Reproduce “Online-Adaptive Fuzzy Cognitive Maps for Neuro-symbolic Financial Forecasting” 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

Brandon Rodriguez, Abel Deulofeu, Olaoluwa Adigun

The authors present an online-adaptive fuzzy cognitive map and LSTM hybrid for forecasting NASDAQ direction. The map updates factor weights from prediction error, and its directional signal steers the LSTM output. On a 250-day 2025 test, the ensemble reached 78.8% state-directional accuracy and 52.0% return-sign accuracy, versus 78.4% and 44.4% for the LSTM. The comparison does not isolate online adaptation.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.