Forecasting the Tehran Stock market by Machine ‎Learning Methods using a New Loss Function

Document Type: Research Paper

Authors

1 Department of mathematics, Ferdowsi University of Mashhad, Mashhad, Iran

2 Department of Mathematics and Statistics, Macquarie University, Sydney, Australia

10.22034/amfa.2020.1896273.1399

Abstract

Stock market forecasting has attracted so many researchers and investors that ‎many studies have been done in this field. These studies have led to the ‎development of many predictive methods, the most widely used of which are ‎machine learning-based methods. In machine learning-based methods, loss ‎function has a key role in determining the model weights. In this study a new loss ‎function is introduced, that has some special features, making the investing in the ‎stock market more accurate and profitable than other popular techniques. To ‎assess its accuracy, a two-stage experiment has been designed using data of ‎Tehran Stock market. In the first part of the experiment, we select the most ‎accurate algorithm among some of the well-known machine learning algorithms ‎based on artificial neural network, ANN, support vector machine, SVM. In the ‎second stage of the experiment, the various popular loss functions are compared ‎with the proposed one. As a result, we introduce a new neural network using a ‎new loss function, which is trained based on genetic algorithm. This network has ‎been shown to be more accurate than other well-known and common networks ‎such as long short-term memory (LSTM) for both train and test data.‎

Keywords


[1] Murphy, J., Technical Analysis of the Financial Markets, New York Institute of Finance, 1999, P. 24-31.

[2] Huber, Peter J., Robust Estimation of a Location Parameter, Annals of Mathematical Statistics, 1964, 53 (1), P.73–101.  Doi:10.1214/aoms/1177703732

[3] Warren S. and Walter P., A logical calculus of the ideas immanent in nervous activity, 1943, The bulletin of mathematical biophysics, 5, P.115–13.

 [4] Vapnik, V., Golowich, S. E. and A. J. Smola, A. J., Support vector method for function approximation, regression estimation and signal processing, 1997, New York, Cambridge, MA: MIT Press.

[5] Hsu, S., Hsieh, J., Chih, T., and Hsu, K., A two-stage architecture for stock price forecasting by integrating self-organizing map and support vector regression, Expert Systems with Applications, 2009, 36(4), P.7947-7951. Doi:10.1016/j.eswa.2008.10.065

[6] Kimoto, T., Asakawa, K., Yoda, M., and Takeoka, M., Stock market prediction system with modular neural network, Proceedings of the International Joint Conference on Neural Networks, 1990, P.1–6. Doi:10.1109/ijcnn.1990.137535

[7]  Hedayati Moghaddamb, A., Hedayati Moghaddamb, M. and Esfandyari, M., Stock market index prediction using artificial neural network, Journal of Economics, Finance and Administrative Science, 2016, 21, (41) , 89-93, Doi: 10.1016/j.jefas.2016.07.002

[8] Gandhmal, P., Dattatray and Kumar, K., Systematic analysis and review of stock market prediction techniques, Computer Science Review, 2019, 34, 100190.‎  Doi:10.1016/j.cosrev.2019.08.001

[9] Diler, A., Forecasting the direction of ISE National-100 index by neural networks backpropagation algorithm, ISE Review, 2003, 7, P.65-81.

[10] Kim, K., Financial time series forecasting using support vector machines, Neurocomputing, 2003,  55(1-2), P.307-319. Doi:10.1016/s0925-2312(03)00372-2

[11] Nabipour, M., Nayyeri, P., Jabani, H.,  Mosavi, A.,  Salwana, E. and Shahab, S., Deep Learning for Stock Market Prediction,  Entropy, 2020, 22, 840, Doi:10.3390/e22080840

 [12] Huang, W., Nakamori, Y., and Shou-Yang, W., Forecasting stock market movement direction with support vector machine, Computers & Operations Research, 2005, 32, P.2513-2522.  Doi:10.1016/j.cor.2004.03.016

[13] Altay, E., and Satman, M. H., Stock Market Forecasting: Artificial Neural Networks and Linear Regression Comparison in an Emerging Market, Journal of Financial Management and Analysis, 2005, 18(2), P.18-33.

[14] Cao, Q., Leggio, K. B., and Schniederjans, M.J.,  A comparison between Fama and French’s model and artificial neural networks in predicting the Chinese stock market, Computers & Operations Research, 2005, 32, P.2499-2512.  Doi:10.1016/j.cor.2004.03.015

[15] Roh, T.H., Forecasting the volatility of stock price index, Expert Systems with Applications, 2007, 33, P.916–922. Doi:10.1016/j.eswa.2006.08.001

[16] Hyup Roh, T., Forecasting the volatility of stock price index, Expert Systems with Applications, 2007 33(4), P.916–922.  Doi: 10.1016/j.eswa.2006.08.001

[17] Rashid, A., and Ahmad, S., Predicting stock returns volatility: An evaluation of linear vs. nonlinear methods, International Research Journal of Finance and Economics, 2008, 20, P.141–150.

[18] Manish, k., and Thenmozhi, M., Forecasting stock index movement: A comparison of support vector machines and random forest, Indian Institute of Capital Market Conference, Mumbai India, 2005. Doi:10.2139/ssrn.876544

[19] Xu, X., Zhou, C., and Wang, Z., Credit scoring algorithm based on link analysis ranking with support vector machine, Expert Systems with Applications, 2009, 36 (2), P.2625-2632.  Doi:10.1016/j.eswa.2008.01.024

 [20] Kara, Y., Boyacioglu, M.A., Baykan, O.K., Predicting direction of stock price index movement using artificial machines: the sample of the IStanbul STock Exchange, Expert Systems with Applications, 2011, 38(5), P.5311-5319.  Doi:10.1016/j.eswa.2010.10.027

[21] Kara, Y., AcarBoyacioglu, M., and Baykan, O.K., Predicting direction of stock price index movement using artificial neural networks and support vector machines: The sample of the Istanbul Stock Exchange, Expert Systems with Applications, 2011, 38 (5), P.5311–5319.  Doi: 10.1016/j.eswa.2010.10.027

[22] Patel, J., Shah, S., Thakkar, P., and Kotecha, K., Predicting stock market index using fusion of machine learning techniques, Expert Systems with Applications, 2015, 42 (4), P.2162–2172.  Doi: 10.1016/ j.eswa.2014. 10.031

[23] Patel, J., Shah, S., Thakkar, P., and Kotecha, K., Predicting stock and stock price index movement using trend deterministic data preparation and machine learning techniques, Expert Systems with Applications, 2015,42(1), P.259-268. Doi:10.1016/j.eswa.2014.07.040

‎[24] Štěpánek, J., Šťovíček, J., Cimler, R., Application of Genetic Algorithms in Stock Market Simulation, ‎Social and Behavioral Sciences, 2012, 47, P.93-97. Doi:10.1016/j.sbspro.2012.06.619 ‎

[25] Montri, I., Veera B., and Sarun I., Artificial Neural Network and Genetic Algorithm Hybrid Intelligence for Predicting Thai Stock Price Index Trend, Computational Intelligence and Neuroscience, 2016 ID, 6878524 Doi:10.1155/2016/3045254

[26] Hsu, M.W., Lessmann, S., Sung, M.C., Ma, T. and Johnson, J.E., Bridging the divide in financial market forecasting: machine learners vs. Financial economists, Expert Systems with Applications, 2016, 61(1), P.215-234.  Doi:10.1016/j.eswa.2016.05.033

 [27] Inthachot, M., Boonjing, V., and Intakosum, S., Artificial Neural Network and Genetic Algorithm Hybrid Intelligence for Predicting Thai Stock Price Index Trend, Computational Intelligence and Neuroscience, 2016, ID 3045254.  Doi:10.1155/2016/3045254

[28] Ramezanian, R., Peymanfar, A., and Ebrahimi, S. B., An integrated framework of genetic network programming and multi-layer perceptron neural network for prediction of daily stock return: An application in Tehran stock exchange market, Applied Soft Computing Journal, 2019, 82, 105551. Doi: 10.1016/ j.asoc.

 [29] Matyjaszek, M., Fernández, P. R., Krzemień, A., Wodarski, K. and Valverde G. F., Forecasting coking coal prices by means of ARIMA models and neural networks, considering the transgenic time series theory. Resources Policy, 2019, 61, P.283-292. Doi:10.1016/j.resourpol.2019.02.017

[30] Matheus, J. S. S., Fahad, F. W. A., Bruno, M. H., Ana B. N., aDanilo, G. R., Vinicius A.S. and Herbert K., Can artificial intelligence enhance the Bitcoin bonanza, The Journal of Finance and Data Science, 2019, 5, P.83-98.  Doi:10.1016/j.jfds.2019.01.002

[31] Alberta, A. A., Lópezb, L. F. M., and Blasb, N. G., Multi linear Weighted Regression (MWE) with Neural Networks for trend prediction, Applied Soft Computing Journal, 2019, 82, 105555. Doi:0.1016/j.asoc.2019.105555

 [32] Botchkarev, A., Performance Metrics (Error Measures) in Machine Learning Regression, Forecasting and Prognostics: Properties and Typology, Interdisciplinary Journal of Information, Knowledge, and Management, 2019, 14, P.45-79. Doi:10.28945/4184

[33] Shah, D., Isah, H., Zulkernine, F., Stock market analysis: A review and taxonomy of prediction techniques, Int. J. Financial Stud., 2019, 7(2), 26. Doi: 10.3390/ijfs7020026.

[34] Zhong, X., Enke, D., Predicting the daily return direction of the stock market using hybrid machine learning algorithms. Financial Innovation, 2019, 5 (1), 1-20.  Doi: 10.1186/s40854-019-0138-0

[35] Wen, M., Li, P., Zhang, L., Chen, Y., Stock Market Trend Prediction Using High-Order Information of Time Series, IEEE Access 2019, 7, 28299–28308. Doi: 10.1109/ACCESS.2019.2901842

 

[36] Cervelló-Royo, R., Guijarro, F.,  Forecasting stock market trend: A comparison of machine learning algorithms, Financ. Mark. Valuat. 2020, 6, 37–49. Doi: 10.46503/NLUF8557

 

[37] Papageorgiou, K.I., Poczeta, K., Papageorgiou, E., Gerogiannis, V.C., Stamoulis, G., Exploring an Ensemble of Methods that Combines Fuzzy Cognitive Maps and Neural Networks in Solving the Time Series Prediction: Problem of Gas Consumption in Greece. Algorithms, 2019, 12 (11), 235.  Doi: 10.3390/a12110235

 

[39] Ghasemzadeha, M., Mohammad-Karimi, N., Ansari-Samani, H., Machine learning algorithms for time series in financial markets, Advances in Mathematical Finance and Applications, 2020, 4(5), P. 479-490. Doi:10.22034/amfa.2020.674946

 

[40] 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, 2(5), P. 197-213. Doi 10.22034/amfa.2019.585043.1184
 

[41] Tavana, M., Izadikhah, M., Di Caprio, D., Farzipoor Saen, R., A new dynamic range directional measure for two-stage data envelopment analysis models with negative data, Computers & Industrial Engineering, 2018, 115, P. 427-448, Doi: 10.1016/j.cie.2017.11.024

 
[42] Randall, S., Sexton, Jatinder, N. D., and Gupta, b., Comparative evaluation of genetic algorithm and backpropagation for training neural networks, Information Sciences, 2000, 129, P.45-59. Doi:10.1016/s0020-0255(00)00068-2
 

[43] Izadikhah, M., Improving the Banks Shareholder Long Term Values by Using Data Envelopment Analysis Model, Advances in Mathematical Finance and Applications, 2018, 3(2), P. 27-41. Doi: 10.22034/amfa.2018.540829

[44] Dorsey, R.E., Mayer, W.J., Optimization Using Genetic Algorithms, Advances, in: J.D. Johnson, A.B. Whinston (Eds.), Artificial Intelligence in Economics, Finance, and Management, Vol. 1. JAI Press Inc., Greenwich, CT, P.1994.

[45] Dorsey, R.E., Mayer, W.J., Genetic algorithms for estimation problems with multiple optima, non-differentiability and other irregular features, Journal of Business and Economic Statistics, 1995, 13, P.53-66.  Doi:10.2307/1392521

[46] Dibachi, H., Behzadi. MH, Izadikhah, M., Stochastic Modified MAJ Model for Measuring the Efficiency and Ranking of DMUs, Indian Journal of Science and Technology, 2015, 8 (8), P. 549–555, Doi: 10.17485/ijst/2015/v8iS8/71505

 

‎[47] Sinayi, H., Mortazavi, S., Teymoori Asl, Y., Tehran Stock Exchange Index forecasting using artificial

neural networks, Journal of Accounting and Auditing Review, 2005, 41, 59-83.