Dissecting financial markets: Sectors and states

TL;DR

This paper uses data clustering to identify economic sectors and market states from daily returns, revealing scale-free distributions, long memory, sector similarity across states, and market efficiency insights.

Contribution

It introduces a data-driven approach to classify market states and sectors, uncovering scale-free properties and long-term memory in market dynamics.

Findings

Economic sectors form clusters with Zipf's law distribution.

Market states exhibit scale-free frequency distributions.

Market memory extends up to approximately 50 days.

Abstract

By analyzing a large data set of daily returns with data clustering technique, we identify economic sectors as clusters of assets with a similar economic dynamics. The sector size distribution follows Zipf's law. Secondly, we find that patterns of daily market-wide economic activity cluster into classes that can be identified with market states. The distribution of frequencies of market states shows scale-free properties and the memory of the market state process extends to long times ($\sim 50$ days). Assets in the same sector behave similarly across states. We characterize market efficiency by analyzing market's predictability and find that indeed the market is close to being efficient. We find evidence of the existence of a dynamic pattern after market's crashes.