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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Qiu, Yimeng, Fang, Feihuang
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917035882053632
author Qiu, Yimeng
Fang, Feihuang
author_facet Qiu, Yimeng
Fang, Feihuang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_20066
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Multi-Layer Machine Learning and Econometric Pipeline for Forecasting Market Risk: Evidence from Cryptoasset Liquidity Spillovers
Qiu, Yimeng
Fang, Feihuang
Machine Learning
Computational Engineering, Finance, and Science
Econometrics
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.
title A Multi-Layer Machine Learning and Econometric Pipeline for Forecasting Market Risk: Evidence from Cryptoasset Liquidity Spillovers
topic Machine Learning
Computational Engineering, Finance, and Science
Econometrics
url https://arxiv.org/abs/2510.20066