A Multi-Layer Machine Learning and Econometric Pipeline for Forecasting Market Risk: Evidence from Cryptoasset Liquidity Spillovers

TL;DR

This paper develops a multi-layer machine learning and econometric pipeline to forecast market risk in cryptoassets by analyzing liquidity and volatility spillovers, demonstrating significant causal relationships and moderate predictive accuracy.

Contribution

It introduces an integrated multi-layer framework combining econometrics and machine learning for crypto market risk forecasting, with novel interpretability and robustness features.

Findings

Significant Granger-causal relationships across layers.

Moderate out-of-sample predictive accuracy.

Robustness of results across different analyses.

Abstract

We study whether liquidity and volatility proxies of a core set of cryptoassets generate spillovers that forecast market-wide risk. Our empirical framework integrates three statistical layers: (A) interactions between core liquidity and returns, (B) principal-component relations linking liquidity and returns, and (C) volatility-factor projections that capture cross-sectional volatility crowding. The analysis is complemented by vector autoregression impulse responses and forecast error variance decompositions (see Granger 1969; Sims 1980), heterogeneous autoregressive models with exogenous regressors (HAR-X, Corsi 2009), and a leakage-safe machine learning protocol using temporal splits, early stopping, validation-only thresholding, and SHAP-based interpretation. Using daily data from 2021 to 2025 (1462 observations across 74 assets), we document statistically significant Granger-causal relationships across layers and moderate out-of-sample predictive accuracy. We report the most informative figures, including the pipeline overview, Layer A heatmap, Layer C robustness analysis, vector autoregression variance decompositions, and the test-set precision-recall curve. Full data and figure outputs are provided in the artifact repository.