Provide an improved factor pricing model using neural networks and the gray wolf optimization algorithm

Advances in Mathematical Finance and Applications

مقاله 2، دوره 8، شماره 1، فروردین 2023، صفحه 23-45   

نوع مقاله: Research Paper

شناسه دیجیتال (DOI): 10.22034/amfa.2022.1942547.1641

نویسندگان

Reza Tehrani¹؛ Ali Souri²؛ Ardeshir Zohrabi^{* 1}؛ Seyyed Jalal Sadeghi Sharif³

¹Financial Management and Insurance, Faculty of Management, University of Tehran, Tehran, Iran

²Faculty of Economics, University of Tehran, Tehran, Iran

³Faculty of Management & Accounting, Shahid Beheshti, University, Tehran, Iran

چکیده

The issue of asset pricing in the market is one of the most important and old issues in the financial world. Factor pricing models seek to be able to determine a significant relationship between return on assets based on the risk parameters of that asset. A wide range of factors can be found in the literature that can be an element for measuring the risk of an asset, but the big question is which of these models will work better. The factors studied in this research include factors that cover market risk, valuation risk, psychological (technical) market risk, profit quality risk, profitability, investment, etc. In this study, we have tried to Using machine learning techniques and optimization tools is a way to derive adaptive-robust nonlinear models that can reduce the risk of model error as much as possible. In this research, two models have been developed. In the first model, using the feature extraction technique and optimization of models based on neural network, a non-linear and adaptable model has been developed for each asset. In the second approach, a portfolio of improved neural network-based models is used in the first stage, which can be used to minimize the risk of model error and achieve a model that is resistant to different market conditions. Finally, it can be seen that the development of these models can significantly improve the risk of error and average error of the model compared to traditional CAPM approaches and the Fama and French three-factor model.

کلیدواژه‌ها

Asset pricing model؛ machine learning؛ neural network؛ gray wolf optimization

مراجع

[1] Asness, C. S., Momentum in Japan: The exception that proves the rule, Journal of Portfolio Management, 2011, 37, P.67–75. Doi:10.3905/jpm.2011.37.4.067

[2] Asness, C. S., Moskowitz, T. J., and Pedersen. L. H., Value and momentum everywhere, Journal of Finance 2013, 68, P.929–85. Doi:10.1111/jofi.12021

[3] Carhart, M. M., On persistence in mutual fund performance, The Journal of Finance1997, 52(1), P.57–82. Doi:10.1111/j.1540- 6261.1997.tb03808.x

[4] Chui, A., Wei, J., and Titman, S., Individualism and momentum around the world, Journal of Finance 2010, 65, P.361–92. Doi:10.1111/j.1540-6261.2009.01532.x

[5] Doaei, M., Mirzaei,A., Rafigh,M., Hybrid Multilayer Perceptron Neural Network with Grey Wolf Optimization for Predicting Stock Market Index, Advances in Mathematical Finance & Applications, 2021, 6(4), P.883-894 Doi: 10.22034/AMFA.2021.1903474.1452

[6] Elliot, B., Docherty, P., Easton, S., and Lee. D., Profitability and investment-based factor pricing models, Accounting & Finance, 2018, 58(2), P.397–421. Doi:10.1111/acfi.12217

[7] Fama, E. F., French, K. R., Common risk factors in the returns on stocks and bonds, Journal of Financial Economics, 1993, 33(1), P.3–56. Doi:10.1016/0304-405X(93)90023-5.

[8] Fama, E. F., French, K. R., Size, value, and momentum in international stock returns, Journal of Financial Economics, 2012, 105(3), P.457–72. Doi:10.1016/j.jfineco.2012.05.011

[9] Fama, E. F., and French, K. R., A five-factor asset pricing model, Journal of Financial Economics, 2015, 116 (1), P.1–22. Doi:10.1016/j.jfineco.2014.10.010

[10] Fama, E. F., and French, K. R., Dissecting anomalies with a five-factor model, The Review of Financial Studies. 2016, 29(1), P.69–103. Doi:10.1093/rfs/hhv043

[11] Fama, E. F., and French, K. R., International tests of a five-factor asset pricing model, Journal of Financial Economics, 2017, 123(3), P.441–63. Doi:10.1016/j.jfineco.2016.11.004

[12] Fama, E. F., and French. K. R., Choosing factors, Journal of Financial Economics, 2018, 128(2), P.234–52. Doi:10.1016/j. jfineco.2018.02.012

[13] Farzinfar,A,A., Jahangirnia,H., The Integration of Multi-Factor Model of Capital Asset Pric ing and Penalty Function for Stock Return Evaluation, Advances in mathematical finance & applications, 2019, 4(2), P.43-64. Doi: 10.22034/amfa.2019.584793.1180

[14] Feldman, D. C, the devil is in the detail: converting good research into publishable articles, Journal of management, 2004, 30(1), P.1–6.  Doi: 10.1016/j.jm.2003.09.001

[15] Gandomi, A. H., Yun, G. J., Yang, X.-S., Talatahari, S., Chaos-enhanced accelerated particle swarm optimization, Communications in Nonlinear Science and Numerical Simulation, 2013, 18(2), P.327–340.

 Doi: 10.1016/j.cnsns.2012.07.017

[16] Guo, B., Zhang, W., Zhang, Y., and Zhang, H., The five-factor asset pricing model tests for the Chinese stock market, Pacific-Basin Finance Journal, 2017, 43, P.84–106. Doi:10.1016/j.pacfin.2017.02.001

[17] Hanauer, M. X., and Lauterbach, J. G., The cross-section of emerging market stock returns, Emerging Markets Review. 2019, 38, P.265–86. Doi:10.1016/j.ememar.2018.11.009

[18] Huynh, T. D., Explaining anomalies in Australia with a five-factor asset pricing model, International Review of Finance, 2018, 18(1), P.123–35. Doi:10.1111/irfi.12125

[19] Jacobs, H., Market maturity and mispricing, Journal of Financial Economics, 2016, 122, P.270–87. Doi:10.1016/j. jfineco.2016.01.030

[20] Karolyi, A. G., Home bias, an academic puzzle, Review of Finance, 2016, 20, P.2049–78. Doi:10.1093/rof/rfw007

[21] Khani Farahani, A., Sheshmani, M., Mohades, A., Studying the Expected Returns Based on Carhart Model Com-pared to CAPM Model and Implicit Capital Cost Model Based on Cash and Capital Flow of Growth and Value Stocks, Advances in Mathematical Finance and Applications, 2017, 2(4), P.61-79. Doi:10.22034/AMFA. 2017.536267

[22] Kubota, K., and Takehara. H., Does the Fama and French five-factor model work well in Japan? International Review of Finance, 2018, 18(1), P.137–46. Doi:10.1111/irfi.12126

[23] Lin, Q., Noisy prices and the Fama–French five-factor asset pricing model in China, Emerging Markets Review, 2017, 31, P.141–63. Doi:10.1016/j.ememar.2017.04.002

[24] Lintner, J., The valuation of risk assets and the selection of risky investments in stock portfolios and capital budgets, The Review of Economics and Statistics, 1965, 47(1), P.13–37. Doi:10.2307/1924119.

[25] 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

[26] Mashayekhi, B., Panahi, D., The Investigation of Relationship between Financial Ratios and Stock Return: Income Smoother Firms Versus Non-Income Smoother ones, Financial Research Journal, 2008, 9(3), (in Persian).Dor: 20.1001.1.10248153.1386.9.24.5.2

[27] Matevž, S., Lončarski, I., Multi-factor asset pricing models: Factor construction choices and the revisit of pricing factors, Journal of International Financial Markets, Institutions and Money, 2018, 55, P.65-80, Doi:10. 1016/j.intfin.2018.02.006

[28] Miller, M. H., and Modigliani. F., Dividend policy, growth, and the valuation of shares, The Journal of Business. 1961, 34(4), P.411–33. Doi:10.1086/jb.1961.34.issue-4

[29] Mirjalili, S. M., Lewis, A., Grey wolf optimizer, Advances in Engineering Software, 2014, 69, P.46–61. Doi: 10.1016/j.advengsoft.2013.12.007

[30] 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

[31] Ramzi Radchobeh, Z., Rezazadeh, J., Kazemi, H., Ambiguity Theory and Asset Pricing: Empirical Evidence from Tehran Stock Exchange, Advances in Mathematical Finance and Applications, 3(4), P.101-114, 2018, Doi: 10.22034/AMFA.2019.579558.1143

[32] Rashid, A., 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, Doi:10.1016/j.econlet.2015.03.019

[33] Ross, S. A., The Arbitrage Theory of Capital Asset Pricing, Economic Theory, 1976, 13, P. 341–360. Doi: 10.1016/0022-0531(76)90046-6

[34] Roy, R., Shijin, S., Dissecting anomalies and dynamic human capital: The global evidence, Borsa Istanbul Review, 2018, 18(1), P.1-32, Doi:10.1016/j.bir.2017.08.005.

[35] Sharpe, W. F., Capital asset prices: A theory of market equilibrium under conditions of risk, The Journal of Finance, 1964, 19(3), P.425–42. Doi:10.2307/2977928

[36] Taherinia, M., Rashidi Baghi, M., Prediction the Return Fluctuations with Artificial Neural Networks’ Approach, Advances in mathematical finance and applications, 2019, 4(2), P.103-114. Doi: 10.22034/amfa.2019.580643.1149

[37] Yang, X.-S., Flower pollination algorithm for global optimization, In Unconventional computation and natural computation, 2012, P.240–249. Springer. Doi: 10.1007/978-3-642-32894-7_27

[38] Zaremba, A., and Maydybura. A., The cross-section of returns in frontier equity markets: Integrated or segmented pricing? Emerging Markets Review, 2019, 38, P. 219–38. Doi:10.1016/j.ememar.2019.02.003.