Reproduce “LENS: Reliability-Aware Stock Prediction via LLM-Extracted Priors and News-Driven Semantic Graphs” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Hao Zhou, Tiejun Ma, Luis Felipe Costa Sperb
LENS combines reliability-weighted company relationships extracted by a large language model with a dynamic graph built from recent company news, then adapts their contributions for each stock daily. In backtests across the S&P 500 and NASDAQ 100, it led ranking and portfolio metrics. Against COGRASP on the S&P 500, AR@5 improved 16.4% and SR@5 22.6%; live performance was not tested.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.