Forecasting the Profitability in the Firms Listed in Tehran Stock Exchange Using Data Envelopment Analysis and Artificial Neural Network

محورهای موضوعی : Financial Mathematics

Maryam Saberi ¹ (Department of Management and Accounting, Tarbiat Modares University,Tehran, Iran)
Mohammad Reza Rostami ² (Department of Management and Accounting, Tarbiat Modares University,Tehran, Iran)
Mohsen Hamidian ³ (Department of Economics and Accounting, Islamic Azad University South Tehran Branch, Iran)
Nafiseh Aghami ⁴ (Department of Management and Accounting, Al-Zahra University, Tehran, Iran.)

تاریخ دریافت : 1395/08/22 تاریخ پذیرش : 1395/11/11 تاریخ انتشار : 1395/08/11

کلید واژه: decision making, Fuzzy DEA, Artificial Neural Network (ANN), Earnin predicting,

چکیده مقاله :

Profitability as the most important factor in decision-making, has always been considered by stake holders in the company's profitability. Alsocan bea basis forevaluatingthe performance of themanagers. The ability to predict the profitability can be very useful to help decision-makers. That's why one of the most important issues is the expected profitability. The importance of these forecasts depends on the amount of misalignment with reality. The amount of deviation is less than the forecast of higher accuracy. Although there are various methods for predicting but the use of artificial intelligence techniques is increasing due to fewer restriction. The aim of this study is to evaluate the predictive power of profitability using DEA and neutral network, to enhance the decision-making users of 2012 to 2015of 7 premier financial ratios were used as independent variables. Test results show that both of ANN and DEA have ability to forecast profitability and given that neutral network prediction accuracy is higher than the DEA, the model predict better the profitability of companies.

منابع و مأخذ:

[1] Abdipoor, S. Nasseri A, Akbarpour M, “Integrating Neutral Network and Colonia Competitive    

       Algorithm:” A new approach for predicting bankruptcy in Tehran security exchange "Asian economic and    

       financial review, 2013, 3(11): P. 1528-1539.

[2] Alkali, J, Rashid, Z, “Relationship Between Profitability and Voluntary Disclosure: A case of Banks in  

       Kenya”, Available at SSRN: http:// ssrn.com/abstract=2706027.2015.

[3] Anders,I, Landajo, M & Larca, P, “Forecasting Business Profitability by Using Classification Techniques  

       “: A Comparative Analysis Based on a Spanish CSE. European Journal of Operational Research, 2015, 167,  

       (3), P. 518-542.

[4] Beynon, M, Clatworthy M, “The Prediction of Profitability Using Accounting Narratives: A variable-

      precision rough set approach intelligent systems in accounting, financial finance & management”, 2004, 4,  

      P. 227-242.

[5] Cao,Q & Gan ,Q , “Forecasting EPS of Chinese  Listed Companies Using Neutral Network With GA”,  

       International of Society Systems Science, 2011, 2(3), P. 207-225.

[6] Collopy, F &Armstrong J.S, “Error Measures for Generalizing About Forecasting Methods: Empirical

      Comparisons”. International Journal of forecasting, 1992, 3, P. 69-80.

[7] Dai, W, Jui-yu W, U, Chi-Jie Lu, “Combining Nonlinear Independent Component Analysis and Neutral  

      Network for the Prediction of Asian Stock Market Indexes, Export System with Applications” 2011, 39(4), P.  

      4444-4452.

[8] Demuth H and Beal M, “Matlab 6.5/Neutral Network Toolbar”, Version 4, The Math works, inc, (CD-

       ROM), 2002, P. 1-840.

[9] Drs, Kanam, E, Sinoeraya, M.Si, Ak Rini Widyananingsith, SE, M, Acc, Ak. “The effect of Reported

      Comprehensive Income, Firm Size”, Profitability & Leverage on Income Smoothing. 

      http://ssrn.com/abstract=2731472. 2016.

[10] Galal, H, Muamar bennisa, S, s Vasin, S, “Optimization Optimal Production Program Using Profitability

        Optimization by Genetic Algorithm and Neutral Network”, International Journal of Mechanical

        Aerospace, industrial, Mechatronics & Manufacturing Engineering, 2014, 8, P. 913-918.

[11] Göçken, M, özçalici,M, Boru, A,  Dosdogru, T,  A, “ Integrating Metaheuristics  and Artificial Neutral   

        Networks for Improved Stock Price Prediction”, Expert Systems with Applications, 2016, 44, P. 320-331.

[12] Guoqiang Zhang, B, Eddy Patuwo, Michael Y. Hu, “Forecasting With Artificial Neutral Network”: The   

         State of The Art, International Journal of Forecasting, 1998, 14, P. 35-62.

[13] Hagan, MT, HB Demuth and M Beal, “Neutral Network Design PWS Publishing CO”. Boston,  

         MA. ISBN:0-534-94332-2. 2004.

[14] Hipper, Henrique S, Perdeira, Eduardo, C & Souza Reinaldo, C; “Neutral Networks for Short term load   

        Forecasting: A Review and Education”, IEEE Transactions on Power System, 16:6, 2001, P. 44-55.

[15] Radu, M, Delia, M, Todea, N, “StructureRatios of Profit & Loss Account-Source of Information for      

        Performance Analysis”, Procedia Economic and Finance, 2015, 26, P. 396-403.

[16] Mohiuddin, K, M. Mao, J. K, Jain., A, “Artificial Neutral Networks: A Tutorial, Computational Science &      

        Engineering”, 1996, 29(3), P. 31-44.

[17] Montgomery, C.D, L ynwood, A, I & Gardiner. J.S, “Forecasting Time Series Analysis, Second Ed, Mc    

        Grow Hill”.1990.

[18] P. Ravi Kumar and V Ravi, “Bankruptcy Prediction in Banks and Firms via Statistical and Intelligent

        Techniques”, European Journal of Operational Research, 2007, 180(1), P. 1-28

[20] Shanker, M., Hu,m. Y & M.S. Hugan, “Effect of Data Standardization on Neutral Network Training,    

        Omega”, 1996, 24, P. 385-397.

[21] Shumway, T, “Forecasting Bankruptcy More Accounting: A Simple Model, Journal of Business”, 2004,   

         74, P.101-124.

[22] Tzafestas, S. Tzafestas, E, “Computational Intelligence Techniques for Short Term Electric Load    

        Forecasting”, Journal of Intelligent and Robotic System, 2001, 31, P. 7-68.

[23] Ju-Jie, W, Jain-Zhou, W, Zhe-George, ZH, Shu-Po, G, “Special Issue on Forecasting in Management   

        Science Stock Index Forecasting Based on Hybrid Model. Omega “, 2012, 40(6), P. 758-766.