Market-Informed Networks for Modeling and Forecast Evaluation of Financial Extremes
Abstract
Modeling the joint distribution of extreme values in high-dimensional financial time series is challenging because extremes are sparse and locally extreme observations are not necessarily extreme relative to their full marginal distribution. To address this, we introduce a time-dependent network Hüsler-Reiss model in which market-informed adjacency matrices determine how strongly observations contribute to the estimation. We propose binary and weighted specifications, including the Joint Extremes Adjacency Matrix (JEAM) which combines information about individual extremeness with historical patterns of joint extreme movements. In the forecasting evaluation part, covering one-minute stock returns from three sectors of the S&P 100, JEAM achieves the best out-of-sample log scores for both tail directions; improving scores by 12.5-13.6% in the lower tail and 11.4-14.9% in the upper tail. The results show that incorporating market-informed network structures in the estimation, improves forecast evaluation of extremes across time series.
Related
- Mathematical Characterization of Dynamic Risk Spillovers in Carbon-Energy Financial Networks with Multi-Dimensional Uncertainty: A TVP-VAR-DY Connectedness Approach via Generalized Forecast-Error Variance Decomposition
- Flowz: When Does Learning Forecast Errors Add Value? Conditional Flow Matching for Financial Price Forecasts
- Aggregate Calibration Can Mask Stress-State Undercoverage: Bounded-Memory Forecast Intervals under Recurrent Financial Stress
- Financial Contagion Networks as Annealing-Ready Ising Systems Cascades, Bailout Optimization, and Susceptibility
- Lazy training of quantum physics informed neural networks
BibTeX
@misc{jungbluth2026marketinformed,
title = {{Market-Informed Networks for Modeling and Forecast Evaluation of Financial Extremes}},
author = {Ayla Jungbluth and Johannes Lederer and Simon Trimborn},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.11575},
eprint = {2609.11575},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.11575},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Market-Informed Networks for Modeling and Forecast Evaluation of Financial Extremes
AU - Ayla Jungbluth
AU - Johannes Lederer
AU - Simon Trimborn
PY - 2026
DA - 2026/09/10
PB - arXiv
DO - 10.48550/arxiv.2609.11575
UR - https://arxiv.org/abs/2609.11575
AB - Modeling the joint distribution of extreme values in high-dimensional financial time series is challenging because extremes are sparse and locally extreme observations are not necessarily extreme relative to their full marginal distribution. To address this, we introduce a time-dependent network Hüsler-Reiss model in which market-informed adjacency matrices determine how strongly observations contribute to the estimation. We propose binary and weighted specifications, including the Joint Extremes Adjacency Matrix (JEAM) which combines information about individual extremeness with historical patterns of joint extreme movements. In the forecasting evaluation part, covering one-minute stock returns from three sectors of the S&P 100, JEAM achieves the best out-of-sample log scores for both tail directions; improving scores by 12.5-13.6% in the lower tail and 11.4-14.9% in the upper tail. The results show that incorporating market-informed network structures in the estimation, improves forecast evaluation of extremes across time series.
ER -