Advanced Algorithms in Designing and Creating Optimal Portfolios

محورهای موضوعی : • Risk management and its new technologies

Reza Mansourian ¹

1 - Department of Accounting and Financial Engineering, South Tehran Branch, Islamic Azad University, Tehran, Iran

تاریخ دریافت : 1403/04/10 تاریخ پذیرش : 1403/09/16 تاریخ انتشار : 1403/09/30

کلید واژه: Smart Portfolio, Momentum Algorithm, Kalman Filter , kelly Creterion,

چکیده مقاله :

Objectives: Achieving sustained and long-term economic growth requires efficient resource allocation. This research aims to enhance optimization methods based on Sharpe Ratio performance and introduce an intelligent trading method utilizing various algorithms.

Design/methodology/approach: A quantitative investment model is developed using the Momentum Algorithm and a long-term investment model over a six-year horizon. The model is applied monthly from 2019 to 2023 within the stock exchange framework. Additionally, a series of smart models (Overall Functions, Overall Mean, and Overall Algorithm with Kalman Filter) are created to determine capital amounts using intelligent patterns.

Findings: The findings demonstrate that the proposed structure outperforms conventional algorithms, indicating it can serve as a viable alternative for achieving superior investment outcomes.

Innovation: This research contributes to the existing literature by introducing advanced optimization techniques that leverage intelligent algorithms for trading strategies. The findings provide new insights into capital allocation efficiency and risk management in financial markets.

چکیده انگلیسی:

Objectives: Achieving sustained and long-term economic growth requires efficient resource allocation. This research aims to enhance optimization methods based on Sharpe Ratio performance and introduce an intelligent trading method utilizing various algorithms.

Design/methodology/approach: A quantitative investment model is developed using the Momentum Algorithm and a long-term investment model over a six-year horizon. The model is applied monthly from 2019 to 2023 within the stock exchange framework. Additionally, a series of smart models (Overall Functions, Overall Mean, and Overall Algorithm with Kalman Filter) are created to determine capital amounts using intelligent patterns.

Findings: The findings demonstrate that the proposed structure outperforms conventional algorithms, indicating it can serve as a viable alternative for achieving superior investment outcomes.

Innovation: This research contributes to the existing literature by introducing advanced optimization techniques that leverage intelligent algorithms for trading strategies. The findings provide new insights into capital allocation efficiency and risk management in financial markets.

منابع و مأخذ:

 Amiri, M., Haddadian, H.R., Zandieh, M., and Raeiszadeh, A., Presentation of Smart Trading Model in Financial Markets Based on Genetic Algorithm, Fuzzy Logic and Neural Network, Journal of Financial Engineering and Securities Management, 2016, 27, (in Persian).
 Asmerilda Hitaj, Giovanni Zambruno, (2016), Are Smart Beta strategies suitable for Hedge Funds portfolios?, Review of Financial Economics, doi:10.1016/j.rfe.2016.03.001
 Achelis(2000). Journal of Accounting Research. s.l.: Vision Books,
 Ang A., Chen J. and Xing Y. (2006). Downside Risk: Review of Financial Studies, 19(4), 1191-1239.
 Black, F. (1972). Capital Market Equilibrium with Restricted Borrowing. s.l.: Journal of Finance,. 45(3), 444-455.
 Chetran saran mehra, adam prugel , Bennett, (2016), Constructing Smart Portfolios From Data Driven Quantitative Investment Models, A thesis submitted in partial ful_llment for the degree of Doctor of Philosophy.
 E. Gatev, W. N. Goetzmann, and K. G. Rouwenhorst, “Pairs trading: Performance of a relative-value arbitrage rule,” Review of Financial Studies, vol. 19, pp. 797–827, 2006.
 Fabozzi, F. J. & Markowitz, H. M. (2011). Equity Valuation and Portfolio Management. Vol. 199. John Wiley & Sons.
 Jegadeesh, N. and Titman, S. (1993). Returns to buying winners and selling losers: implications for stock market efficiency, Journal of Finance, Vol. 48, pp. 65-91.
 Jamshidi Eini, E., and Khalvarzadeh, H., Investigation of Smart Methods in Problem Solving of Constrained Portfolio in Tehran Stock Market, Quarterly Journal of Financial Analysis Knowledge, 2016, 9(31), (in Persian).
 J. T. Moskowitz, Y. H. Ooib, and L. Pedersenb, “Time series momentum,” Journal of Financial Economics, vol. 104, pp. 228–250, 2011.
 J. Kelly, “A new interpretation of information rate,” Information Theory, vol. 2, pp. 185–189, 1956.
 Heydari, H., and Mollabrahami, A., A Dynamic View on the Value at Risk of Stock Portfolios Based on Space-State and Kalman Filter Models, Third Conference on Financial Mathematics and Applications, Sharif University of Technology, 2012, (in Persian).
 Hirabayashi, A., Aranha, C., & Hitoshi, I. (2009). Optimization of the trading rule in foreign exchange using genetic algorithm. . s.l.: ACM Genetic and Evolutionary Computation,. 1529-1536.
 Huang, C., Chang, C., Li, Kuo, Bo, Lin, Hsieh, T., & Chang, B. (2012). A genetic-search model for first-day returns using fundamentals. . s.l.: Machine Learning and Cybernetics, 5, 1662-1667.
 Huck, N. & Afawubo, K. (2015). Pairs trading and selection methods: is cointegration superior? Applied Economics. 47(6): pp: 599-613.
 Harry Markowitz, 1991, Portfolio selection: efficient diversification of investments, Wiley-Blackwell.
 Hon, M.T., I. tonks (2003). “Momentum in the UK stock markets”, Journal of Multinational Financial Management. 13 (1):43-70.
 Kaucic, M. (2012). Portfolio management using artificial trading
 Khezri, M., Sahabi, B., Yaturi, K., and Heydari, H., Investigating the Time-Varying Effects of Inflation Determinants: Space-state models, Quarterly Journal of Economic Modeling, 2015, 9(30), P. 25- 46, (in Persian).
 Fallah Shams, M., and Ataei, Y., Comparison of the Efficiency of Momentum in Selecting Appropriate Portfolios, Journal of Financial Engineering and Securities Management, 2013, (in Persian).
 Ghasemi Dashtaki, M., Prediction of Initial Public Offering Pricing: Neural Network and Genetic Algorithm Combination, M.A. Theses, University of Tehran, Tehran, Iran, 2008, (in Persian).
 Rahnamay Roodposhti, F., Nikoumaram, H., Toluie Ashlaghi, H., Hosseinzadeh Lotfi, F., and Bayat, M., Investigation of Portfolio Optimization Performance Based on Sustainable Model with Classic Optimization in Risk Prediction and Portfolio Financial Return, Journal Financial Engineering and Securities Management, 2015, 22, (in Persian).
 Rahnamay Roodposhti, F., Chavoshi, K., and Saber, E., Portfolio Optimization of Stocks of Joint Venture Funds of Tehran Stock Exchange with Genetic Algorithm Approach, Quarterly Journal of Investment Knowledge, 2014, 3(12), (in Persian).
 Raei, R., and Saeedi, A., Fundamentals of Financial Engineering and Risk Management (5th Ed.), Tehran: SAMT Publication, 2012, (in Persian).
 Raza , Muhammad Wajid & Ashraf, Dawood, (2018). "Does the Application of Smart Beta Strategies Enhance Portfolio Performance? The Case of Islamic Equity Investments," Working Papers 2018-1, The Islamic Research and Teaching Institute (IRTI).
 N. Baba, T. Kawachi, T. Nomura, Y. Sakatani, (2004), “Utilization of NNs & Gas for improving the traditional technical analysis in the financial market”, SICE annual Conference, 2(2), 1409-1412.
 Torrubiano, R.and Suarez ,A(2008).”A Hybrid Optimization Approach to Index Tracking”, Operation Research Journal, 166
 Kalman, R. E. (1960). A new approach to linear filtering and prediction problems. Journal of basic Engineering. 82(1): 35-45.
 Simpson, P.W., & Osborn, D.R., & Sensier, M. (2001). Modelling businesscycle movements in the UK economy. Economica, 68: 243-267.
 Pakizeh, K., Rahmani, M., and Azizzadeh, F., Investigating the Effect of Investment Styles and Optimal Portfolio Formulation Using Technical Indicators and Fundamental Ratios, Scientific-Research Quarterly Journal of Investment Knowledge, 2017, 6(21), (in Persian).
 Tehrani, R., and Nourbakhsh, A., Investment Management, Charles P. Jones, Negahe Danesh, 2009, (in Persian).
 Tehrani, R., Hendijanizadeh, M., and Norouzian Lakvan, E., Presenting a New Approach for Active Portfolio Management and Smart Stock Trading with Emphasis on Feature Selection Attitude, Scientific-Research Quarterly Journal of Investment Knowledge, 2014, 4(13), (in Persian).
 Tehrani, R., Fallah Tafti, S., and Asefi, S., Optimization of a Portfolio Based onMetaheuristic Krill Herd Algorithms Using Different Risk Criteria in Tehran Stock Exchange, Quarterly Journal of Financial Research, 2018, 4(20), P. 409-426, (in Persian).
 Usta, I., Y.M. Kantar (2011). Mean-Variance-Skewness-Entropy Measures: A Multi-Objective Approach for Portfolio Selection, Entropy. 13: 117-133.
 W. F. Sharpe, “Capital asset prices: A theory of market equilibrium under conditions of risk,” The Journal of Finance, pp. 425–442, 1964.
 S. Ross and R. Roll, “The arbitrage theory of capital asset pricing,” Journal of Economic Theory, vol. 13, pp. 341–360, 1976.
 L. MacLean, E. O. Thorp, and W. T. Z. W. T., The Kelly Capital Growth Investment Criterion, L. MacLean, E. O. Thorp, and W. T. Z. W. T., Eds.
 World Scientific Press, 2011.
 Zhu, H., Wang, Y., Wang, K. and Chen, Y. (2011) .Particle Swarm Optimization (PSO) for the constrained portfolio optimization problem. s.l.: Expert Systems with Applications,. 38: 10161-10169.