Optimal Execution with Quadratic Variation Inventories

TL;DR

This paper empirically confirms the presence of Brownian motion in trader inventories and wealth, and extends optimal execution models to incorporate stochastic inventory processes, comparing theoretical predictions with actual trading behavior.

Contribution

It introduces statistical tests for Brownian components in inventories and extends optimal execution models to include Itô processes, validated with empirical data.

Findings

Significant evidence of Brownian motion in inventories and wealth.

Extended optimal execution models to include stochastic inventories.

Empirical comparison shows alignment between model predictions and actual trader behavior.

Abstract

The first half of the paper is devoted to description and implementation of statistical tests arguing for the presence of a Brownian component in the inventories and wealth processes of individual traders. We use intra-day data from the Toronto Stock Exchange to provide empirical evidence of this claim. We work with regularly spaced time intervals, as well as with asynchronously observed data. The tests reveal with high significance the presence of a non-zero Brownian motion component. The second half of the paper is concerned with the analysis of trader behaviors throughout the day. We extend the theoretical analysis of an existing optimal execution model to accommodate the presence of It\^o inventory processes, and we compare empirically the optimal behavior of traders in such fitted models, to their actual behavior as inferred from the data.