International Journal of Engineering and Information Systems (IJEAIS)   Year: 2019 | Volume: 3 | Issue: 1 | Page No.: 1-13 Empirical Mode Decomposition Based Ensemble Random Forest Model for Financial Time Series Forecasting Utpala Nanda Chowdhury, Sanjoy Kumar Chakravarty, Md. Tanvir Hossain, Shamim Ahmad Abstract: Financial time series (TS) forecasting has gained profound research interest in the financial sector and various models have been proposed. The accuracy of such a forecasting model may offer investors an opportunity to maximize their profits. But, the inherent non-linearity and non-stationary characteristics of the stock market and financial TS has made this task immensely challenging. To address this problem, an ensemble method constituting Empirical Mode Decomposition (EMD) and Random Forest (RF) algorithm is proposed in this paper for future stock price prediction. At first, several intrinsic mode functions (IMFs) and one residual component were decomposed from the historical stock price TS. Then RF model was built to predict the future price for the target stock. 16 years' historical data of three prominent stocks from three different sectors listed in Dhaka Stock Exchange (DSE), Bangladesh are used to test the effectiveness of the proposed EMD-RF method. Empirical results demonstrated efficacy of the proposed method compared with six other forecasting methods.