Escudo de la República de Colombia
Sistema Nacional de Biliotecas - Repositorio Institucional Universidad Nacional de Colombia Biblioteca Digital - Repositorio Institucional UN Sistema Nacional de Bibliotecas UN

Short-Term Forecasting of Financial Time Series with Deep Neural Networks

Arévalo Murillo, Andrés Ricardo (2016) Short-Term Forecasting of Financial Time Series with Deep Neural Networks. Maestría thesis, Universidad Nacional de Colombia - Sede Bogotá.

Texto completo

Vista previa
PDF - Versión Aceptada
Available under License Creative Commons Attribution Non-commercial No Derivatives.



In this work, a high-frequency strategy using Deep Neural Networks (DNNs) is presented. The input information to the DNN consists of: (i). Current time (hour and minute); (ii). the last n one-minute pseudo-returns, where n is the sliding window size parameter; (iii). the last n one-minute standard deviations of the price; (iv). The last n trend indicator, computed as the slope of the linear model fitted using the transaction prices inside a particular minute. The output DNN prediction is the next one-minute pseudo-return, this output is later transformed to obtain the next one-minute average price forecasting. The DNN predictions are used to build a high-frequency trading strategy that buys (sells) when the next predicted average price is above (below) the last closing price. This high-frequency trading strategy is only applicable to high liquidity stocks, because it requires to open and close positions in a time interval equal or less than one minute. For experimental testing, this work uses three datasets: (i). Apple stock (ticker: AAPL) from September to November of 2008. (ii). Apple stock (ticker: AAPL) from August of 2015 to August of 2016. (iii). Google stock (ticker: GOOG) from August of 2015 to August of 2016. Apple Inc. and Google Inc. are high liquidity stocks. The period of the first dataset covers the stock crash during the financial crisis of 2008. During this crash, the AAPL price suffered a dramatic fall from 172 to 98 dollars. This first dataset was chosen intentionally for demonstrate the performance of the proposed strategy under high volatility conditions. Whereas the second and third datasets were chosen in order to test the proposed strategy in normal market conditions. Multiple DNNs with different sliding window size parameter n and number of hidden layers L were trained. The best-performing-found DNN has a 65% of directional accuracy.

Tipo de documento:Tesis/trabajos de grado - Thesis (Maestría)
Colaborador / Asesor:Hernandez Perez, German Jairo
Información adicional:Master in Systems and Computer Engineering. Research lines: Applied Computing and Intelligent Systems
Palabras clave:Short-term Forecasting, High-frequency Trading, Computational Finance, Deep Neural Networks
Temática:0 Generalidades / Computer science, information & general works
Unidad administrativa:Sede Bogotá > Facultad de Ingeniería > Departamento de Ingeniería de Sistemas e Industrial > Ingeniería de Sistemas
Código ID:54538
Enviado por : Andrés Ricardo Arévalo Murillo
Enviado el día :12 Dec 2016 20:05
Ultima modificación:12 Dec 2016 20:05
Ultima modificación:12 Dec 2016 20:05
Exportar:Clic aquí
Estadísticas:Clic aquí

Solamente administradores del repositorio: página de control del ítem

Vicerrectoría de Investigación: Número uno en investigación
Indexado por:
Indexado por Scholar Google WorldCat DRIVER Metabiblioteca OAIster BASE BDCOL Registry of Open Access Repositories SNAAC Red de repositorios latinoamericanos eprints Open archives La referencia Tesis latinoamericanas OpenDOAR CLACSO
Este sitio web se ve mejor en Firefox