A Hybrid EMD-ANN Model for Stock Price Prediction 股票价格预测的混合EMD-ANN模型.pdfVIP

A Hybrid EMD-ANN Model for Stock Price Prediction B Dhanya Jothimani( ) , Ravi Shankar, and Surendra S. Yadav Department of Management Studies, Indian Institute of Technology Delhi, New Delhi, India dhanyajothimani@ Abstract. Financial time series such as foreign exchange rate and stock index, in general, exhibit non-linear and non-stationary behavior. Sta- tistical models and machine learning models, often, fail to predict time series with such behavior. Former models are prone to large statistical errors. While machine learning models such as Support Vector Machines (SVM) and Artificial Neural Network (ANN) suffer from the limitations of overfitting and getting stuck in local minima, etc. In this paper, a hybrid model integrating the advantages of Empirical Mode Decomposi- tion (EMD) and ANN is used to predict the short-term forecasts of Nifty stock index. In first stage, EMD is used to decompose the time series into a set of subseries, namely, intrinsic mode function (IMF) and residue component. In the next stage, ANN is used to predict each IMF indepen- dently along with residue component. The results show that the hybrid EMD-ANN model outperformed both SVR and ANN models without decomposition. Keywords: Hybrid EMD-ANN model · EMD · ANN · SVR · Nifty · Time series 1 Introduction The non-linear and non-stationary behavior of financial time series makes them difficult to predict. Several statistical and computational intelligent techniques have been proposed. [1] and [2] have compared and analyzed the role of these techniques for stoc