FINANCIAL PREDICTION MODELS FROM INTERNAL AND EXTERNAL FIRM FACTORS BASED ON COMPANIES LISTED ON THE STOCK EXCHANGE OF THAILAND
Keywords:
Thai public companies, financial performance, prediction models, internal firm factors, external firm factorsAbstract
In this study, 3 prediction methods using statistical and machine learning techniques,namely logistic regression, artificial neural network (ANN), and support vector machineare compared to classify a company’s financial performance in relation to the averagereturn on assets of all the companies listed on the Stock Exchange of Thailand in each year.In total, there are 1968 firm-year observations for the period from 2005 to 2014. Ourestimated models use a combination of internal firm factors including firm characteristics and financial indicators, and external firm factors from political, economic, social, and technological aspects as indicators for changes in the macro-economic environment. Theresults suggest that the ANN outperforms the other techniques by achieving 71.85%accuracy rates. With these prediction models, managers and decision makers can predicta firm’s financial performance more accurately and can keep track of the performance 1year in advance which helps to identify the firm’s future business trends; these are very important factors for decision makers as to whether or not they should take necessary action to improve their firm’s performance.
References
Agustinus, P. and Rachmadi, P. (2008). Determinants ofcorporate performance of listed companies inIndonesia. Munich, Germany: Munich UniversityLibrary. Available from: mpra.ub.uni-muenchen.de/6777/1/MPRA paper 6777.pdf. Accessed date:1 December 2016.
Almajali, A.Y., Alamro, S.A., and Al Soub, Y.Z. (2012).Factors affecting the financial performance ofJordanian insurance companies listed at AmmanStock Exchange. J. Manag. Research., 4(2):266-289.
Altman, E. (1968). Financial ratios, discriminant analysisand the prediction of corporate bankruptcy.J. Financ., 23(4):589-609.
Alzharani, A.M., Ahmad, A.B., and Aljaaidi, K.S. (2011).An empirical investigation of factors associatedwith firm performance evidence from Kingdom ofSaudi Arabia. International Proceedings ofEconomics Development and Research, 25(1):30-36.
Bagchi, B. (2015). A long-run and short-run cointegrationmodel explaining relationship between liquiditymanagement and profitability. Int. J. Busi. Excel.,8(2):123-145.
Bank of Thailand. (2017). Statistics. Available from:www2.bot.or.th. Accessed date: 2 January 2017
Basterretxea, K., Tarela, J.M., and Del Campo, I. (2004).Approximation of sigmoid function and thederivative for hardware implementation of artificialneurons. IEE P-Circ. Dev. Syst., 151(1):18-24.
Biesebroeck, J.V. (2005). Firm size matters: Growth andproductivity growth in African manufacturing.Econ. Dev. Cult. Change, 53(3):545-583.
Bose, I. and Pal, R. (2006). Predicting the survivalor failure of click-and-mortar corporations:A knowledge discovery approach. Eur. J. Oper.Res., 174(2):959-982.
Boyacioglu, M.A., Kara, Y., and Baykan, O.K. (2009).Predicting bank financial failures using neuralnetworks, support vector machines and multivariatestatistical methods: A comparative analysis in thesample of saving deposit insurance fund (SDIF)transferred banks in Turkey. Expert Syst. Appl.,36(2):3355-3366.
Chang, C.C. and Lin, C.J. (2011). LIBSVM: A library forsupport vector machines. ACM Transactions onIntelligent Systems and Technology, 2(3):27:1-27:27.
Ciampi, F. (2015). Corporate governance characteristicsand default prediction modeling for smallenterprises. An empirical analysis of Italian firms.J. Bus. Res., 68(5):1012-1025.
Delen, D., Kuzey, C., and Uyar, A. (2013). Measuringfirm performance using financial ratios: A decisiontree approach. Expert Syst. Appl., 40(10):3970-3983.
Doan, N.P. and Nguyen, J.D. (2011). Firm characteristics,capital structure and operational performance:A Vietnamese study. Proceedings of the 7thAsia-Pacific Economic Association Conference;June 24-25, 2011; Busan, South Korea.
Evans, D.S. (1987). The relationship between firm growth,size, and age: Estimates for 100 manufacturingindustries. J. Ind. Econ., 35(4):567-581.
Galbraith, V.L. and Thomas, D.S. (1941). Birth rates andthe interwar business cycles. J. Am. Stat. Assoc.,36(216):465-476.
Hovakimian, A., Opler, T., and Titman, S. (2001). Thedebt-equity choice. J. Financ. Quant. Anal.,36(1):1-24.
Iswatia, S. and Anshoria, M. (2007). The influenceof intellectual capital to financial performanceat insurance companies in Jakata Stock Exchange(JSE). Proceedings of the 13th Asia PacificManagement Conference; November 18-20, 2007;Melbourne, Australia, p. 1393-1399.
Khalifa, K.M. and Shafii, Z. (2013). Financialperformance and identify affecting factors inthis performance of non-oil manufacturingcompanies listed on Libyan Stock Market (LSM).European J. Bus. Manag., 5(12):82-99.
Kumar, P.R. and Ravis, V. (2007). Bankruptcy predictionin banks and firms via statistical and intelligenttechniques - A review. Eur. J. Oper. Res., 180(1):1-28.
Lam, M. (2004). Neural network techniques for financialperformance prediction: Integrating fundamentaland technical analysis. Decis. Support Syst.,37(4):567-581.
Lee, Y.C. (2007). Application of support vector machinesto corporate credit rating prediction. Expert Syst.Appl., 33(1):67-74.
Liargovas, P. and Skandalis, K. (2010). Factor affectingfirms financial performance: The case of Greece.Global Business and Management Research,2(2&3):184-197.
Loderer, C. and Waelchli, U. (2010). Firm age andperformance. European Corporate GovernanceInstitute, Finance Working Paper No. 230/2009.Rochester, NY, USA: SSRN. Available from:ssrn.com/abstract=1342248. Accessed date: 17November 2016
Lussier, R.N. (1995). A nonfinancial business successversus failure prediction model for young firms.J. Small Bus. Manage., 33(1):8-20.
Mahajan, R., Garg, S., and Sharma, P. (2014). Anillustration of logistic regression technique: a caseof processed food sector. Int. J. Bus. Excel.,7(5):659-676.
Malhotra, G. and Mukherjee, A. (2013). Comparativestudy of forced distribution and absolute ratingperformance management systems. Int. J. Bus.Excel., 6(2):121-130.
Mokhatab Rafiei, F., Manzari, S.M., and Bostanian,S. (2011). Financial health prediction modelsusing artificial neural networks, genetic algorithmand multivariate discriminant analysis: Iranianevidence. Expert Syst. Appl., 38(8):10210-10217.
Naidu, S. and Chand, A. (2013). Financial problems facedby micro, small and medium enterprises in the smallisland states: a case study of the manufacturingsector of the Fiji Islands. Int. J. Bus. Excel., 6(1):1-21.
Naser, K and Mokhtar, M.Z. (2004). Determinants ofcorporate performance of Malaysian companies.Proceedings of the 4th Asia Pacific InterdisciplinaryResearch in Accounting Conference; July 4-6,2004; Singapore, p. 16-25.
Ogut, H., Doganay, M.M., Ceylan, N.B., and Aktas, R.(2012). Prediction of bank financial strengthratings: The case of Turkey. Econ. Model.,29(3):632-640.
Pantea, M., Gligor, D., and Anis, C. (2014). Economicdeterminants of Romanian firms' financialperformance. Procedia - Social and BehavioralSciences, 124(1):272-281.
Pao, H.T. (2008). A comparison of neural network andmultiple regression analysis in modeling capitalstructure. Expert Syst. Appl., 35(3):720-727.
Pratheepkanth, P. (2011). Capital structure and financialperformance: Evidence from selected businesscompanies in Colombo Stock Exchange Sri Lanka.Int. Ref. Res. J., 2(2):171-183.
Ray, S. (2011). Prediction of corporate financial distress inglass and glassware sector of India. Int. J. Bus.Excel., 4(6):678-695.
Rich, E. and Knight, K. (1991). Artificial Intelligence.2nd ed. Singapore: McGraw-Hill, Singapore,640p.
Roiger, J.R. and Geatz, M.W. (2003). Data MiningA Tutorial Based Primer. Adison Wesley, Boston,MA, USA, 408p.
Rumelhart, D.E., Hinton, G.E., and Williams, R.J. (1986).Learning internal representations by errorpropagation. In: Parallel Distributed Processing:Explorations in the Microstructure of Cognition.Rumelhart, D.E. and Williams, J.L., (eds).:, MITPress, Cambridge, MA, USA, p. 318-362.
Russell, S. and Norvig, P. (2003). Artificial Intelligence:A Modern Approach. 2nd ed. Prentice Hall, UpperSaddle River, NJ, USA, 960p.
Sharma, S.K. and Raina, D. (2013). Performance analysisof Indian automobile sector using non-parametricapproach. Int. J. Bus. Excel., 6(5):505-525.
Shin, K-S., Lee, T.S., and Kim, H-J. (2005). Anapplication of support vector machines inbankruptcy prediction model. Expert Syst. Appl.,28(1):127-135.
Stock Exchange of Thailand. (2017). Companies/Securities in Focus. Available from: www.set.or.th.Accessed date: 2 January 2017
Tam, K.Y. and Kiang, M.Y. (1992). Managerialapplications of neural networks: the case of bankfailure prediction. Manage. Sci., 38(7):926-947.
Tinoco, M.H. and Wilson, N. (2013). Financial distressand bankruptcy prediction among listed companiesusing accounting market and macroeconomicvariables. International Review of FinancialAnalysis, 30:394-419.
Vapnik, V.N. (1998). Statistical Learning Theory. JohnWiley and Sons, Hoboken, NJ, USA, 768p.
Weintraub, R. (1962). The birth rate and economicdevelopment: An empirical study. Econometrica,40(4):812-817.
Wu, W., Lee, V.C., and Tan, T.Y. (2006). Datapreprocessing and data parsimony in corporatefailure forecast models:Evidence from Australianmaterials industry. Account. Financ., 46(2):327-345.
Xu, W., Xiao, Z., Dang, X., Yang, D., and Yang, X.(2014). Financial ratio selection for business failureprediction using soft set theory. Knowledge-BasedSystems, 63(1):59-67.
Yang, C.C., Lee, C.F., Gu, Y.X., and Lee, Y.W. (2010).Co-determination of capital structure and stockreturns - A LISREL approach: An empirical test ofTaiwan stock markets. Q. Rev. Econ. Financ.,50(2):222-233.
Youn, H. and Gu, Z. (2010). Predicting Korean lodgingfirm failures: An artificial neural network modelalong with a logistic regression model. Int. J. Hosp.Manag., 29(1):120-127.
Zeitun, R. and Tian, G. (2007). Capital structure andcorporate performance: Evidence from Jordan.Australian Accounting, Business and Finance J.,1(4):40-61.
Zhang, G., Hu, M.Y., Patuwo, B.E., and Indro, D.C.(1999). Artificial neural networks in bankruptcyprediction: General framework and cross-validationanalysis. Eur. J. Oper. Res., 116(1):16-32.
