Portfolio optimization requires accurate estimates of expected returns and covariances. For return prediction, combining multiple forecasting models improves accuracy, but traditional methods assume model reliability can be quantified through past performance. This assumption fails when predictive relationships undergo structural breaks, creating epistemic uncertainty about which models will prove reliable. For covariance estimation, realized covariance models using high-frequency data offer precision gains, but computational barriers limit their applications to approximately 5 assets, far below diversification requirements. This paper addresses both challenges through a unified framework that combines principled uncertainty management in returns forecasting with scalable high-frequency covariance estimation. We develop a knowledge-based system using Dempster-Shafer Theory that learns to combine multiple forecasting models while explicitly representing uncertainty about their reliability. We derive a computationally tractable framework for estimating realized covariance models that capture asymmetric volatility dynamics for portfolios of 25-30 assets. Integrating these within Black-Litterman, our approach achieves an annualized certainty-equivalent return of 5.6% over 2011-2020, substantially exceeding both naive diversification and standard Black-Litterman, with benefits extending to traditional benchmark strategies.
| Original language | English |
|---|
| Pages (from-to) | 727-742 |
|---|
| Number of pages | 16 |
|---|
| Journal | Quantitative Finance |
|---|
| Volume | 26 |
|---|
| Issue number | 5 |
|---|
| Early online date | 17 Mar 2026 |
|---|
| DOIs | |
|---|
| Publication status | E-pub ahead of print - 17 Mar 2026 |
|---|
We are grateful to the Editor, an Associate Editor, and two anonymous referees for their helpful suggestions, which greatly improved this paper. We also thank Massimo Guidolin, the conference participants at the 18th International Joint Conference on Computational and Financial Econometrics (CFE) and Computational and Methodological Statistics (CMStatistics) at King’s College London, the 37th International Conference of the French Finance Association (AFFI),the 11th International Conference of the Financial Engineering and Banking Society (FEBS), the 2023 Annual Meeting of the European Financial Management Association (EFMA),and seminar participants at University of Liechtenstein for their helpful comments and suggestions.
- Risk Management
- Decision-making
- Knowledge Fusion
- Realized Volatility
- Finance
- Economics, Econometrics and Finance (miscellaneous)
- Management Science and Operations Research