Decision-Induced Ranking Explains Prediction Inflation and Excessive Turnover in SPO-Based Portfolio Optimization
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917524424097792 |
|---|---|
| author | Wang, Yi Hasuike, Takashi |
| author_facet | Wang, Yi Hasuike, Takashi |
| contents | Decision-focused learning (DFL) is attractive for portfolio optimization because it trains predictors according to downstream decision quality rather than prediction accuracy alone. However, SPO(Smart, Predict then Optimize surrogate)-based DFL may produce inflated return signals and unstable portfolio reallocations. This study provides a KKT-based interpretation showing that portfolio decisions can be viewed as ranking over risk- and transaction-cost-adjusted marginal scores. Empirically, we examine prediction inflation and excessive turnover in SPO-trained portfolios, and evaluate clipping, min-max rescaling, and partial portfolio adjustment as practical stabilization mechanisms. The results suggest that realistic output constraints and portfolio-level turnover control improve the implementability of SPO-based portfolio strategies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_01176 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Decision-Induced Ranking Explains Prediction Inflation and Excessive Turnover in SPO-Based Portfolio Optimization Wang, Yi Hasuike, Takashi Portfolio Management Computational Finance Decision-focused learning (DFL) is attractive for portfolio optimization because it trains predictors according to downstream decision quality rather than prediction accuracy alone. However, SPO(Smart, Predict then Optimize surrogate)-based DFL may produce inflated return signals and unstable portfolio reallocations. This study provides a KKT-based interpretation showing that portfolio decisions can be viewed as ranking over risk- and transaction-cost-adjusted marginal scores. Empirically, we examine prediction inflation and excessive turnover in SPO-trained portfolios, and evaluate clipping, min-max rescaling, and partial portfolio adjustment as practical stabilization mechanisms. The results suggest that realistic output constraints and portfolio-level turnover control improve the implementability of SPO-based portfolio strategies. |
| title | Decision-Induced Ranking Explains Prediction Inflation and Excessive Turnover in SPO-Based Portfolio Optimization |
| topic | Portfolio Management Computational Finance |
| url | https://arxiv.org/abs/2605.01176 |