Optimal Game Theory Model for Stock Price Prediction

Authors

  • V. S. Triveni, T. Deepthi, M. P. Molimol

DOI:

https://doi.org/10.17762/msea.v71i4.863

Abstract

The prediction of stock price movement direction is significant in financial circles and academic. Stock price contains complex, incomplete, and fuzzy information which makes it an extremely difficult task to predict its development trend. Predicting and analysing financial data is a nonlinear, time-dependent problem. The existing deep learning models showed much variance and showed overfitting in the model. Thus, the model was not able to generalize well to unseen future data. The existing Long Short-Term Memory (LSTM) model would do well on the training data but was not able to predict the future data. Therefore, it is important to remove redundant and irrelevant attributes from the Shanghai dataset before evaluating algorithms. The objective is to navigate through the search space and locate the best or a good enough combination that improves performance over selecting all attributes. Therefore, Game theory is an approach for decision-making based on several players of various conflicts of interest and mutually interdependent situations. Co-operation and interaction are the important processes in the Game theory and this is considered a rational method to solve conflict based on the feature interaction. The results obtained by the proposed Game theory model showed an accuracy of 92.54 % better when compared with the existing GAN-ERMSE obtained 61.45% of accuracy.

Downloads

Published

2022-09-19

How to Cite

V. S. Triveni, T. Deepthi, M. P. Molimol. (2022). Optimal Game Theory Model for Stock Price Prediction . Mathematical Statistician and Engineering Applications, 71(4), 3043–3054. https://doi.org/10.17762/msea.v71i4.863

Issue

Section

Articles