Improving Stock Return Forecasting by Deep Learning Algorithm

Advances in Mathematical Finance and Applications

مقاله 1، دوره 4، شماره 3، مهر 2019، صفحه 1-13   

نوع مقاله: Research Paper

شناسه دیجیتال (DOI): 10.22034/amfa.2019.584494.1173

نویسندگان

Zahra Farshadfar^{* 1}؛ Marcel Prokopczuk²

¹Departments of Economics, College of Humanities, Kermanshah Branch, Islamic Azad University, Kermanshah, Iran.

²Institute for Financial Markets, Leibniz University Hannover, Hannover, Germany.

چکیده

Improving return forecasting is very important for both investors and researchers in financial markets. In this study we try to aim this object by two new methods. First, instead of using traditional variable, gold prices have been used as predictor and compare the results with Goyal's variables. Second, unlike previous researches new machine learning algorithm called Deep learning (DP) has been used to improve return forecasting and then compare the results with historical average methods as bench mark model and use Diebold and Mariano’s and West’s statistic (DMW) for statistical evaluation. Results indicate that the applied DP model has higher accuracy compared to historical average model. It also indicates that out of sample prediction improvement does not always depend on high input variables numbers. On the other hand when using gold price as input variables, it is possible to improve this forecasting capability. Result also indicate that gold price has better accuracy than Goyal's variable to predicting out of sample return.

کلیدواژه‌ها

deep learning؛ historical average model؛ nonlinear model؛ gold price

مراجع

[1] Adebiyi, A., Adewumi, A., Ayo, C., Comparison of ARIMA and artificial neural networks models for stock price 
prediction, Journal of Applied Mathematics, 2014. Doi: 10.1155/2014.614342.

[2] Agrawal, J., Chourasia, V., Mittra, A., State-of-the-art in stock prediction techniques. International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, 2013, 2(4), P.1360–1366.

[3] Ahmadi, E., Jasemi, M., Monplaisir, L., Nabavi, M., Mahmoodi., A., Amini Jam, P., New efficient hybrid candlestick technical analysis model for stock market timing on the basis of the support vector machine and heuristic algorithms of imperialist competition and genetic, Expert Systems with Applications, 2018, 94(1), P.21-31. Doi:10.1016/j.eswa.2017.10.023.

[4] Bishop, C., M., Pattern Recognition and machine learning, Springer, Germany, 2006.

[5] Brooks, C., Introductory econometrics for finance. 3^rd ed, Cambridge university press, 2015, P.419- 424.

[6] Bollerslev, T., Marrone, J., Xu, L., Zhou, H., Stock return predictability and variance risk premia: Statistical inference and international evidence, Journal of Financial and Quantitative Analysis, 2014, 49(03), P.633–661. Doi: 10.1017/S0022109014000453.

[7] Campbell, S. D., Macroeconomic volatility, predictability, and uncertainty in the great moderation, Journal of Business and Economic Statistics, 2012, 25(2), P.191-200. Doi: 10.1198/073500106000000558

[8] Campbell, J., Thompson, S., Predicting excess stock returns out of sample: Can anything beat the historical average? Review of Financial Studies, 2008, 21(4), P.1509–1531. Doi: 10.1093/rfs/hhm055.

[9] Chong, E., Han, C., Park, F., Deep learning networks for stock market analysis and prediction: Methodology, data representations, and case studies, Expert Systems with Applications, 2017, 83, P.187–205.Doi: 10.1016/j.eswa.2017.04.030.

[10] Diebold, F., Mariano, R., Comparing predictive accuracy, Journal of Business and Economic Statistics, 1995, 13, P.253-263. Doi: 10.1198/073500102753410444.

[11] Ehteshami; S., Hamidian, M., Hajiha, Z., Shokrollahi, S., Forecasting Stock Trend by Data Mining Algorithm, 2018, 3(1), P.97-105. Doi: 10.22034/AMFA.2018.539138.

[12] Enke, D. - Mehdiyev, N., Stock market prediction using a combination of stepwise regression analysis, differential evolution-based fuzzy clustering, and a fuzzy inference neural network, Intelligent Automation and Soft Computing, 2013, 19 (4), P. 636–648. Doi: 10.1080/10798587.2013.839287

[13] Farshadfar, Z., Khalili, M., Study the Effect of Stock Liquidity on Execs Return with Five Factor Arbitrage Pricing Model, 2016, 9(29), P.97-109. (In Persian)

[14] Farshadfar, Z., Prokopczuk, M., Nonlinear Model Improves Stock Return out of Sample Forecasting (Case Study: United State Stock Market), Journal of Finance and Managerial Accounting, 2018, 3 (1), P. 1-13.

[15] Ferreira, M., Santa-Clara, P., Forecasting stock market returns: The sum of the parts is more than the whole. Journal of Financial Economics, 2011, 100 (3), P.514–537. Doi: 10.1016/j.jfineco.2011.02.003.

[16] Goyal, A., Welch, I., Predicting the equity premium with dividend ratios, Management Science, 2003, 49, P.639-654.

[17] Hammoudeh, S., R., Ewing, B. T., Relationships among strategic commodities and with financial variables: a new look, Econ Policy, 2008, 27(2), P.251–264. Doi: 10.1111/j.1465-7287.2008.00126.x.

[18] Jasemi, M., Kimiagari, A., Memariani, A., A conceptual model for portfolio management sensitive to mass psychology of market, International Journal of Industrial Engineering Theory Application and Practice, 2011, 18 (1), P.1–15.

[19] Kim, Y., Enke, D., Developing a rule change trading system for the futures market using rough set analysis, Expert Systems with Applications, 2016a, 59, P.165–173. Doi: 10.1016/j.eswa.2016.04.031

[20] Kim, Y., Enke, D., Using neural networks to forecast volatility for an asset allocation strategy based on the target volatility, Procedia Computer Science, 2016b, 95, P.281–286. Doi: 10.1016/j.procs.2016.09.335

[21] Lee, C., Sehwan, Y., Jongdae, J., Neural Network model versus ARIMA model in forecasting Korean stock price index, Information System, 2007, 8 (2), P.372–378.

[22] Lee, K., Chi, A., Yoo, S., Jin, J., Forecasting Korean stock price index using back propagation neural network model, bayesian chiao’s model, and ARIMA model, Academy of Information and Management Sciences Journal, 2008, 11 (2), P.53 -75.

[23] Nair, V., Hinton, G., Rectified linear units improve restricted Boltzmann machines, 27^th international conference on machine learning, 2010, P.807–814.

[24] Narayan, P., Narayan, S., Modelling the impact of oil prices on Vietnam's stock prices. Applied Energy, 2010, 87, P.356-361. Doi: 10.1016/j.apenergy.2009.05.037.

[25] Narayan, P., Sharma, S., New evidence on oil price and stock returns, Journal of Banking and Finance, 2011, 35, 3253-3262. Doi: 10.1016/j.jbankfin.2011.05.010.

[26] Nasr, N., Farhadi Sartangi, M., Madahi, Z., A Fuzzy Random Walk Technique to Forecasting Volatility of Iran Stock Exchange Index, 2019, 4(1), P.15-30. Doi:10.22034/AMFA.2019.583911.1172.

[27] O’Connor, F. A. – Lucey, B. M. – Batten, J. A. – Baur, D. G., The financial economics of gold a survey. International Review of Financial Analysis, 2015, 41, P.186–205.

[28] Phan, D., Sharma, S., Narayan, P., Stock return forecasting: Some new evidence. International Review of Financial Analysis, 2015, 40, P.38–51. Doi: 10.1016/j.irfa.2015.07.005.

[29] Rapach, D., Strauss, J., Zhou, G., Out-of-sample equity premium prediction: Combination forecast and links to the real economy. Review of Financial Studies, 2010, 23, P.821-862. Doi: 10.1093/rfs/hhp063.

[30] Rather, A., Sastry, V., Agarwal, A., Stock market prediction and Portfolio selection models: a survey. Opsearch, 2017, 54, P.558-579.

[31] Soytas, U., Sari, R., Hammoudeh, S., Hacihasanoglu, E., World oil prices, precious metal prices and macro economy in turkey, Energy Policy, 2009, 37(12), P. 5557–5566. Doi: 10.1016/j.enpol.2009.08.020.

[32] Welch, I., Goyal, A., A comprehensive look at the empirical performance of equity premium prediction, The Review of Financial Studies, 2008, 21 (4), P.1455-1508. Doi: 10.1093/rfs/hhm014.

[33] Westerlund, J., Narayan, P., Does the choice of estimator matter when forecasting stock returns, Journal of Banking and Finance, 2012, 36, P.2632-2640. Doi :10.1016/j.jbankfin.2012.06.005.

[34] West, K., Asymptotic inference about predictive ability, 1996, Econometrica, 64, P. 1067-1084.