Designing a Novel Model for Stock Price Prediction Using an Integrated Multi-Stage Structure: The Case of the Bombay Stock Exchange

Abstract

Stock price prediction is considered a strategic and challenging issue in the stock markets. Considering the complexity of stock market data and price fluctuations, the improvement of effective approaches for stock price prediction is a crucial and essential task. Therefore, in this study, a new model based on “Adaptive Neuro-Fuzzy Inference System (ANFIS), Particle Swarm Optimization (PSO) and Genetic Algorithm (GA)” is employed to predict stock price accurately. ANFIS has been utilized to predict stock price trends more precisely. PSO executes towards developing the vector, and GA has been utilized to adjust the decision vectors employing genetic operators. The stock price data of top companies of the Bombay Stock Exchange (BSE) from 2010 to 2020 are employed to analyze the model functionality. Experimental outcomes demonstrated that the average functionality of our model (77.62%) was achieved noticeably better than other methods. The findings verified that the ANFIS-PSO-GA model is an efficient tool in stock price prediction which can be applied in the different financial markets, especially the stock market.