Co-trading networks for modeling dynamic interdependency structures and estimating high-dimensional covariances in US equity markets

Paper: arXiv 2302.09382

Authors: Yutong Lu, Gesine Reinert, Mihai Cucuringu

Abstract

The time proximity of trades across stocks reveals interesting topological structures of the equity market in the United States. In this article, we investigate how such concurrent cross-stock trading behaviors, which we denote as co-trading, shape the market structures and affect stock price co-movements. By leveraging a co-trading-based pairwise similarity measure, we propose a novel method to construct dynamic networks of stocks. Our empirical studies employ high-frequency limit order book data from 2017-01-03 to 2019-12-09. By applying spectral clustering on co-trading networks, we uncover economically meaningful clusters of stocks. Beyond the static Global Industry Classification Standard (GICS) sectors, our data-driven clusters capture the time evolution of the dependency among stocks. Furthermore, we demonstrate statistically significant positive relations between low-latency co-trading and return covariance. With the aid of co-trading networks, we develop a robust estimator for high-dimensional covariance matrix, which yields superior economic value on portfolio allocation. The mean-variance portfolios based on our covariance estimates achieve both lower volatility and higher Sharpe ratios than standard benchmarks.

Complexity vs Empirical Score

• Math Complexity: 6.5/10
• Empirical Rigor: 6.0/10 (capped from 8.0: transaction costs not modelled; see penalty flags)
• Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper introduces an innovative network-based framework combining high-frequency co-trading data with spectral clustering to improve high-dimensional covariance matrix estimation. The empirical validation is strong, utilizing three years of high-frequency limit order book data to demonstrate tangible out-of-performance in mean-variance portfolio optimization.

Research Flowchart

  flowchart TD
    A[Research Goal: Model dynamic stock interdependency & estimate high-dimensional covariance] --> B[Data: High-frequency Limit Order Book <br> 2017-01-03 to 2019-12-09]
    B --> C[Construct Dynamic Co-trading Networks <br> via pairwise trade proximity measure]
    C --> D[Apply Spectral Clustering]
    C --> E[Develop Co-trading Network-based <br> Covariance Matrix Estimator]
    D --> F[Outcome 1: Identified dynamic, economically <br> meaningful clusters beyond static GICS sectors]
    E --> G[Outcome 2: Portfolios with lower volatility <br> and higher Sharpe ratios vs benchmarks]