2026-04-13T18:47:26Zhttps://recercat.cat/oai/request

oai:recercat.cat:2099.1/264182025-07-23T07:09:41Zcom_2072_1033col_2072_452951

Multivariate dynamic Kernels for financial time series forecasting Peña-Grass, Mauricio Universitat Politècnica de Catalunya. Departament de Ciències de la Computació Arratia Quesada, Argimiro Alejandro Belanche Muñoz, Luis Antonio Àrees temàtiques de la UPC::Matemàtiques i estadística::Estadística matemàtica Statistics -- Applications Support vector machine regression Dynamic kernels Hyperparameters selection Variable length time series Financial market forecasting Compressed data Estadística matemàtica--Aplicacions Classificació AMS::62 Statistics::62P Applications This thesis proposes a novel forecasting method that elaborates on the capability of integrating information measured at different frequencies and at irregular time intervals in financial markets. A data compression process is developed to take a whole range of financial time series and analyze their temporal information through multivariate dynamic kernels within a statistical machine learning algorithm, namely support vector machines. A number of dynamic kernels are designed to make the computational process more tractable without sacrifice on accuracy. Unlike most publications in the field, a complete analytical framework directly from the training data is provided for tuning hyperparameters. Experiments, based on predicting the S&P500 market, show promising results. Other potential applications of dynamic kernels are envisioned in such diverse areas as risk measurement, bioinformatics and industrial processes. 2015-06 Master thesis https://hdl.handle.net/2099.1/26418 FME-1145 eng Restricted access - author's decision application/pdf Universitat Politècnica de Catalunya Universitat de Barcelona