Research map / Probabilistic and scientific modeling / Variational and generative sampling
FactorVAE: A Probabilistic Dynamic Factor Model Based on Variational Autoencoder for Predicting Cross-Sectional Stock Returns
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 |
|---|---|---|---|
| add prior-posterior learning to train the factor predictor toward posterior factors (ablation) | FactorVAE · China A-shares test | Rank IC: 0.042(0.003) -> 0.055(0.004) | Helped |
| add prior-posterior learning to train the factor predictor toward posterior factors (ablation) | FactorVAE · China A-shares test | Rank ICIR: 0.384(0.033) -> 0.568(0.044) | Helped |
| replace CA-style portfolio construction with dynamically re-weighted portfolios (ablation) | FactorVAE factor encoder · Missing stocks m=50 | Rank IC: 0.043(0.005) -> 0.053(0.007) | Helped |
| replace CA-style portfolio construction with dynamically re-weighted portfolios (ablation) | FactorVAE factor encoder · Missing stocks m=100 | Rank IC: 0.039(0.003) -> 0.056(0.002) | Helped |
| replace CA-style portfolio construction with dynamically re-weighted portfolios (ablation) | FactorVAE factor encoder · Missing stocks m=200 | Rank IC: 0.041(0.004) -> 0.050(0.008) | Helped |
| use risk-adjusted returns in TopK-Drop stock selection (ablation) | FactorVAE portfolio strategy · China A-shares portfolio test | AR: 15.32% -> 16.32% | Helped |
| use risk-adjusted returns in TopK-Drop stock selection (ablation) | FactorVAE portfolio strategy · China A-shares portfolio test | SR: 1.92 -> 2.09 | Helped |
| use risk-adjusted returns in TopK-Drop stock selection (ablation) | FactorVAE portfolio strategy · China A-shares portfolio test | MDD: 4.47% -> 4.50% | No clear effect |
| use probabilistic latent factors and the proposed prior-posterior learning | FactorVAE · China A-shares portfolio test | AR: 3.62% -> 15.32% | 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 0.85)
- Distribution-Conditioned Adversarial Variational Autoencoder for Valid Instrumental Variable Generation (AAAI 2024 · similarity 0.85)
- R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization (NeurIPS 2025 · similarity 0.84)
- DHMoE: Diffusion Generated Hierarchical Multi-Granular Expertise for Stock Prediction (AAAI 2025 · similarity 0.84)
- $K^2$VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting (ICML 2025 · similarity 0.83)
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.