Developing a Prediction-Based Stock Returns and Portfolio Optimization Model

Subject Areas : Financial and Economic Modelling

Farzad Eivani ¹ , Davood Jafari Seresht ² , Abbas Aflatooni ³

1 - Department of Accounting, Bu-Ali Sina University, Hamadan, Iran
2 - Department of Economics, Bu-Ali Sina University, Hamedan, Iran
3 - Department of Accounting, Bu-Ali Sina University, Hamadan, Iran

Received: 2021-07-02 Accepted : 2021-11-16 Published : 2022-07-01

Keywords: Decision tree, Stock Return Prediction, Portfolio Selection,

Abstract :

The purpose of this study is to develop a prediction-based stock returns and portfolio optimization model using a combined decision tree and regression model. The empirical evidence is based on the analysis on 112 unique firms listed on the Tehran Stock Exchange from 2009 to 2019. Regression analyses, as well as six decision tree techniques including CHAID, ID3, CRIUSE, M5, CART, and M5 are used to determine the most effective variables for predicting stock returns. The results show that the six decision tree methods perform better than the regression model in selecting the optimal portfolio. Further analysis reveals that the CART model outperforms the other five decision tree models when compared using Akaike and Schwartz Bayesian. This finding is confirmed by comparing the actual returns of the selected portfolio across all six models in 2019. The findings indicate that the predicted returns on portfolio based on the CART model are not significantly different than the actual returns for 2019, suggesting that the selected model appropriately predicts the returns on the portfolio

References:

[1] Abzari, M., Ketabi, S., & Abbasi, A. Optimization of investment portfolio using linear programming methods and presentation of an applied model. Journal of Social Sciences and Humanities, 2005, 22(2), P. 1-17. https://dx.doi.org/10.22099/jaa.2005.3467

[2] Ali Mohammadi, A.M., AbBasimehr, M.H., & Javaheri, A. Prediction of stock return using financial ratios: A decision tree approach. Financial Management Strategy, 2015, 3(4), P. 151-129. https://dx.doi.org/10.22051/jfm.2016.2349

[3] Ali Zadeh, Z. Particle swarm optimization algorithm and optimal portfolio selection. Iranian capital market, 2016, 107, P. 80-82.

[4] Aouni, B. Multi-attribute portfolio selection: New perspectives. Information Systems and Operational Research, 2009, 47(1), P. 1-4. https://doi.org/10.3138/infor.47.1.1

[5] Barkhordari, M.H., Rezaei, M. Optimal portfolio determination of stuck efficient industry using cover analysis of data from the perspective of institutional investors (Case Study: Ansar Bank). Journal of Development In Monetary and Banking Management, 2015, 2(5), P. 53-72.

[6] Barzegari Khaneghah, J., Jamali, Z. Predicting stock returns with financial ratios; An exploration in recent researches. Journal of Accounting, Accountability and Society Interests, 2016, 6(2), P. 71-92. https://dx.doi.org/10.22051/ijar.2016.2432

[7] Behnampour N, Hajizadeh E, Semnani S, Zayeri F. The introduction and application of classification tree model for determination of risk factor for esophageal cancer in golestan province. Jorjani Biomed Journal, 2013; 1(2), P. 38-46. http://goums.ac.ir/jorjanijournal/article-1-183-en.html

[8] Breiman L., Friedman, J., Stone, C.J., & Olshen, R.A. Classification and Regression Trees. 1^ST New York, N.Y.: Chapman and Hall/CRC; 1984. https://doi.org/10.1201/9781315139470

[9] Chalaki, P., Uoosefi, M. Earnings management prediction by decision trees. Accounting and Auditing Studies, 2012, 1(1), P. 110-123. https://dx.doi.org/22034/IAAS.2012.105369

[10] Chang, T.S. A comparative study of artificial neural networks, and decision trees for digital game content stocks price prediction. Expert systems with applications, 2011, 38(12), P. 14846-14851.‏ https://doi.org/10.1016/j.eswa.2011.05.063

[11] Davoodi Kasbi, A., Dadashi, I. Stock price prediction using the Chaid rule-based algorithm and particle swarm optimization (pso). Advances in Mathematical Finance and Applications, 2020, 5(2), P. 197-213. https://doi.org/10.22034/amfa.2019.585043.1184

[12] Delen, D., Kuzey, C., & Uyar, A. Measuring firm performance using financial ratios: A decision tree approach. Expert systems with applications, 2013, 40(10), P. 3970-3983.‏ https://doi.org/10.1016/j.eswa.2013.01.012

[13] Fallahpour, S., Pirayesh Shirazinejad, H. Portfolio formation using diagonal quadratic discriminant analysis and weighting based on posterior probability. Financial Engineering And Securities Management (Portfolio Management), 2018, 9(34), P. 85-103.

[14] Hejazi, R., Mohamadi, S., Aslani, Z., Aghajani, M. Earnings management prediction using neural networks and decision tree in TSE. Accounting and Auditing Review, 2012, 19(2), P. 31-46. https://doi.org/10.22059/acctgrev.2012.29198

[15] Hosseinpour, R., Bagherpour, M.A., & Salehi, M. Identification of financial and non-financial variables affecting the bases for adjusting audit reports related to accounting estimates: data mining approach. Audit knowledge, 2017, 17(1), P. 107-130. http://danesh.dmk.ir/article-1-1494-fa.html

[16] Izadinia, N., Ramesheh, M., & Yadegari, S. Forecast for stock returns based on trading volume. Journal of Financial Accounting, 2012, 4(16), P. 174-160. http://qfaj.ir/article-1-263-fa.html

[17] Jafari, B., Azar, A. Fuzzy decision tree; the new approach in strategy formulation. Management Researches, 2013, 6(19), P. 25-39. https://doi.org/22111/jmr.2013.1257

[18] Jahanshad, A., Parsaei, M. Analysis of factors affecting expected stock returns based on the implied cost of capital. Journal of Investment Knowledge, 2015, 4(14), P. 125-144.

[19] Kaczmarek, T., & Perez, K. Building portfolios based on machine learning predictions. Economic Research-Ekonomska Istraživanja, 2021, 1(1), P. 1-19.‏ https://doi.org/10.1080/1331677X.2021.1875865

[20] Karami, G.R., Moradi, M.T., Moradi, F., & Mosalanezhad, A. Study of linear and nonlinear relationships between financial ratios and stock returns in tehran stock exchange. Accounting and Auditing Reviews, 2007, 13(4), P. 19-46.

[21] Karami, G.R., Talaeei, L. (2013). Predictability of stock returns using financial ratios in the companies listed in Tehran Stock Exchange. International Research Journal of Applied and Basic Sciences, 2013, 5(3), 360-372.‏

[22] Kass, G.V. An exploratory technique for investigating large quantities of categorical data. Journal of the Royal Statistical Society: (Applied Statistics), 1980, 29(2), 119-127.‏ https://doi.org/10.2307/2986296

[23] Keyghobadi, A.R., Fathi, S., & Seif, S. The impact ranking of key balance sheet items and ratios profitability on the optimal portfolio selection (with data mining technique), Financial Accounting and Audit Research, 2015, 7(28), P. 86-75.

[24] Kim, H., Loh, W.Y. Classification trees with unbiased multiway splits. Journal of the American Statistical Association, 2001, 96(454), P. 589-604.‏ https://doi.org/10.1198/016214501753168271

[25] Mahmoudiazar, M., Raei, R. Prediction of stock market returns with out of sample data: Evaluating out of sample methods (regression method and wavelet neural network). Journal of Asset Management and Financing, 2014, 2(2), P. 1-16.

[26] Moghadam, A., Ghadrdan, E., & Rashedi, M. Predicting stock return by using the market ratios in tehran stock exchange. Accounting and Auditing Research, 2014, 6(24), P. 104-117. https://doi.org/10.22034/iaar.2014.104331

[27] Oztekin, A., Kizilaslan, R., Freund, S., & Iseri, A. A data analytic approach to forecasting daily stock returns in an emerging market. European Journal of Operational Research, 2016, 253(3), P. 697-710.‏ https://doi.org/10.1016/j.ejor.2016.02.056

[28] J.R. Induction of decision trees. Machin Learning, 1986, 1(1), P. 81–106. https://doi.org/10.1007/BF00116251

[29] Rahnemaei Roudeposhti, F., Chavoshi, K., Ibrahim, S. Optimization of portfolios consisting of shares of Tehran Stock Exchange mutual funds with the genetic algorithm approach. Journal Of Investment Knowledge, 2014, 3(4), P. 231-218.

[30] Rai, R., Pouyanfar, A. Advanced investment management. SAMT Press, 2018, Tehran, Iran.

[31] Ramesh, K., Vinitha, A., Dhamodharan, M., & Shanmuga vadive, M. An improved random forest algorithm for effective stock market prediction trending towards machine learning. International Journal of Grid and Distributed Computing, 2020, 13(1), P. 873-881.

[32] Salehi, M., Farrokhi Pilehrood, L. Prediction of earnings management using the neural network and the decision tree. Financial Accounting and Auditing Research, 2018, 10(37), P. 1-24.

[33] Soroushyar, A., Akhlaghi, M. The comparative assessment of data mining methods effectiveness to forecasting return and risk of stock in companies listed in tehran stock exchange. Journal of Financial Accounting Research, 2017, 9(1), P. 57-76. https://doi.org/22108/far.2017.21746

[34] Tavasoli, N., Javid, D. Stock return prediction by decision tree. The 5th National Management and Accounting Conference, 2015. Tehran, Iran.

[35] Tiwari, S., Pandit, R., Richhariya, V. Predicting future trends in stock market by decision tree rough-set based hybrid system with HHMM. International Journal of Electronics and Computer Science Engineering, 2010, 1(3), P. 1578-1587. https://doi.org/10/1/1/261/3105

[36] Uddin, M. R., Rahman, Z., & Hossain, R. Determinants of stock prices in financial sector companies in Bangladesh-A study on Dhaka Stock Exchange (DSE). Interdisciplinary Journal of Contemporary Research in Business, 2013, 5(3), P. 471-480.‏

[37] Wang, H., Jiang, Y., & Wang, H. Stock return prediction based on Bagging-decision tree. International Conference on Grey Systems and Intelligent Services, 2009, P. 1575-1580. https://doi.org//10.1109/gsis.2009.5408165

[38] Wang, Y., & Witten, I. H. Inducing model trees for continuous classes. In Proceedings of the 9TH European conference on machine learning, 1997, 9, London: Springer‐Verlag.

[39] Zamani, M., Afsar, A., Saghafnejad, S.V., & Bayat, E. Expert system Stock price prediction and portfolio optimization using fuzzy neural networks, fuzzy modeling and genetic algorithm. Financial Engineering And Securities Management (Portfolio Management), 2014, 5(21), P. 107-130.