AI-Driven Strategic Asset Allocation vs Traditional Mean-Variance Optimization: Evidence from Global Institutional Portfolios
“Results demonstrate that AIenhanced return forecasts improve portfolio performance compared to traditional historical mean approaches, achieving a Sharpe ratio of 0.79 compared to 0.72 for standard MVO.”
AssetMulti-asset
StrategyPortfolio optimizationmachine learning
TechniqueRecurrent neural networktree ensemble
GeographyGlobal
Also stated: 2015–2026, Sharpe ratio, Information ratio, Excess return, Drawdown
Missing from abstract: benchmark, out-of-sample test, costs, multiple testing, universe
Institutional-grade audit of this strategy.
£5 — Request the audit- Audit of the paper claims accounting for costs, luck, crises, originality, geography, etc.
- Reproduction code integratable into Bloomberg, IBKR, etc.
- Bias-free datasets for backtesting included
- Delivered in 2 working days
The paper's neighbourhoodPortfolio optimization by year
The family is counted across the whole universe. Asset, method and authors are counted inside the family.
| Similar papers | citation | same method | same asset | same authors | |
|---|---|---|---|---|---|
| On the Limits of Low-Frequency OHLCV Signals in Machine Learning-Driven Portfolio Optimization A Cost-Aware, Leak-Free Benchmark on Large-Cap US Equities by Pardo | 2026 | ||||
| Optimal attention allocation: Picking alpha or betting on beta? by Gu et al. | 2023 | ||||
| A Learnheuristic Approach to A Constrained Multi-Objective Portfolio Optimisation Problem by Bullah and van Zyl | 2023 | ||||
| Factor-Targeted Asset Allocation (Presentation Slides) by Lee and Salerno | 2022 | ||||
| Factor-targeted Asset Allocation: A Reverse Optimization Approach (Working Paper) by Lee and Salerno | 2021 |