Investigation of Flash Crash via Topological Data Analysis

TL;DR

This paper applies topological data analysis, specifically persistence landscapes and dynamic time series analysis, to study and predict the Flash Crash in the stock market, demonstrating its effectiveness in characterizing and forecasting extreme financial events.

Contribution

It introduces a novel application of topological data analysis to financial market crashes, enhancing event characterization and prediction capabilities.

Findings

Effective characterization of the Flash Crash event.

Successful prediction of extreme market events.

Validation of topological methods in financial analysis.

Abstract

Topological data analysis has been acknowledged as one of the most successful mathematical data analytic methodologies in various fields including medicine, genetics, and image analysis. In this paper, we explore the potential of this methodology in finance by applying persistence landscape and dynamic time series analysis to analyze an extreme event in the stock market, known as Flash Crash. We will provide results of our empirical investigation to confirm the effectiveness of our new method not only for the characterization of this extreme event but also for its prediction purposes.