Home Drew Rogers

Elo Arbitrage Engine (work in progress)

This project aims to evolve my Elo-based ratings system into a systematic arbitrage engine for institutional capital markets. By treating financial assets as competitive agents within a sector-specific "league," the engine utilizes Bayesian inference to estimate latent intrinsic value. I use Optuna to optimize hyperparameters to maximize risk-adjusted returns, turning my previously developed predictive framework into a scalable relative-value strategy.

Architecture: Latent Strength Estimization (based on performance deltas), Bayesian Updating, Sector Leagues

Optimization: Optuna Hyperparameter Search, Optimizing for the Information Ratio and Maximum Drawdown, Pruning Logic

Execution: Relative-Value Spreads, Convergence Trading, Market Neutrality

This project is currently under development. More details will be available soon.