Graph Theory for Computer Science

22Forecasting Short-Term Stock Market with Graph Prediction Model and Genetic Algorithm–Based Backpropagation Neural Network

Santhosh Nithyananda¹, R. Sankar Ganesh², Samyuktha, P.S.¹, P. Easwaran³* and Smruthymol J.³

¹University of Technology and Applied Science, Musannah, Muladha, Oman

²Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi, Chennai, India

³Karpagam Academy of Higher Education, Coimbatore, India

Abstract

Trading in the stock market is an activity that requires investors to have information that is both timely and accurate in order to make efficient decisions. The process of decision-making is complicated by the fact that a stock market facilitates the trading of a large number of equities. Additionally, the behavior of stock prices is difficult to forecast because it is unknown. Predicting the price of a stock is both an important and complex process due to these reasons. The main aim of this work is to predict the stock prices for short term by utilizing the stock indicators effectively. In this work, a short-term prediction model is proposed on the basis of a hybrid neural network technique. The proposed hybrid model that includes a metaheuristic algorithm called genetic algorithm (GA) and a neural network model called backpropagation neural networks (BPNNs) is implemented. This model is evaluated using two Indian industries, namely, Infosys and Hindustan Unilever Limited stock market datasets. In this proposed graph prediction ...