A novel hybrid model for stock price forecasting integrating Encoder Forest and Informer

Stock forecasting plays a pivotal role in time series forecasting as it enables informed and effective investment decisions by minimizing risks. In this paper, a novel hybrid model for stock price forecasting is proposed to explore the impact of a decomposition-reconstruction method fused with machine learning models, aiming to enhance the predictive ability of the model. Following the decomposition-prediction-reconstruction principle, the hybrid model incorporates wavelet transform, integrating Encoder Forest (EF) with Informer. To mitigate the influence of long-time series noise on stock forecasting, the original data is decomposed into high-frequency signal components (CD) and low-frequency signal components (CA). The Informer and Encoder Forest are trained to predict the future CA and CD, respectively. The hybrid model is implemented for all stocks in three industries of the china stock market. Several models including MLP, RNN, LSTM, Informer, WT + RNN + DT, WT + LSTM + RF, EMD + Informer + EF, VMD + Informer + EF, CEEMD + Informer + EF, and CEEMDAN + Informer + EF are designed as compared methods to verify the superiority and advancement of the proposed technique. Evaluating the performance of individual models reveals that the prediction accuracy follows the ranking: MLP < RNN < LSTM < Informer. Comparing the results of the hybrid model with those of the individual models demonstrates that the hybrid model improves prediction accuracy. This comparison also indicates that the wavelet transform and tree models can enhance the accuracy of the model without altering the initial ranking of the prediction effect. It is worth noting that WT and EMD-like methods employ different data decomposition approaches, leading to diverse outcomes. Experimental results indicate that WT is better suited for a hybrid model that combines two distinct methods. All experimental results indicated that the proposed hybrid model has higher prediction accuracy, stronger generalization ability, and stronger practicability, which is more suitable for Stock forecasting problems.