Stock price prediction using intelligent models, Ensemble Learning and feature selection

Abstract

The use of artificial intelligence-based models have shown that the stock market is predictable despite its uncertainty and unstable nature. The most important challenge of the proposed models in the stock market is the accuracy of the results and increasing the forecasting efficiency. To overcome this challenge, this paper employs ensemble learning (EL) model using intelligence-based learners and metaheuristic optimization methods to maximize the improvement of forecasting performance. The multiplicity of inputs in the prediction model reduces the speed of execution and increases complexity. The proposed model, with feature selection, increases the accuracy and use as a real-time model. Genetic algorithm (GA) and particle swarm optimization (PSO) technique are used to optimize the aggregation results of the base learners. The evaluation results of stock market dataset show that the proposed model can overcome the market fluctuations and can be used as a reliable model.