Author:
Arash Salehpour ,Elaheh Salehpour
Abstract
One of the best ways to make money on the capital market is to buy shares on the stock exchange. The stock market has a nonlinear and chaotic system that is influenced by political, economic, and psychological conditions, and systems such as regression can be used to predict stock prices. In this research, different regression models are used, each of which measures information in a different way and tests the ability to predict the behaviour of index prices with this information. This paper examines linear regression, robust regression, ridge regression, polynomial regression, and elastic net on the historical daily data from 2018-07-01 to 2022-09-28 in the Car index of the Tehran Stock Exchange. Based on the empirical results, it is found that the best R2 score has been attained by the robust regression model. MSE, RMSE, MAE, and R2 for all models have been compared.
Publisher
Inventive Research Organization
Subject
General Earth and Planetary Sciences,General Environmental Science
Reference10 articles.
1. [1] Bazrkar, M.J. and S. Hosseini, Predict Stock Prices Using Supervised Learning Algorithms and Particle Swarm Optimization Algorithm. Computational Economics, 2022.
2. [2] Andersen, R., Modern Methods for Robust Regression Quantitative Applications in the Social Sciences. September 2007, University of Toronto, Canada: SAGE.
3. [3] Masoumi, M., et al., Economic and non-economic determinants of Iranian pharmaceutical companies’ financial performance: an empirical study. BMC Health Services Research, 2019. 19(1): p. 1011.
4. [4] Patel, J., et al., Predicting stock market index using fusion of machine learning techniques. Expert Systems with Applications, 2015. 42(4): p. 2162-2172.
5. [5] Strutz, T., Data Fitting and Uncertainty: A practical introduction to weighted least squares and beyond, ed. Springer.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献