Modeling regime changes to improve portfolio diversification and performance

Asset allocation – the decision of how to divide a portfolio among the major asset classes such as cash, stocks and bonds – is a key determinant of portfolio performance. Because financial markets go through periods of strong and weak economies, the performance of an asset class varies with shifting economic conditions. These regime shifts pose a challenge to the asset allocation decision because they impact the portfolio’s return and risk. The objective of this research project is to develop efficient statistical algorithms to identify, model and forecast market regimes and the main drivers that impact the performance of an investment portfolio. Based on these algorithms, a strategy is developed to modify the asset allocation when changes in financial and economic conditions are detected. This investment strategy is expected to provide better long-term results when compared to more static approaches.

Faculty Supervisor:

Maciej Augustyniak

Student:

Kassimou Abdoul Haki Maoude

Partner:

Caisse de dépôt et placement du Québec

Discipline:

Mathematics

Sector:

Finance, insurance and business

University:

Université de Montréal