Predicting the Occurrence of Negative Stock Returns Using Artificial Intelligence Algorithms and Its Relationship with Conservative Reporting in Companies Listed on the Tehran Stock Exchange
Keywords:
Negative stock returns, artificial intelligence, machine learning algorithms, Conservative reporting, Tehran Stock ExchangeAbstract
Predicting the occurrence of negative stock returns is a central issue in behavioral finance and risk management, playing a critical role in improving investment decision-making and enhancing capital market efficiency. This study employs advanced artificial intelligence algorithms, including artificial neural networks, support vector machines, decision trees, and AI-based optimization algorithms, to develop models for forecasting negative stock returns. These algorithms, with their ability to learn complex patterns and uncover nonlinear relationships among financial data, demonstrate significantly better performance than traditional methods in the early detection of negative return risks. Financial and reporting data from companies listed on the Tehran Stock Exchange were collected over a five-year period, and variables related to conservative financial reporting were incorporated into the analysis. Statistical analyses and performance evaluations of 101 listed companies during the period 2010 to 2015 indicate that conservative reporting—by emphasizing the early recognition of losses and moderating profit recognition behaviors—has a significant impact on improving the accuracy and generalizability of AI models in predicting the risk of negative returns. The findings suggest that integrating intelligent approaches with conservative reporting measures can enhance the quality of financial information, reduce uncertainty, and increase transparency in investment decisions. This research not only deepens scientific understanding of the relationship between conservative financial reporting and stock return risk but also offers practical applications for financial analysts, managers, and capital market policymakers.
Downloads
References
Behera, J., Pasayat, A. K., & Behera, H. (2022). COVID-19 Vaccination Effect on Stock Market and Death Rate in India. Asia-Pacific Financial Markets, 29(4), 651-673. https://doi.org/10.1007/s10690-022-09364-w
Behera, J., Pasayat, A. K., Behera, H., & Kumar, P. (2023). Prediction based mean-value-at-risk portfolio optimization using machine learning regression algorithms for multi-national stock markets. Engineering Applications of Artificial Intelligence, 120, 105843. https://doi.org/10.1016/j.engappai.2023.105843
Chen, J., Wen, Y., Nanehkaran, Y. A., Suzauddola, M. D., Chen, W., & Zhang, D. (2023). Machine learning techniques for stock price prediction and graphic signal recognition. Engineering Applications of Artificial Intelligence, 121, 106038. https://doi.org/10.1016/j.engappai.2023.106038
Guresen, E., Kayakutlu, G., & Daim, T. U. (2011). Using artificial neural network models in stock market index prediction. Expert Systems with Applications, 38(8), 10389-10397. https://doi.org/10.1016/j.eswa.2011.02.068
Kamrani, H., & Abedini, B. (2022). Developing a Model for Detecting Financial Statement Fraud Using Artificial Neural Networks and Support Vector Machines in Companies Listed on the Tehran Stock Exchange. Journal of Accounting and Management Auditing, 41, 285-314.
Karbalaei Mirzai, M. Y., Mir Loohi, S. M., & Khademi, M. (2022). Investigating the Impact of Macroeconomic Variables on the Tehran Stock Exchange Index: A Comparison of Neural Network and VAR Regression Models. Iranian Political Sociology Monthly, 5(9), 1472-1489. https://civilica.com/doc/1702928/
L.Lima, M., Nascimento, T. P., Labidi, S., Timbo, N. S., Batista, M. V. L., Neto, G. N., Costa, E. A. M., & Sousa, S. R. S. (2016). Using Sentiment Analysis for Stock Exchange Prediction. International Journal of Artificial Intelligence & Applications, 7(1), 59-67. https://doi.org/10.5121/ijaia.2016.7106
Nahdhiyah, A. I. (2023). The Effect of Profitability, Liquidity, Leverage, Company Size and Assets Growth on Stock Return: Empirical Evidence From Indonesia. Maksimum, 13(1), 50. https://doi.org/10.26714/mki.13.1.2023.50-58
Qian, Y. (2023). Progress of the Study on the Impact of Investor Sentiment on Stock Returns. BCP Business & Management, 39, 106-111. https://doi.org/10.54691/bcpbm.v39i.4030
Rezaei, M., & Hosseini, A. (2019). Application of Machine Learning Algorithms in Predicting Stock Returns on the Tehran Stock Exchange. Iranian Journal of Financial and Economic Sciences, 23(1), 57-74.
Riwayati, H. E. (2023). The Effectiveness of Liquidity, Solvency, and Profitability Ratios Against the Stock Returns of the Company. Mix Jurnal Ilmiah Manajemen, 13(3), 600. https://doi.org/10.22441/jurnal_mix.2023.v13i3.006
Sethy, T. K. (2024). A New Method for Estimating Liquidity and Stock Returns in Indian Stock Market. China Accounting and Finance Review, 26(2), 253-275. https://doi.org/10.1108/cafr-05-2023-0052
Shaghaghi Shahri, S. (2024). Evaluation and Comparison of Classification Model Performance in Predicting Corporate Credit Ratings Using Artificial Intelligence: A Case Study of the Tehran Stock Exchange. Transactions on Data Analysis in Social Science, 6(2), 31-44. https://www.transoscience.ir/article_200776.html
Syukur, A., & Istiawan, D. (2021). Prediction of LQ45 Index in Indonesia Stock Exchange: A Comparative Study of Machine Learning Techniques. International Journal of Intelligent Engineering and Systems, 14(1), 453-463. https://doi.org/10.22266/ijies2021.0228.42
Tarasi, M., Banitalebi, B., & Zamani, B. (2019). Forecasting Fraudulent Financial Reporting Through Artificial Neural Network. Management accounting, 12(40), 63-79. https://www.magiran.com/paper/1948354
Vaghfi, S. H. (2019). Application of artificial intelligence algorithms in predicting bankruptcy using macroeconomic and accounting variables in companies listed on the Tehran Stock Exchange. Quarterly of Decision Making and Operations Research, 4(2).
Ye, C., Song, X., & Liang, Y. (2023). Corporate sustainability performance, stock returns, and ESG indicators: fresh insights from EU member states. Environmental Science and Pollution Research, 29. https://doi.org/10.1007/s11356-022-20789-8
Downloads
Published
Submitted
Revised
Accepted
Issue
Section
License
Copyright (c) 1404 علی دلیلی (نویسنده); کیهان آزادی هیر (نویسنده مسئول); محسن آرچین لیسار (نویسنده)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
