Comparison of the Ability of Modern and Conventional Metaheuristic and Regression Models to Predict Stock Returns by Accounting Variables and Presenting an Effective Model

Document Type : ŮŽApplied-Research Paper

Authors

1 Department of Accounting, Isfahan Branch (Khorasgan), Islamic Azad University, Isfahan, Iran

2 Department of Accounting, Falavarjan Branch, Islamic Azad University, Isfahan, Iran

3 Department of Industrial engineering, Naghshejahan Higher Education Institute, Isfahan, Iran

10.22034/amfa.2021.1920762.1547

Abstract

Investment in the stock market requires decision-making and access to infor-mation on the future of the stock market. Given the importance of predicting stock returns, the present study aimed to discover the variables and indices that could predict stock returns. The prediction of stock returns has long been a 'hot topic' in advanced countries. While effective steps have been taken in this regard, the accu-rate prediction of stock returns remains a problem due to numerous issues. In this study, an accurate, applicable, and effective model was proposed for the predic-tion of stock returns. The statistical sample included 138 active companies of Tehran Stock Exchange (TSE) during 2008-2017, which were selected by the systematic removal method. In total, 1,380 data years were selected for the re-search to evaluate the questions. Data analysis was performed using an adaptive neuro-fuzzy inference system (ANFIS), multi-gene genetic programming, and regression analysis. In addition, statistical tests were applied to evaluate the accu-racy of the model, implemented by MATLAB and GeneXproTools. According to the results, the hybrid metaheuristic method had a lower error rate compared to artificial neural network and regression analysis in terms of stock return predic-tion. Therefore, the proposed model could provide more accurate data within a shorter time to predict the stock market status since it makes predictions after selecting the most optimal input variables through ANFIS.

Keywords


References
[1] Ahmadifar, M., Zaranejad, M., Forecasting Stock Returns by Hybrid Models Based on neuro-fuzzy inference systems, 9nd International Conference on Industrial Engineering, 2011.
[2] AhmadKhanBeygi, S., Abdolvand, N., Stock Price Prediction Modeling Using Artificial Neural Network Approach and Imperialist Competitive Algorithm Based On Chaos Theory, the Journal of Financial Management Strategy, Autumn 2017, 5 , P 27-73 , Doi:10.22051/jfm.2017.14635.1319
[3] Angelov, P., Filev, D., An approach to online identification of Takagi-Sugeno fuzzy models, IEEE TRANS, Systems, Man and Cybernetics partB, 2004, 34, P.484-498, Doi:10.1109/TSMCB.2003.817053.
[4] Asalakis, G., Valavanis, K., Forcasting Stock market short-term trends using a Hneuro-Fuzzy based methodology, Expert Systems with Appications, 2009, 36, P.10696-10707, Doi: 2F10.1102/FFSKD.2010.5569630.
[5] Azar, A., Karimi, S.,  Forecasts of Stock Returns by Using Accounting Ratios whit Approach Neural Networks, Financial Researchs Journal, Winter and Spring 2010, 11 , P.121-143. 
[6] Barzegari khanghah, J., Jamali, Z., Forecasting Stock returns by using Finaincial Ratios in previous researches, accounting research quarterly, 2016, 6, P.71-91.
[7] Binghui, w., ting ting, D., A Performance Comparison of Neoral Networks in Forecasting Stock Price Trend, the Journal of Financial Management Strategy, 2017, 10, P. 336-346, doi:10.2991/ijcis.2017.10.1.23.
[8] Boso, N., Oghazi, P., Cadogan, J.W., and Story, V., Entrepreneurial and market-oriented activities, financial capital, environment turbulence, and export performance in an emerging economy, 2016.
[9] Chauhan, B., Bidave, U., Gangathade.A, Kale.S., Stock Market Prediction Using Artificial Neural Networks, Economic Computation and Economic Cybernetics Studies and Research, 2014, 21, P. 263-280,
Doi: 10.1016/j.jefas.2016.07.002.
[10] Doloo, M., Heydari, T., predict the price index of Tehran Stock Exchange using hybrid Artificial Neural Network (ANN) models based on Genetic Algorithms (GA) and Harmony Search (HS), the Journal of Financial Economic, autumn 2017, 11 , P.1-24.
[11] Fallahpour, A., Kazemi, N., Molani, M., Nayyeri, S., and Ehsani,M., An Intelligence-Based Model for Supplier Selection Integrating Data Envelopment Analysis and Support Vector Machine, Iranian Journal of Management Studies, 2018, 11, P.209-241, Doi:10.22059/ijms.2018.237965.672750.
[12] Fallahpour, A., Olugu, E.U., Musa, S.N., Khezrimotlagh, D., Wong, K.Y., An integrated model for green supplier selection under fuzzy environment: application of data approach, Neural Computing and envelopment analysis and genetic programming Applications, 2016, 27, P. 707-725, Doi: 10.1007/s00521-015-1890-3.
 [13] Farhi, E., Gourio, F., Accounting for macro-finance trends: Market power, intangibles, and risk premia, National Bureau of Economic Research, 2018.
[14] Gandomi, A.H., Alavi, A.H., Ryan, C., Handbook of genetic programming applications, 2015, Doi.:10.1007/987-3-319-20883-1.
[15] Ghasemzadeha, M., Mohammad-Karimi, N., Ansari-Samani, H., Machine learning algorithms for time series in financial markets, the Journal of Advance in Mathematical Finance and Applications, 2020 , 5, P.479-490.
 Doi: 410.22034/AMFA.2020.674946
[16] Gholamnejad, J., Lotfian R., Mirzaeian Lord, K. Y., Comparison of Artificial Neural Networks and Multivariate Linear Regression Classification Techniques in Metal Recovery Estimation, Journal of Mineral Resources Engineering (JMRE), 2019, 5, P. 21-41, Doi: 10.30479/jmre.2019.10997.1284.
[17] Ince, H., Trafalis,B., Ua Hybrid Forecasting Model for Stock Market Prediction, Economic Computation and Economic Cybernetics Studies and Research, 2017, 21 , P. 263-280.
[18] Karil, Q. C., Acompurision between Fama and French Model and Artificial Neural Network in predicting the Chinese Stock Market, Computer and Operations research, 2005, 32, P. 2499-2512.
[19] Kasabov, N., Song, Q., Denfis: Dynamic,evolving neural-fuzzy inference system and its application for time-series prediction, IEEE Trans. Fuzzy Syst, 2002 , 10 , P.144-154, Doi:10.1109/91.995117.
[20] Khodayari, M.A., Yaghobnezhad, A., A Neural-Network Approach to the Modeling of the Impact of Market Volatility on Investment, the Journal of Advance in Mathematical Finance and Applications, 2020 ,  5 , P. 83-97 , Dio 410.22034/AMFA.2020.674946
[21] Lin, K.V., Servaes, H., and Tamayo, A., Social capital, trust, and firm performance: The value of corporate social responsibility during the financial crisis, the Journal ofFinance, 2017, 72, P.1785-1824, Doi:10.1111/jofi.2017.12505
 [22] Lin, Z.J., Yang, D.C., and Wang, L., Accounting and auditing in China: Routledge, 2018, Doi:10.1080/1540496X.2018.1428796
 [23] Ko,  M., Tiwari, A., Mehnen, J., Areview of soft computing application in supply chain management, Apllied soft computing, 2010, 1, P.661-674. Doi:10.1016/j.asoc.2009.09.004
[24] Melek, A. B., Avci, D., An Adaptive network based Fuzzy Inference System (ANFIS) for the prediction of stock market return: The case of the Istanbul stock Exchange, Export system with application, 2010.
 Doi: 10.1016/j.eswa.2010.04.045.
[25] Monajemi, A., Stock Price Prediction Stock Exchang by Using Fuzzy- Neural Network and genetic Algorithms and Artificial Neural Network, Quantitative Economics Quarterly, 2009, 6, P. 1-26.
[26] Namazi, M., Kiamehr, M.M., Predicting Daily Stock Returns of Companies listed in Tehran Stock Exchange Using Artificial Neural Networks, Financial Research Journal, Winter and Spring 2008, 9, P.345-364.
[27] Omidi Gohar, E., Darabi, R., The Relationship between Earnings Variability and Earnings Forecast Using Neural Networks in Companies Listed on Tehran Stock Exchange, Journal of Economic and Business Reasearch, Winter 2015,  6 ,  P. 77-92.
[28] Raei, R., Chavooshi, K., prediction Stock Return Behavior By Arbitrage Pricing Theory (APT) And Artificial Neural Networks(ANN), Financial Research Journal, Winter and Spring 2003, 5, P. 233-243
[29] Rahmani, M., Khalili Eraqi, M., Nikoomaram, H., Portfolio Optimization by Means of Meta Heuristic Algorithms, the Journal of Advance in Mathematical Finance and Applications, 2019, 4, P. 83-97.
 Doi: 410.22034/AMFA.2020.674946

[30] Rajabpour, E., Taghva, M.R., Hossienzadeh Yazdi, M.A., Baba Ahmadi, S., Predicting the Stock Price of Companies in Tehran Stock Exchange Using Artificial Neural Networks, the Journal of Accounting New Researchs, 2014, 2, P. 45-57.

[31] Renu, V., Chandra, A., Predicting stock returns nifty index: An Application of Artificial Neural Network, International research Journal of Finance and Economics, 2010, ISSN 1450-2887.
 
[32] Izadikhah, M. Financial Assessment of Banks and Financial Institutes in Stock Exchange by Means of an Enhanced Two stage DEA ModelAdvances in Mathematical Finance and Applications, 2021, 6(2), P. 207-232. Doi: 10.22034/amfa.2020.1910507.1491
[33] Saghafi, A., Sheri, S., Role of Fundamental Accounting Information in Predicting Stock Return, the Journal of Empirical Studies in Financial Accounting Quarterly, Winter 2004, 2 , P.87-120.
[34] Sheta, A. et al., A Comparison between Regression Artifical Neural Networks and Suppport Vector Machines for Prodicting Stock Market Index, International Journal of Advance Research in Artificial Intelligence, 2015, 4, P. 55-63, Doi:10.14569/ljaral.2015.040710.
[35] Takagi, T., Sugeno, M., Fuzzy identification of system and its application to modeling and control, IEEE Trans. Syst. Man, Cybern,1985, 15(1), P. 116-132, Doi.:10.1109/TSMC.1985.6313399.
[36] Tan, H., Prokhorov, K., Wunsch, K., Conservative Thiry Calendar Stock Prediction Using a Probabilistic Neural Networks, Proceedings of Computational Intelligence for Financial Engineering Conference, 1995, Doi:10.1109/CIFER.1995.495262.
[37] Tavana, M., Fallahpour, M.A., Caprio, D.Di., and Santos-Arteaga, F.J., A hybrid intelligent fuzzy predictive model with simulation for supplier evaluation and selection, Expert systems with applications, 2016, 61, P. 129-144. Doi: 10.1016/j.eswa.2016.05.027.
[38] Tolouie Eshlaghy, A., Haghdoust, S., Modelling of Prediction Stock Price by Using Neural Networks and Compare it with Mathematical Prediction Method, the Journal of Economic Reasearch, Summer 2007, 7 , P. 237-251.
[39] Trinkel, B.S., Forecasting annual excess stock returns via an adaptive network based fuzzy inference system, Intelligent system in Accunting Finance and Management, 2006, 13, P.165-177, Doi:10.1002/isaf.264
[40] Zancheting, c., Desing of experiments in neuro-fuzzy systems, International Journal of Computational intelligence and applications.,2010, l, P. 137-152.
Volume 7, Issue 2
April 2022
Pages 447-466
  • Receive Date: 16 January 2021
  • Revise Date: 30 May 2021
  • Accept Date: 21 June 2021
  • First Publish Date: 18 July 2021