Using Wavelets to Classify Price Jumps and Co-Jump Contagion

Summary

The study introduces an unsupervised method for analyzing stock price jumps through representations built from wavelet coefficients. It aims to distinguish jump patterns associated with a system’s internal dynamics from those linked to external shocks. The analysis identifies volatility time-asymmetry as a prominent feature and finds that mean-reversion and trend help define additional classes of jumps.

The wavelet representation is also used to study co-jumps, when multiple stocks jump within the same minute. The authors argue that a significant share of these events reflects endogenous contagion. This offers a way to investigate how shocks propagate across stocks, though the document does not state the sample, validation procedure, or evidence for separating endogenous from exogenous events. The reported conclusions therefore describe the study’s findings rather than a demonstrated universal classification rule.

Key ideas

• Wavelet coefficients provide an unsupervised representation for classifying stock price jumps.
• Volatility time-asymmetry is a major feature in the jump analysis.
• Mean-reversion and trend are additional features that help distinguish jump classes.
• The authors argue that a significant fraction of same-minute co-jumps arises from endogenous contagion.

Tags

# Riding Wavelets: A Method to Discover New Classes of Price Jumps


# Riding Wavelets: A Method to Discover New Classes of Price Jumps









Cascades of events and extreme occurrences have garnered significant attention across diverse domains such as financial markets, seismology, and social physics. Such events can stem either from the internal dynamics inherent to the system (endogenous), or from external shocks (exogenous). The possibility of separating these two classes of events has critical implications for professionals in those fields. We introduce an unsupervised framework leveraging a representation of jump time-series based on wavelet coefficients and apply it to stock price jumps. In line with previous work, we recover the fact that the time-asymmetry of volatility is a major feature. Mean-reversion and trend are found to be two additional key features, allowing us to identify new classes of jumps. Furthermore, thanks to our wavelet-based representation, we investigate the reflexive properties of co-jumps, which occur when multiple stocks experience price jumps within the same minute. We argue that a significant fraction of co-jumps results from an endogenous contagion mechanism.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.