Loading...

A Machine Learning-Based Hierarchical Risk Parity Approach for Portfolio Asset Allocation on the Tehran Stock Exchange

Aghaee Dabaghan Fard, Sina | 2022

75 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 56107 (01)
  4. University: Sharif University of Technology
  5. Department: Industrial Engineering
  6. Advisor(s): Habibi, Moslem; Fazli, Mohammad Amin
  7. Abstract:
  8. The process of portfolio construction and optimization can be broken down into three main steps: selecting appropriate assets, allocating capital, and monitoring and adjusting the portfolio. This study focuses on evaluating the performance of the Hierarchical Risk Parity (HRP) method for capital allocation in investment portfolios, specifically in Iran’s capital market. The aim is to enhance the method's effectiveness by implementing alternative correlation calculation approaches, such as Wavelet and Chatterjee correlations. The study utilizes three different portfolios containing assets from the Tehran Stock Exchange, the US stock market, and the cryptocurrency market. The primary objective is to use the HRP method to allocate optimal weights to each asset in the portfolios, using modern mathematical concepts like graph theory and unsupervised machine learning. While the performance of this method requires further research in markets like the Tehran Stock Exchange, the results indicate that it is more effective in reducing risk than traditional methods. Furthermore, the correlation methods applied in this research provide robust alternatives to conventional methods like Pearson correlation, which are susceptible to outliers and non-linear relationships. The HRP method's performance is particularly enhanced when wavelet correlation is used, especially in high-volatility conditions. Various tests were conducted, including different time windows for correlation calculation and weight adjustment intervals, and the results were robust to these tests. Moreover, in this study, we collected fundamental data for companies listed on the Tehran Stock Exchange and used machine learning models to automate the stock selection process for inclusion in the portfolio based on financial ratios
  9. Keywords:
  10. Portfolio Optimization ; Tehran Stock Exchange ; Machine Learning ; Hierarchical Risk Parity ; Wavelet Correlation ; Chatterjee Rank Correlation ; Asset Allocation ; Resources Allocation

 Digital Object List

 Bookmark