Predicting Financial Time Series Data Using Hybrid Model

Abstract

Prediction of Financial time series is described as one of the most challenging tasks of time series prediction, due to its characteristics and their dynamic nature. Support vector regression (SVR), Support vector machine (SVM) and back propagation neural network (BPNN) are the most popular data mining techniques in prediction financial time series. In this paper a hybrid combination model is introduced to combine the three models and to be most beneficial of them all. Quantization factor is used in this paper for the first time to improve the single SVM and SVR prediction output. And also genetic algorithm (GA) used to determine the weights of the proposed model. FTSE100, S&P 500 and Nikkei 225 daily index closing prices are used to evaluate the proposed model performance. The proposed hybrid model numerical results shows the outperform result over all other single model, traditional simple average combiner and the traditional time series model Autoregressive (AR).

Comparing Forecasts of GARCH (1, 1)-M and GARCH (1, 1)-M-ANNs Model: A Study Based On Stock Market Data

“…Integrated systems of random walk (RW)-feed-forward ANNs and random walk-Elman ANNs models were developed to forecast exchange rate by (Adhikari and Agrawal, 2014). A combined approach of back-propagation ANNs with support vector regression (SVR) and support vector machine (SVM) for Financial Times Stock Exchange 100 Index (FTS100), S and P500 and Nikkie 225 daily closing indices were developed by (Al-hnaity and Abbod, 2016). Different combinations of empirical models and ANNs have been applied to improve financial data forecast such as: ARIMA, ARCH/GARCH, EGARCH, APGARCH, GJR and NPGARCH models were combined with ANNs (Zhang, 2003;Fatima and Hussain, 2008;Bildirici and Ersin, 2009;Lahmiri, 2017;Chkili and Hamdi, 2021).…”