Vector-Quantized Discrete Latent Factors Meet Financial Priors: Dynamic Cross-Sectional Stock Ranking Prediction for Portfolio Construction

By Namhyoung Kim, Jae Wook Song

Published 2026-05-13

Everscope rating

1666.9

Relevance to quantitative trading

9 / 10

Implementation complexity

7 / 10

Reproducibility

4 / 5

About this paper

Methodology: PRISM-VQ (PRior-Informed Stock Model with Vector Quantization). Problem types: Ranking, Portfolio Optimization, Time Series Forecasting, Clustering, Multi-task Learning, Dimensionality Reduction, Structured Prediction.

arXiv:2605.13407 · Code · Paper rankings

Open the interactive Everscope explorer for full analysis, charts, and paper battles.