---
title: Extreme Risk in Markets
url: https://www.ml-quant.com/papers/ssrn/5199540/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: SSRN 5199540
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5199540
featured: 2025-04-02
citations: unknown
topic: Derivatives & Volatility
---


# Extreme Risk in Markets

The research distinguishes between two types of extreme financial market risk - sudden price jumps and volatility bursts - using ultra-high-frequency data and a specific thresholding technique.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5199540
- Identifier: SSRN 5199540
- Released: 2025-03-31
- First featured: Quant Letter No. 91 (2025-04-02): https://www.ml-quant.com/issues/2025-04-02/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: Derivatives & Volatility

## Related

- [Prediction of linear fractional stable motions using codifference, with application to non-Gaussian rough volatility](https://www.ml-quant.com/papers/arxiv/2507.15437/): A new method for predicting future changes in linear fractional stable motion (LFSM) has been proposed, which performs better than the fractional Brownian motion in predicting high-frequency FX rates and volatility time series.
- [Asymptotic Expansions for High-Frequency Option Data](https://www.ml-quant.com/papers/ssrn/4440168/): A new method for analyzing financial data helps test for sudden volatility changes, with evidence from SP500 options indicating significant variation.
- [Testing for Stationarity of Volatility Curves](https://www.ml-quant.com/papers/ssrn/4516345/): The paper introduces a test for stability of hidden volatility curves over time using high-frequency financial data, revealing nonstationary variation in intraday volatility pattern over time in SP 500 futures data.
- [Intraday Volatility Forecasting](https://www.ml-quant.com/papers/ssrn/5216864/): The paper presents a new model for predicting high-frequency intraday conditional discrete return densities and volatility using deep learning, which surpasses empirical nonparametric forecasting rules and Space State Models.
- [The realized local volatility surface](https://www.ml-quant.com/papers/doi/10-21314-jois-2023-003/): The article introduces the realized local volatility surface, a new concept that uses high-frequency trading data to predict market volatility, using Tesla's data as a successful example.
- [Binary Tree Option Pricing Under Market Microstructure Effects: A Random Forest Approach](https://www.ml-quant.com/papers/arxiv/2507.16701/): The article introduces a machine learning extension of the binomial option pricing model, using Random Forest classifiers on high-frequency market data, proving its efficiency in predicting price movements and estimating fair value.