Evaluation of the Accuracy of Support Vector Machine based on Genetic Algorithm Compared to Common Linear Methods in Forecasting Earnings Per Share

Document Type : Research Paper

Author

Assistant Professor of Accounting, Islamic Azad University, Kerman Branch, Kerman, Iran

Abstract

Earnings and earnings per share information are metrics that are considered important by many users; Therefore, companies try to attract investors with the most accurate forecast of earnings per share. On the other hand, despite the various methods of forecasting earnings, accurate forecasting of earnings per share in the financial field is not easy and most researchers are trying to determine the best way to forecast earnings; Therefore, the main purpose of this study is to investigate the accuracy of support vector machine based on genetic algorithm compared to common linear methods in forecasting earnings per share. For this purpose, samples consisting of 100 companies listed on the Tehran Stock Exchange during the years 2008-2019 have been studied. In order to achieve the objectives of the research, first by studying previous research in the field of earnings forecasting, 14 financial ratios affecting earnings forecasting have been selected. Then, in order to provide a model for predicting the profitability of companies, a combined model of support vector machine based on genetic algorithm, support vector machine and linear regression is compared. The results showed that the hybrid model of support vector based on genetic algorithm is much better in predicting the trend of earnings per share and has a higher accuracy compared to the model of support vector based on kernel functions and linear regression method. Thus, with the development of the support vector machine model based on the genetic algorithm, the model training error is reduced to 0.036 and the accuracy of the model is increased up to 75%.

Keywords

Main Subjects

References

Afsar, A., Houshdar Mahjoub, R., Minaei, B. (2014). Customer credit clustering for Present appropriate facilities. Iran Management Study (IQBQ), 17 (4), 1-24. (In Persian)
Alavi Tabari, H.; Jalili, A. (2006). The usefulness of fundamental variables in predicting profit growth. Accounting and Auditing Reviews, 13 (1), 119-143. (In Persian)
Alimohamadi, A., Abbasimehr, M., Javaheri, A. (2015). Prediction of Stock Return Using Financial Ratios: A Decision Tree Approach. Financial Management Strategy, 3(4), 125-146. (In Persian)
Baruch, L., Siyi, L., Theodore, S. T. (2009). The Usefulness of Accounting Estimates for Predicting Cash Flows and Earning. Unpublished PhD. Dissertation, New York University.
Cao, Q., Parry Mark, E. (2009). Neural Network Earning per Share Forecasting Models: A Comparison of Backward Propagation and Genetic Algorithm. Decision Support Systems, 47, 32-41.
 Habibzade, M., Ezadpour, M. (2020). Using neural network approach to predict company’s profitability and comparison with decision tree C5 and support vector machine (SVM). Financial Knowledge of Securities Analysis, 13(46), 39-56. (in persian)
Hejazi, R., Ghitasi, R., Karimi, M. (2011). Profit smoothing and information uncertainty. Accounting and Auditing Reviews, 18 (63), 63-80. (In Persian)
Haykin, S., (1998). Neural Networks: A Comprehensive Foundation. Prentice Hall PTR, Upper Saddle River.
Hoseininasab, H., Karimi Taklu, S. (2014). Predicting earnings per share using the fuzzy backup vector machine approach. Monetary and Banking Management Development Quarterly, 2 (3), 1-22. (In Persian)
Hoseininasab, H., Karimi Taklu, S., Yusefinejad, M. (2013). Comparing the precision of approaches of support vector machine and artificial neural networks to predict the benefits per share of listed companies in Tehran Stock Exchange. Journal of Iran's Economic Essays, 10(20), 109-134. (In Persian)
Huang, X., & Sun, Li, (2017). Managerial Ability and Real Earnings Management. Advances in Accounting, 39(C), 91-104.
Joshua O. S., James N. M., Linda A. M. (2021). Improving Earnings Predictions and Abnormal Returns with Machine Learning. Accounting Horizons, doi: https://doi.org/10.2308/HORIZONS-19-125
Kardan, B., Salehi, M., Gharekhani, B., Mansouri, M. (2017). The evaluation accuracy of BBO and ICDE as Linear- evolutionary Algorithms and SVR and CART as Non-linear Algorithms to earnings management prediction. Journal of Financial Accounting Research, 9(1), 77-96. (In Persian)
Kaveh, M., DucBui, M., Rutschman, P., (2019). A comparative study of three different learning algorithms applied to ANFIS for predicting daily suspended sediment concentration. International Journal of Sediment Research, 32 (3), 340-350.
Kothari, S. P.  Shu, S.  Wysocki, P.  (2005).  Do Managers Withhold Bad News?  MIT Sloan Research Paper, 4, 556-05.
Kurdistan, G., Bahramfar, N., Amiri, A. (2019). The effect of disclosure quality on information asymmetry. Financial Accounting and Auditing Research, 11 (42), 159-178. (In Persian)
 Lang, M., Lundholm, R. (1996). Corporate disclosure policy and analyst behavior. The Accounting Review, 71, 467-492.
Mahdavi, G. H., Behmanesh, M. R. (2005). Designing a stock price forecasting model for investment companies using artificial neural networks (Case study: Alborz Investment Company). Economics Research, 5 (19), 211-233. (In Persian)
Michael, D. (1999). The simple Genetic Algorithm: Foundation and Theory. The MIT Press
Omidi Gohar, E., Darabi, R. (2015). The Relationship between Earnings Variability and Earnings Forecast Using Neural Networks in Companies Listed on Tehran Stock Exchange. Journal of Economics and Business, 6(11), 77-92. (In Persian)
Payne, J. L.  (2008).  The Influence of Audit Firm Specialization on Analysts’ Forecast Errors.  Auditing: A Journal of Practice &Theory, 27(2), 109–136.
Rezaee, N., Amirhosseini, Z. (2017). Evaluation of Financial Performance Using Decision Tree Algorithm Method. Financial Management Strategy, 5(2), 185-205. (In Persian)
Pouyanfar, A., Fallahpour, S., Azizi, M. (2013). Genetic algorithm-based support vector least squares approach to estimating the credit rating of bank customers. Financial Engineering and Securities Management, 4 (17), 133-158. (In Persian)
Rees, L.  Siavaramakrishnan, K.  (2007).  The Effect of Meeting or Beating Revenue Forecasts on the Association between Quarterly Returns and Earnings Forecast Errors.  Contemporary Accounting Research, 24(1), 259-90.
Sarbana, M., Ashtab, A. (2008). Identifying the factors affecting the profit forecast error of new companies listed on the Tehran Stock Exchange. Journal of Humanities and Social Sciences "Economic Sciences, 8 (28), 55-76. (In Persian)
 Tong, S., Kian, CH., (2018). Predicting IPOs performance using generalized growing and pruning algorithm for radial basis function (GGAP-RBF) Net Work. The 2006 IEEE International Joint Conference on Neural Network Proceedings, 12(1). DOI: 10.1109/IJCNN.2006.247258
Vakilian Agohei, M., Vadiei, M., Hoseini Maasoom, M. (2009). The Relationship between Economic Value Added (EVA) and Residual Income (RI) in the Predicting Future Earning Per Share (EPS). Financial Research Journal, 11(27), 111-122. (In Persian)
Vapnik, V.  (1995).  The nature of statistical learning theory.  Springer-Verlag
New York.
Yu, L., Wang, S., & Cao, J. (2009). A modified least squares support vector machine classifier with application to credit risk analysis. International Journal of Information Technology and Decision Making, 8(4), 697-710.
Zhang, H., Yang, F., Li, Y., Li, Y. (2015). Predicting profitability of listed construction companies based on principal component analysis and support vector machine—Evidence from China Author links open overlay panel. Automation in Construction, 53, 22-28.
Zhou, L., Lai, K. K., & Yu, L. (2010). Least squares support vector machines ensemble models for credit scoring. Expert System with Applications, 37(1),127-133.
 
Financial Management Strategy
Volume 11, Issue 3 - Serial Number 42
November 2023
Pages 127-154

Files

History

  • Receive Date: 24 October 2022
  • Revise Date: 04 August 2023
  • Accept Date: 09 October 2023

Share

How to cite

Statistics