Testing COVID-19 Indicators in Bitcoin Return Forecasting

Summary

The study tests whether COVID-19 health indicators add predictive value when forecasting Bitcoin returns. It compares LightGBM regression models trained with and without pandemic-related features, including vaccination, hospitalization, and testing measures. A genetic algorithm optimizes the models across 31 independent runs, and the study compares R², RMSE, and MAE distributions using overlap analysis and Mann–Whitney U tests. Permutation feature importance is used to assess the contribution of individual inputs.

The reported results favor models that include COVID-19 data: R² rose by 40% and RMSE fell by 2%, with both changes described as highly statistically significant. Vaccination measures, especially the 75th percentile of fully vaccinated individuals, ranked prominently. The evidence concerns predictive performance in the study’s dataset and setup; it does not establish that these features cause Bitcoin returns or will improve live trading. The document gives no detailed information about the sample period, model validation design, or transaction costs, so the practical and out-of-sample value is difficult to assess.

Key ideas

• The study compares LightGBM Bitcoin return models with and without COVID-19 indicators.
• A genetic algorithm optimizes models over 31 independent runs.
• Mann–Whitney U tests and distribution overlaps are used to compare performance metrics.
• Permutation feature importance identifies vaccination measures as prominent predictors.
• The reported gains show predictive improvement in the study setup, not proof of live trading value.

Tags

# 2508.00078


# Evaluating COVID 19 Feature Contributions to Bitcoin Return Forecasting: Methodology Based on LightGBM and Genetic Optimization









This study proposes a novel methodological framework integrating a LightGBM regression model and genetic algorithm (GA) optimization to systematically evaluate the contribution of COVID-19-related indicators to Bitcoin return prediction. The primary objective was not merely to forecast Bitcoin returns but rather to determine whether including pandemic-related health data significantly enhances prediction accuracy. A comprehensive dataset comprising daily Bitcoin returns and COVID-19 metrics (vaccination rates, hospitalizations, testing statistics) was constructed. Predictive models, trained with and without COVID-19 features, were optimized using GA over 31 independent runs, allowing robust statistical assessment. Performance metrics (R2, RMSE, MAE) were statistically compared through distribution overlaps and Mann-Whitney U tests. Permutation Feature Importance (PFI) analysis quantified individual feature contributions. Results indicate that COVID-19 indicators significantly improved model performance, particularly in capturing extreme market fluctuations (R2 increased by 40%, RMSE decreased by 2%, both highly significant statistically). Among COVID-19 features, vaccination metrics, especially the 75th percentile of fully vaccinated individuals, emerged as dominant predictors. The proposed methodology extends existing financial analytics tools by incorporating public health signals, providing investors and policymakers with refined indicators to navigate market uncertainty during systemic crises.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.