Research map / Learning theory and algorithms / Prediction and decision losses
Deep Portfolio Optimization via Distributional Prediction of Residual Factors
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use spectral residuals instead of raw returns | DPO · U.S. market | ASR: +0.874 -> +1.393 | Helped |
| Add quantile-based distributional prediction rather than predicting only conditional means (ablation) | DPO · U.S. market, spectral residuals | ASR: +1.237 -> +1.393 | Helped |
| Add the fractal network instead of using a multilayer perceptron (ablation) | DPO · U.S. market, spectral residuals | ASR: +1.284 -> +1.393 | Helped |
| Add volatility normalization to the fractal network (ablation) | DPO · U.S. market, spectral residuals | ASR: +1.154 -> +1.393 | Helped |
| Add quantile-based distributional prediction rather than predicting only conditional means (ablation) | DPO · U.S. market, raw returns | ASR: +0.405 -> +0.874 | Helped |
| Add the fractal network instead of using a multilayer perceptron (ablation) | DPO · U.S. market, raw returns | ASR: +0.854 -> +0.874 | Helped |
| Add volatility normalization to the fractal network (ablation) | DPO · U.S. market, raw returns | ASR: +0.542 -> +0.874 | Helped |
| Use spectral residuals instead of FA residuals | Reversal strategy · Japanese market | ASR: 2.64 -> 2.86 | Helped |
Closest papers by meaning
- FactorGCL: A Hypergraph-Based Factor Model with Temporal Residual Contrastive Learning for Stock Returns Prediction (AAAI 2025 · similarity 0.86)
- AlphaForge: A Framework to Mine and Dynamically Combine Formulaic Alpha Factors (AAAI 2025 · similarity 0.86)
- Distributional Adversarial Attacks and Training in Deep Hedging (NeurIPS 2025 · similarity 0.86)
- DHMoE: Diffusion Generated Hierarchical Multi-Granular Expertise for Stock Prediction (AAAI 2025 · similarity 0.85)
- Retrieval-Augmented Diffusion Modeling for Stochastic Discount Factor Portfolios (NeurIPS 2026 · similarity 0.85)
- Operator Deep Smoothing for Implied Volatility (ICLR 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.