictions. First, lets look at some of the terms related to ML. Machine Learning algorithms There are many ML algorithms (list of algorithms ) designed to learn and make predictions on the data. ML algorithms can be either used to predict a category (tackle classification problem) or to predict the direction and magnitude (tackle regression problem). Predict the price of a stock in 3 months from now, on the basis of companys past quarterly results. Predict whether Fed will hike its benchmark interest rate. Indicators/Features Indicators can include Technical indicators (EMA, BBANDS, MACD, etc.), Fundamental indicators, or/and Macroeconomic indicators. Example 1 8211 RSI(14), Price SMA(50). and CCI(30). We can use these three indicators, to build our model, and then use an appropriate ML algorithm to predict future values. Example 2 8211 RSI(14), RSI(5), RSI(10), Price SMA(50), Price SMA(10), CCI(30), CCI(15), CCI(5) In this example we have selected 8 indicators. Some of these indicators may be irrelevant for our model. In order to select the right subset of indicators we make use of feature selection techniques. Feature selection It is the process of selecting a subset of relevant features for use in the model. Feature selection techniques are put into 3 broad categories: Filter methods, Wrapper based methods and embedded methods. To select the right subset we basically make use of a ML algorithm in some combination. The selected features are known as predictors in machine learning. Support Vector Machine (SVM) SVM is a well-known algorithm for supervised Machine Learning, and is used to solve both for classification and regression problem. A SVM algorithm works on the given labeled data points, and separates them via a boundary or a Hyperplane. SVM tries to maximize the margin around the separating hyperplane. Support vectors are the data points that lie closest to the decision surface. Framing rules for a forex strategy using SVM in R 8211 Given our understanding of features and SVM, let us start with the code in R. We have selected the EUR/USD currency pair with a 1 hour time frame dating back to 2010. Indicators used here are MACD (12, 26, 9). and Parabolic SAR with default settings of (0.02, 0.2). First, we load the necessary libraries in R, and then read the EUR/USD data. We then compute MACD and Parabolic SAR using their respective functions available in the TTR package. To compute the trend, we subtract the closing EUR/USD price from the SAR value for each data point. We lag the indicator values to avoid look-ahead bias. We also create an Up/down class based on the price change. Thereafter we merge the indicators and the class into one data frame called model data. The model data is then divided into training, and test data. We then use the SVM function from the e1071 package and train the data. We make predictions using the predict function and also plot the pattern. We are getting an accuracy of 53 here. From the plot we see two distinct areas, an upper larger area in red where the algorithm made short predictions, and the lower smaller area in blue where it went long. SAR indicator trails price as the trend extends over time. SAR is below prices when prices are rising and above prices when prices are falling. SAR stops and reverses when the price trend reverses and breaks above or below it. We are interested in the crossover of Price and SAR, and hence are taking trend measure as the difference between price and SAR in the code. Similarly, we are using the MACD Histogram values, which is the difference between the MACD Line and Signal Line values. Looking at the plot we frame our two rules and test these over the test data. Short rule (PriceSAR) gt -0.0025 amp (Price SAR) lt 0.0100 amp MACD gt -0.0010 amp MACD lt 0.0010 Long rule (PriceSAR) gt -0.0150 amp (Price SAR) lt -0.0050 amp MACD gt -0.0005 We are getting 54 accuracy for our short trades and an accuracy of 50 for our long trades. The SVM algorithm seems to be doing a good job here. We stop at this point, and in our next post on Machine learning we will see how framed rules like the ones devised above can be coded and backtested to check the viability of a trading strategy. To learn more on Machine Learning you can watch the latest webinar, Machine Learning in Trading , which was hosted by QuantInsti, and conducted by our guest speaker Tad Slaff, CEO/Co-founder Inovance. Machine learning is covered in the Executive Programme in Algorithmic Trading (EPAT) course conducted by QuantInsti. To know more about EPAT check the EPAT course page or feel free to contact our team at contactquantinsti for queries on EPAT. Download R Code Login to access this file for FREESVM Based Models for Predicting Foreign Currency Exchange Rates Concepts in SVM Based Models for Predicting Foreign Currency Exchange Rates Bureau de change A bureau de change or currency exchange is a business whose customers exchange one currency for another. Although originally French, the term bureau de change is widely used throughout Europe, and European travellers can usually easily identify these facilities when in other European countries. It is also common to find a sign saying Exchange or Change. Since the adoption of the euro, many exchange offices incorporate its logotype prominently on their signage. more from Wikipedia Foreign exchange market The foreign exchange market (forex, FX, or currency market) is a form of exchange for the global decentralized trading of international currencies. Los centros financieros en todo el mundo funcionan como anclas del comercio entre una amplia gama de diferentes tipos de compradores y vendedores durante todo el día, con la excepción de los fines de semana. El mercado de divisas determina los valores relativos de las diferentes monedas. more from Wikipedia Support vector machine A support vector machine (SVM) is a concept in statistics and computer science for a set of related supervised learning methods that analyze data and recognize patterns, used for classification and regression analysis. The standard SVM takes a set of input data and predicts, for each given input, which of two possible classes forms the input, making the SVM a non-probabilistic binary linear classifier. more from Wikipedia Exchange rate In finance, an exchange rate (also known as the foreign-exchange rate, forex rate or FX rate) between two currencies is the rate at which one currency will be exchanged for another. It is also regarded as the value of one countrys currency in terms of another currency. For example, an interbank exchange rate of 91 Japanese yen (JPY, ) to the United States dollar (US) means that 91 will be exchanged for each US1 or that US1 will be exchanged for each 91. more from Wikipedia Positive-definite kernel In operator theory, a branch of mathematics, a positive definite kernel is a generalization of a positive-definite matrix. more from Wikipedia Forecasting Forecasting is the process of making statements about events whose actual outcomes (typically) have not yet been observed. A commonplace example might be estimation of some variable of interest at some specified future date. Prediction is a similar, but more general term. Both might refer to formal statistical methods employing time series, cross-sectional or longitudinal data, or alternatively to less formal judgemental methods. more from Wikipedia Regularization (mathematics) In mathematics and statistics, particularly in the fields of machine learning and inverse problems, regularization involves introducing additional information in order to solve an ill-posed problem or to prevent overfitting. This information is usually of the form of a penalty for complexity, such as restrictions for smoothness or bounds on the vector space norm. A theoretical justification for regularization is that it attempts to impose Occams razor on the solution. more from Wikipedia Tools and Resources Publisher Site Contact Us Switch to single page view (no tabs) Javascript is not enabled and is required for the tabbed view or switch to the single page view The ACM Digital Library is published by the Association for Computing Machinery. Copyright copy 2016 ACM, Inc. Terms of Usage Privacy Policy Code of Ethics Contact Us Did you know the ACM DL App is now available Did you know your Organization can subscribe to the ACM Digital Library The ACM Guide to Computing Literature