Cross-Stock Predictability via LLM-Augmented Semantic Networks

By Yikuan Huang, Zheqi Fan, Kaiqi Hu, Yifan Ye

Published 2026-04-26

Everscope rating

1895.4

Relevance to quantitative trading

9 / 10

Implementation complexity

6 / 10

Reproducibility

3 / 5

About this paper

Methodology: Retrieve-then-Reason Framework. Problem types: Classification, Pairs Trading, Portfolio Optimization, Natural Language Processing, Graph Learning, Risk Management.

arXiv:2604.19476 · Paper rankings

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