Reproduce “Asymmetric Bidirectional Predictive Dynamics in Google Search and COVID-19 Time Series: A Multi-Horizon Forecast-Error Analysis” 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
Andrei Velichko, Imen Mahmoud
The authors test whether search histories add predictive information to COVID-19 indicators beyond each target’s own recent history, using matched LightGBM forecasts in both directions. Across eight pre-specified pairs, the “loss of smell” search improved case-forecast accuracy, while the reverse direction chiefly changed forecast-error distributions. These observational results describe model-relative patterns, not causal effects or universal search predictability.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.