Scaling analysis of multivariate intermittent time series

TL;DR

This paper investigates the scaling properties of asset prices and trading volumes in stock markets, revealing multi-scaling behavior and proposing a multi-factor analysis method for risk forecasting.

Contribution

It introduces a multi-factor scaling analysis method and demonstrates its application to equity index and trading volume data, extending understanding of market dynamics.

Findings

Trading volume data exhibit multi-scaling similar to asset prices.

Risk of large price movements is inversely related to low-variability period length.

A two-factor model effectively analyzes equity index and volume time series.

Abstract

The scaling properties of the time series of asset prices and trading volumes of stock markets are analysed. It is shown that similarly to the asset prices, the trading volume data obey multi-scaling length-distribution of low-variability periods. In the case of asset prices, such scaling behaviour can be used for risk forecasts: the probability of observing next day a large price movement is (super-universally) inversely proportional to the length of the ongoing low-variability period. Finally, a method is devised for a multi-factor scaling analysis. We apply the simplest, two-factor model to equity index and trading volume time series.