Multivariate Forecasting of Bitcoin Volatility with Gradient Boosting: Deterministic, Probabilistic, and Feature Importance Perspectives

TL;DR

This paper applies Light Gradient Boosting Machine to predict Bitcoin volatility using a wide range of predictors, comparing deterministic and probabilistic methods, and analyzing feature importance to understand driving factors.

Contribution

It introduces a comprehensive LGBM-based framework for Bitcoin volatility forecasting, incorporating both deterministic and probabilistic approaches with feature importance analysis.

Findings

LGBM models outperform traditional baselines in volatility prediction.

Probabilistic forecasts effectively capture uncertainty in Bitcoin volatility.

Key drivers include trading volume, lagged volatility, investor attention, and market cap.

Abstract

This study investigates the application of the Light Gradient Boosting Machine (LGBM) model for both deterministic and probabilistic forecasting of Bitcoin realized volatility. Utilizing a comprehensive set of 69 predictors -- encompassing market, behavioral, and macroeconomic indicators -- we evaluate the performance of LGBM-based models and compare them with both econometric and machine learning baselines. For probabilistic forecasting, we explore two quantile-based approaches: direct quantile regression using the pinball loss function, and a residual simulation method that transforms point forecasts into predictive distributions. To identify the main drivers of volatility, we employ gain-based and permutation feature importance techniques, consistently highlighting the significance of trading volume, lagged volatility measures, investor attention, and market capitalization. The results demonstrate that LGBM models effectively capture the nonlinear and high-variance characteristics of cryptocurrency markets while providing interpretable insights into the underlying volatility dynamics.