Generating realistic metaorders from public data

ArXiv ID: 2503.18199 “View on arXiv”

Authors: Unknown

Abstract

This paper introduces a novel algorithm for generating realistic metaorders from public trade data, addressing a longstanding challenge in price impact research that has traditionally relied on proprietary datasets. Our method effectively recovers all established stylized facts of metaorders impact, such as the Square Root Law, the concave profile during metaorder execution, and the post-execution decay. This algorithm not only overcomes the dependence on proprietary data, a major barrier to research reproducibility, but also enables the creation of larger and more robust datasets that may increase the quality of empirical studies. Our findings strongly suggest that average realized short-term price impact is not due to information revelation (as in the Kyle framework) but has a mechanical origin which could explain the universality of the Square Root Law.

Keywords: Price impact, Square Root Law, Metaorders, Algorithmic trading, Kyle model, Equity

Complexity vs Empirical Score

• Math Complexity: 6.5/10
• Empirical Rigor: 7.2/10
• Quadrant: Holy Grail
• Why: The paper involves algorithmic complexity and statistical modeling, requiring moderate mathematical sophistication, while being heavily data-driven with specific backtesting methodology and validation against established stylized facts.

  flowchart TD
    A["Research Goal: Develop algorithm<br>to generate realistic metaorders<br>from public trade data"] --> B["Methodology: Constrained Optimization<br>to recover metaorders"]
    B --> C["Inputs: Public trade data<br>without labels"]
    C --> D["Computation: Constrained optimization<br>to find non-overlapping metaorders"]
    D --> E{"Verification against<br>stylized facts?"}
    E -- Yes --> F["Key Findings: Model replicates<br>Square Root Law & impact profiles"]
    E -- No --> B
    F --> G["Conclusion: Impact is mechanical<br>not informational<br>(refuting Kyle model)"]