Comparative Analysis of Artificial Neural Networks and Linear Regression in Predicting the Continuation of Shareholders' Overreaction Trends

Document Type : Research Paper

Authors

1 PhD Student, Department of Accounting, Faculty of Humanities, Zahedan Branch, Islamic Azad University, Zahedan, Iran.

2 Assistant Prof., Department of Accounting, Zahedan Branch, Islamic Azad University, Zahedan, Iran.

3 ssistant Prof., Department of Financial and Accounting, Faculty of Humanities, Meybod University, Meybod, Iran.

10.22059/acctgrev.2024.373333.1008920

Abstract

Objective
Overreaction is a noticeable anomaly in financial markets that leads to various consequences, including market inefficiency. As such, one of the prominent topics investigated in major global stock exchanges is shareholders' overreaction. This phenomenon is particularly prevalent in emerging and less developed markets, where investors tend to overreact to financial events. Overreaction, as a behavioral bias, distorts investors' decision-making in uncertain conditions, pulling the market away from its efficient state. Predicting and identifying the persistence of these reactions can assist investors in making more rational decisions regarding the purchase or sale of shares and other securities. Therefore, predicting and identifying the continuation of shareholders' overreaction trends can serve as a valuable tool for investors, financial analysts, and investment managers to make decisions based on intuition and precise analysis. To create an effective predictive model, various methods, such as regression analysis, can be employed to analyze the relationship between different variables and the continuation of shareholders' overreaction trends. Additionally, artificial neural networks (ANNs), as an advanced method, can be used to model the non-linear complexities and intricate connections between variables. This topic is directly related to predicting shareholders' behavior and investment decision-making, ultimately helping improve investment strategies and risk management. Hence, the main objective of this research is to conduct a comparative analysis of artificial neural networks and linear regression in predicting the continuation of shareholders' overreaction trends.
Methods
The present study is descriptive-causal, utilizing ex post facto research. To test the research hypotheses, multivariate linear regression based on panel data and a combination of time series was employed. Data was collected using the library research method, and necessary information was gathered by studying the financial statements of companies within the statistical population. The statistical population includes all companies listed on the Tehran Stock Exchange between 2011 and 2021, with 110 companies selected through systematic elimination sampling. In data analysis, regression methods were used to examine the relationships between variables, and the results were compared with those obtained from artificial neural networks.
Results
The results indicate the superiority of the artificial neural network model in terms of the coefficient of determination and the MSE (Mean Squared Error) index. Specifically, the highest coefficient of determination for the artificial neural network (with 1 hidden layer and 9 neurons) for test data is 0.3880, compared to 0.349 for the linear regression model. Moreover, the results show that the MSE for the artificial neural network (1 hidden layer and 9 neurons) for test data is 0.003266, compared to 0.004 for the linear regression model. Thus, similar to the coefficient of determination, the MSE index is also better in the case of the artificial neural network.
Conclusion
The artificial neural network model is capable of uncovering complex and non-linear patterns, providing the most accurate predictions. By using this model, stock return trends can be predicted more precisely and reliably.

Keywords

Main Subjects


 
Ananzeh, I., Jdaitawi, Q. & Al-Jayousi, A. (2013). Relationship between Market Volatility and Trading Volume: Evidence from Amman Stock Exchange. International Journal of Business and Social Science, 4(16), 188- 198.
Assan, A. & Thomas, T. (2013). Stock returns and trading volume: does the size matter? Investment Management and Financial Innovations, 1(3), 76-88.
Astvan, S., Samimi Nia, G. & Mubaraki, M. (2021). The effect of investors' emotional tendency on the risk of falling stock prices of companies listed on the Tehran Stock Exchange.  The Third International Conference on Management, Accounting, Banking and Economics in Iran 1404, Mashhad, https://civilica.com/doc/1443890 (in Persian)
Byun, S. J., Lim, S. S. & Yun, S. H. (2016). Continuing overreaction and stock return predictability. Journal of Financial and Quantitative Analysis, 51(6), 2015-2046.
Choi, K., Jiang, Z., Kang, S. & Yoon, S. (2012). Relationship between Trading Volume and Asymmetric Volatility in the Korean Stock Market. Modern Economy, 3, 584-589.
Cui, H., & Zhang, Y. (2019), does investor sentiment affect stock price crash risk? Applied Economics Letters, 1–5.
Daniel, K., Hirshleifer, D. & Subrahmanyam, A. (1998). Investor psychology and security market under and overreactions. The Journal of Finance, 53(6), 1839-1885.
Dawood Abadi, A., (2019). Investigating the information content of the continuation of the overreaction trend based on the volume of transactions and special fluctuations and its effect on the profitability of momentum in markets with price limits. Master’s thesis; Islamic Azad University, Arak branch. (in Persian)
Dehghan Khavari, S. & Mirjalili, S.H. (2018). The interaction of systematic risk with stock returns in Tehran Stock Exchange. Financial Economics, 13(49), 257-282. (in Persian)
Elfakhani, S. & Zaher, T. (1998). Differential Information Hypothesis, Firm Neglect and the Small Firm Size Effect. Journal of Financial and Strategic Decisions, 11(2), 29-40.
Esfehani, S., (2018). The role of automatic stops on movement against the direction of the market with an emphasis on the interactive effect of changes in the amount of floating shares in the industry. Master's thesis, Arak Azad University. (in Persian)
Faghfour Maghrebi, Y., Sajadi, S. H., Asnaashari, H. & Rezaeian, A. (2020). Investigating the Mediating Role of Understanding, Processing Fluency and Credibility of an Earnings Press Release on the Relationship between Language Sentiment, Readability, Sophistication and Investors’ Judgment and Decision-making. .Accounting and Auditing Review, .27(1), 87-113. doi: 10.22059/acctgrev.2020.295623.1008337 (in Persian)
Fama, E. F. & French, K. R. (1992). The Cross-Section of Expected Stock Returns. Journal of Finance (47), 427–465.
Golarzi, G. & Danayi, K. (2019). Evaluation of Shareholders’ Overreaction and its Comparison in Small and Large Companies (Case Study: Accepted Companies in Tehran Stock Exchange). Financial Management Perspective, 9(25), 59-76. doi: 10.52547/jfmp.9.25.59 (in Persian)
 Goodell, J. W., Kumar, S., Rao, P. & Verma, S. (2023). Emotions and stock market anomalies: a systematic review. Journal of Behavioral and Experimental Finance, 37, 100722.
Habib, N. M. (2011). Trade Volume and Returns in Emerging Stock Markets An Empirical Study The Egyptian Market. International Journal of Humanities and Social Science, 1(19), 302-312.
Hajannejad, A., Amiri, H., & Khoramkohi, A. (2022). Analyzing the Effects of Investors' Sentiments on the Reaction to the Profit News of Companies Listed on the Tehran Stock Exchange. Financial Accounting Research, 14(1), 1-20. doi: 10.22108/far.2022.132213.1852 (in Persian)
Handayati, P., Indrayani, L. & Indrayono, Y. (2023). The effect of under reaction and overreaction of firm stocks to firm valuation: data from the Indonesian Stock Exchange. International Journal of Business and Systems Research, 17(2), 121-142.
Hassanzadeh Diwa, S., & Bozorg ASL, M., (2021). The effect of investors' behavioral patterns on the risk of future stock price fall, with an emphasis on the role of financial reporting quality. Knowledge of management accounting and auditing, 13(50), 137- 151.
(in Persian)
Hou, K., Xiong, W. & Peng, L. (2009). Atale of two anomalies: The implications of investor attention for price and earnings momentum. Available at SSRN 976394.
Jannat Faridouni, H. & Pourali, M. (2021). Investigating the relationship between the investor's business behavior and the risk of falling stock prices on individual risk, the second international conference on new challenges and solutions in industrial engineering, management and accounting, Damghan, https://civilica.com/doc/1244328. (in Persian)
Kamyabi, Y., & Javady Nia, A. (2021). Investigating the Effect of Moderating Managerial Ability on the Relationship between Investor Sentiment and Accounting Conservatism. .Accounting and Auditing Review28(1), 102-134. doi: 10.22059/acctgrev.2021.307335.1008411 (in Persian)
Kant, R. (2011). Testing of relationship between stock return and trading volume in India. International journal of multidisciplinary research, 1(6), 371-393.
Khorramabadi, M., Abdi, H. & Lashgarara, S. (2024). Investigating investors' feelings and Iran's capital market's reaction to the corona virus epidemic (event research approach). Journal of Accounting Advances16(1). doi: 10.22099/jaa.2024.48558.2375 (in Persian)
Kordestani, Gh. & Teymori, T., (2017). The Effect of Private Information on Investment and Dividend Policy. Journal of Financial Management Strategy, 2(5), 27-53. (in Persian)
Lin, H.Y. (2012). Dynamic stock return–volume relation: evidence from emerging Asian markets. Bulletin of economic research, 65(2), 178-193.
Loang, O. K. (2022). Overreaction, investor sentiment and market sentiment of COVID-19. Vision, 09722629221087386.
Madan Haghighi, S., (2013). Investigating the relationship between free floating stocks and the range of price fluctuations: evidence from Tehran Stock Exchange, The first national accounting and management conference, Shiraz. (in Persian)
Mohanty, P. & Mishra, S. (2024). Did the Indian stock market overreact to Covid-19? The North American Journal of Economics and Finance, 70, 102072.
Ralf, B., Glaser, M., Schaarschimdt, S. & Stankiewicz, S. (2014). The stock return – trading volume relationship in European countries: evidence from asymmetric impulse responses. Working paper series, University of Konstanz, available at: www.unikonstanz.de
Reinganum, M.R. (1981). Misspecifications of capital asset pricing: Empirical anomalies based on earnings yields and market values. Journal of Financial Economics, 9(1), 19-46.
Riadi, D. R., Garnia, E. & Tahmat, T. T. (2023). Impact of The Covid 19 Pandemic: Is There Overreaction in LQ 45 Stock? Jurnal Manajemen dan Keuangan, 12(1), 178-194.
Salem Al Ghazali, A. (2014). The Relationship between Trading Volume and Stock Returns Index of Amman Stocks Exchange Analytical Study. Global Journal of Management and Business Research: Economics and Commerce, 14(7), 8-28.
Sangari, M., Aghaei, M. A., Avazzadeh Fath, F. & Pirzad, A. (2024). Investigating the effect of underreaction and overreaction on Iran's capital market risk. Journal of Investment Knowledge, 13(52), 711-726. doi: 10.30495/jik.2024.23247 (in Persian)
Shams, Sh., & Esfandiari Moghaddam, A., (2018). The relationship between herding behavior with performance and characteristics of investment companies. The financial accounting and auditing researches, 10(38), 47-66. SID. https://sid.ir/paper/198141/en. (in Persian)
Taherinia, M. (2023). Understanding Information Salience Phenomenon: Identifying and Prioritizing its Consequences in the Stock Exchange Market. Journal of Management Accounting and Auditing Knowledge12(45), 71-83. (in Persian)
Taherinia, M., Mohammadi, M. & Bahramian, B. (2024). Analyzing the Impact of Analytical Paralysis on Investors' Decisions in the Tehran Stock Exchange. Accounting and Auditing Review31(1), 95-122. doi: 10.22059/acctgrev.2024.363035.1008840 (in Persian)
Wang, X., & Meng, M. (2012). A Hybrid Neural Network and ARIMA Model for Energy Consumption Forcasting. Journal of Computers, 7(5), 1184-1190.
Xia, Y. & Madni, G. R. (2024). Unleashing the behavioral factors affecting the decision making of Chinese investors in stock markets. Plos one, 19(2), e0298797.
Yang, N. T., Chu, H. H., KO, K. C., & Lee, S. W. (2018). Continuing overreaction and momentum in a market with price limits. Pacific-Basin Finance Journal, 48, 56-71.
Zarei, A., & Darabi, R. (2018). The Impact of Investors Sentiment on Voluntary Disclosure in the Capital Market of Ira. The Financial Accounting and Auditing Researches, 10(37), 131-157. SID. https://sid.ir/paper/198024/en. (in Persian)
Zarowin, P. (1990). Size, seasonality and stock market overreaction. Journal of Financial and Quantitative Analysis, 25(1), 113-125.