Forecasting stock index price using the CEEMDAN-LSTM model

• Published in: The North American journal of economics and finance Vol. 57; p. 101421
• Main Authors: Lin, Yu, Yan, Yan, Xu, Jiali, Liao, Ying, Ma, Feng
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.07.2021
• Subjects: CEEMDAN; Long short-term memory; MCS test; Mixture models; Stock index price forecasting; C53; MCS test; C22; CEEMDAN; Mixture models; Long short-term memory; E37; Stock index price forecasting; C61
• ISSN: 1062-9408; 1879-0860
• DOI: 10.1016/j.najef.2021.101421

•This paper utilizes a new mixture model that combines CEEMDAN with LSTM to forecast stock index price.•The MCS test is introduced as the evaluation criterion of forecasting performance.•The forecasting results of single models are inferior to their mixture models with CEEMDAN.•The forecasting effects of CEEMDAN-LSTM is optimal in developed stock market and emerging stock market. This paper uses a mixture model that Long Short-Term Memory (LSTM) combines with Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) to forecast stock index price of Standard & Poor's 500 index (S&P500) and China Securities 300 Index (CSI300). CEEMDAN decomposes original data to obtain several IMFs and one residue. The LSTM forecasting model utilizes the decomposed data to obtain the prediction sequences. The prediction sequences are reconstructed to gain final prediction. The paper introduces contrast models such as Support Vector Machine (SVM), Backward Propagation (BP), Elman network, Wavelet Neural Networks (WAV) and their mixture models combined with the CEEMDAN. The MCS test is used as evaluation criterion and empirical results present that forecasting effects of CEEMDAN-LSTM is optimal in developed and emerging stock market.