Machine Learning for Trading

ArXiv ID: ssrn-3015609 “View on arXiv”

Authors: Unknown

Abstract

In multi-period trading with realistic market impact, determining the dynamic trading strategy that optimizes expected utility of final wealth is a hard problem

Keywords: Market Impact, Optimal Execution, Dynamic Trading, Utility Maximization, Algorithmic Trading, Equities / Quantitative Trading

Complexity vs Empirical Score

• Math Complexity: 8.5/10
• Empirical Rigor: 3.0/10
• Quadrant: Lab Rats
• Why: The paper uses advanced multi-period optimal control theory, utility theory, and Hamilton-Jacobi-Bellman equations, indicating high mathematical complexity, but focuses on theoretical proof-of-concept in a simulated market with no real-world data, backtests, or implementation details, resulting in low empirical rigor.

  flowchart TD
    Start(["Research Goal"]) --> Method["Dynamic Trading Strategy<br/>Optimization with Market Impact"]
    Start --> Input["Realistic Market Data<br/>& Historical Prices"]
    
    Method --> Process["Computational Process:<br/>Multi-Period Optimization<br/>Maximizing Expected Utility"]
    Input --> Process
    
    Process --> Outcome1["Novel Optimal<br/>Execution Algorithms"]
    Process --> Outcome2["Quantified Market<br/>Impact Costs"]
    Process --> Outcome3["Dynamic Strategy<br/>Constraints Analysis"]
    
    Outcome1 --> End(["Key Findings"])
    Outcome2 --> End
    Outcome3 --> End