Semi-Decision-Focused Learning with Deep Ensembles: A Practical Framework for Robust Portfolio Optimization
I propose Semi-Decision-Focused Learning, a practical adaptation of Decision-Focused Learning for portfolio optimization. Rather than directly optimizing complex financial metrics, I employ simple target portfolios (Max-Sortino or One-Hot) and train models with a convex, cross-entropy loss. I further incorporate Deep Ensemble methods to reduce variance and stabilize performance. Experiments on two universes (one upward-trending and another range-bound) show consistent outperformance over baseline portfolios, demonstrating the effectiveness and robustness of my approach. Code is available at https://github.com/sDFLwDE/sDFLwDE
Code (1)
Tasks
Portfolio OptimizationSimilar Papers 제목 키워드 기반
Data-Aware and Scalable Sensitivity Analysis for Decision Tree Ensembles
Decision tree ensembles are widely used in critical domains, making robustness and sensitivity analysis essential to their trustworthiness. We study the feature sensitivity problem, which asks whether an ensemble is sens…
Novel ensemble collaboration method for dynamic scheduling problems
Dynamic scheduling problems are important optimisation problems with many real-world applications. Since in dynamic scheduling not all information is available at the start, such problems are usually solved by dispatchin…
SchedulingOn Computing Optimal Tree Ensembles
Random forests and, more generally, (decision\nobreakdash-)tree ensembles are widely used methods for classification and regression. Recent algorithmic advances allow to compute decision trees that are optimal for variou…
Uncertainty Quantification for Regression using Proper Scoring Rules
Quantifying uncertainty of machine learning model predictions is essential for reliable decision-making, especially in safety-critical applications. Recently, uncertainty quantification (UQ) theory has advanced significa…
Deep interpretable ensembles
Ensembles improve prediction performance and allow uncertainty quantification by aggregating predictions from multiple models. In deep ensembling, the individual models are usually black box neural networks, or recently,…
Uncertainty Quantification