Stock portfolio optimization of companies listed on the Tehran Stock Exchange based on a combination of two-level ensemble machine learning methods and multi-objective meta-innovative algorithms based on market timing approach

Subject Areas : Financial engineering

sanaz faridi ¹ , amir daneshvar ² , Mahdi Madanchi Zaj ³ , Shadi Shahverdiani ⁴

1 - Department of Financial Management, Science and Research Branch, Islamic Azad University, Tehran, Iran
2 - Department of Industrial Management, Electronic Campus, Islamic Azad University, Tehran, Iran
3 - Department of Financial Management, Electronic Campus, Islamic Azad University, Tehran, Iran
4 - Department of Financial management, Shahr-e-Qods Branch, Islamic Azad University, Tehran, Iran

Received: 2021-11-14 Accepted : 2021-12-19 Published : 2022-09-23

Keywords: "Multi-objective meta-heuristic algorithms", " Portfolio optimization", "Market timing", "Combined (ensemble) machine learning model",

Abstract :

In this article, using the market timing approach and homogeneous and inhomogeneous collective learning methods, the purchase, maintenance and sales signal and market forecast are presented based on the basic characteristics, technical characteristics and time series of returns of each company in the 100 days leading to the current day. . Based on this, 208 companies were selected as active companies between 1390 and 1399 To teach data by two-level ensemble learning machine (HHEL) and market trend forecasting based on market timing strategy, use data from 5 years 1390 to 1394 and to test the data as stock portfolio optimization based on stock portfolio maximization and risk minimization. The investment portfolio uses MOPSO and NSGA II algorithms and is compared with the obtained investment portfolio with the buy and hold strategy. The results showed that the MOPSO algorithm achieved the highest stock portfolio yield with 96.437% compared to the NSGA II algorithm with a yield of 91.157% and the same investment method with a yield of 13.058%. Also, the portfolio risk in NSGA II algorithm was much lower than the portfolio risk in MOPSO algorithm with 0.792% and 1.367%, respectively