Prediction of Time Series Data Using GA-BPNN Based Hybrid ANN Model

Abstract

Time series analysis has drawn the attention of many researchers as the findings from analysis are of huge importance and value. Although there exists many models for Time Series Prediction, there is still no single model which can accurately predict data, this is because of the wide range of existing applications. Artificial Neural Networks are widely used for forecasting data because of its high capability to understand non linear relationships among data. An appropriate combination of neural algorithms can provide better prediction results for time series data. This paper aimed at hybridizing the traditional Back Propagation Neural Network (BPNN) with Genetic Algorithm(GA) to achieve better prediction accuracy. Levenberg Marquardt Algorithm(LMA) is chosen as the Back Propagation algorithm. The proposed model is tested on L&T stock market data, Air Quality data, Surface roughness and Concrete Strength data and the performance measures of both BPNN and GA-BPNN are evaluated using the standard error measures such as Mean Squared Error(MSE), Mean Absolute Error(MAE) and Root Mean Square Error(RMSE). The proposed model proves to produce better prediction results than the existing BPNN networks for both univariate and multivariate data sets.