From Economic Explanation to Performance Improvement in Machine-Learning Portfolios

Paper: arXiv 2610.15144

Authors: Yunqi Liang, Stefan Zohren, Mihai Cucuringu

Abstract

To extend conventional model-level feature importance to economically meaningful portfolio outcomes and decisions, we propose a local first-order attribution-propagation framework that maps allocation-function feature exposures to local sensitivities of sequential portfolio performance metrics. We relate the propagated attributions to Shapley values defined directly for portfolio objectives and derive statistical inference for Sharpe-ratio attributions. The resulting attribution-guided feature-exposure intervention enables post-training adaptation, translating portfolio-metric explanations into out-of-sample decisions without retraining the underlying allocation model. We further introduce temporal stabilisation and cross-model averaging as complementary regularisation mechanisms. Empirically, the interventions yield statistically significant improvements in net Sharpe ratios across different model classes.

Complexity vs Empirical Score

• Math Complexity: 0.0/10
• Empirical Rigor: 0.0/10
• Quadrant: Philosophers — conceptual discussion, limited math and data

Why this score: Scoring failed: Could not find valid JSON in LLM response: line 1 column 1 (char 0)

Research Flowchart

  flowchart TD
    A[Research Goal: Improve ML Portfolio Performance & Explainability] --> B{Methodology: Local First-Order Attribution-Propagation Framework};
    B --> C[Inputs: Allocation-Function Feature Exposures, Sequential Portfolio Performance Metrics];
    C --> D{Computational Process: Map Exposures to Local Sensitivities, Derive Sharpe-Ratio Attributions};
    D --> E[Intervention: Attribution-Guided Feature-Exposure Intervention, Temporal Stabilization, Cross-Model Averaging];
    E --> F[Outcomes: Statistically Significant Improvements in Net Sharpe Ratios, Post-Training Adaptation];