Forecasting EPS o with Hybrid Genetic algorithm, particle swarm optimization and Neural networks

Document Type : Research Paper

Authors

1 PhD Student in Accounting, Shahid beheshti University, Tehran, Iran.

2 Associate Professor of Accounting, Shahid beheshti University, Tehran, Iran.

Abstract

Forecasting earnings per share (EPS) are among the most important and crucial tasks for both outside investors and internal managers. The focus of most articles in literature is forecasting EPS with linear methods. Researchers rarely employ nonlinear models to forecast EPS. However some researchers show that nonlinearities exist in the relation between EPS and its determinants. This finding of nonlinearities provides support for the use of non-linear models in the field of earnings per share.
In this paper, the model based on an Artificial Neural Network (ANN) to predict EPS is proposed. After that, ANN model was optimized by Genetic Algorithm and particle swarm optimization. The Genetic Algorithm and particle swarm optimizations used to select the most relevant input variables because selection of input variables is a key stage in building predictive models,
In this paper, The Genetic Algorithm and particle swarm optimizations used to select the effective variables on the EPS using a sample of 131 companies listed in the Tehran Stock Exchange through for the years 1389_1391.The results reveals that the genetic algorithm and swarm optimization is able to extract the effective variables on the EPS amongst the factors affecting EPS, and also have been caused improve power capabilities and expansion of neural network structure.

Keywords

References

Alemtabriz, A., Zandieh, M., Mohammad Rahimi, A. (2008). Meta-Innovative Algorithms for Hybrid Optimization, Saffar pubs, Tehran [In Persian].
Anvari Rostami, A.A., Azar, A., Norozi, M. (2014). Modeling of forecasting EPS with using of fuzzy neural network. Studies in Financial Accounting and Auditing, 6(23), 1-15 [In Persian].
Arab Mazar, M., Ghasemi, M. (2009). Pricing initial public offerings: Combining Artificial neural networks and genetic algorithm. Journal of the Accounting and Auditing Reviews, 58(16), 87-102 [In Persian].
Demori, D., Darioush, F., Ashar, M. (2011). Predicting Tehran stock market aggregete index with particle swarm optimization and comparsion with traditional models. Journal of Accounting Knowledge, 2(5), 7-30 [In Persian].
Etemadi, H., Anvari Rostami, A.A., Ahmadian, V. (2015). Models. Journal of Financial Engineering and Securities Management, 6(23), 21-38 [In Persian].
Etemadi, H., Azar, A., Baghaei, V. (2012). Applying neural networks in predicting profitability of listed companies in Tehran Stock Exchange. Journal of Accounting Knowledge, 10(3), 70-51 [In Persian].
Ghasemi, G., (2005). The comparison of management forecast earning and box-jenkins models. M.Sc thesis, Allame Tabatabaei University [In Persian].
Hashemi, A., Sorushnia, A. (2011). An assessment of accruals and its components ability in forecasting abnormal earnings and explaining value of company considering the sign of abnormal earnings. Journal of Accounting Advances, 3(1), 93-112 [In Persian].
Makian, N., Karimi Takalo, S. (2009). Predictive bankruptcy of manufacturing companies with neural networks. Quantities Economics, 1(6), 120-144 [In Persian].
Monfared, J.H., Alinegad, M.A., Metghalchi, S. (2012). A comparative study of neural network models with box Jenkins methodologies in prediction of Tehran price index (TEPIX). Journal of Financial Engineering and Securities Management, 3(11), 1-16 [In Persian].
Pourheidari, O., Azami, Z. (2008). Identifying auditors’ opinions with neural networks. Journal of Accounting Knowledge, 1 (3), 77-97 [In Persian].

Files

History

  • Receive Date: 07 October 2015
  • Revise Date: 22 May 2017
  • Accept Date: 19 August 2017

Share

How to cite

Statistics