The GT-Score: A Robust Objective Function for Reducing Overfitting in Data-Driven Trading Strategies

TL;DR

The paper tackles overfitting in data-driven trading by introducing the GT-Score, a composite objective that combines performance, statistical significance, consistency, and downside risk to guide optimization toward robust strategies. It formalizes GT-Score with the formula $GT_{\text{Score}} = \frac{\mu \cdot \ln(z) \cdot r^2}{\sigma_d}$, where $z = \frac{\mu - \mu_m}{\sigma / \sqrt{N}}$, and validates it on 50 S&P 500 stocks (2010–2024) using walk-forward validation and Monte Carlo analysis. The empirical results show GT-Score substantially reduces backtest overfitting, delivering a 98% higher generalization ratio in walk-forward validation while maintaining competitive out-of-sample performance; paired tests indicate statistically detectable differences with small effect sizes. The work emphasizes robustness to regime shifts and provides reproducible code and data for practitioners to adopt more reliable backtesting pipelines.

Abstract

Overfitting remains a critical challenge in data-driven financial modeling, where machine learning (ML) systems learn spurious patterns in historical prices and fail out of sample and in deployment. This paper introduces the GT-Score, a composite objective function that integrates performance, statistical significance, consistency, and downside risk to guide optimization toward more robust trading strategies. This approach directly addresses critical pitfalls in quantitative strategy development, specifically data snooping during optimization and the unreliability of statistical inference under non-normal return distributions. Using historical stock data for 50 S&P 500 companies spanning 2010-2024, we conduct an empirical evaluation that includes walk-forward validation with nine sequential time splits and a Monte Carlo study with 15 random seeds across three trading strategies. In walk-forward validation, GT-Score improves the generalization ratio (validation return divided by training return) by 98% relative to baseline objective functions. Paired statistical tests on Monte Carlo out-of-sample returns indicate statistically detectable differences between objective functions (p < 0.01 for comparisons with Sortino and Simple), with small effect sizes. These results suggest that embedding an anti-overfitting structure into the objective can improve the reliability of backtests in quantitative research. Reproducible code and processed result files are provided as supplementary materials.

Figures (3)

• Figure S1: Generalization ratio comparison across loss functions. GT-Score achieves a 98% higher generalization ratio (0.365) compared to baseline methods (avg 0.185), indicating substantially reduced overfitting.
• Figure S2: Generalization ratio by walk-forward split. Values closer to 1.0 indicate better generalization. GT-Score consistently maintains a higher ratio across most time periods.
• Figure S3: Monte Carlo transaction-cost sensitivity. Mean out-of-sample test return after subtracting additional per-side costs of 0--10 bps per trade side (entry and exit), proportional to the number of test-window trades. Note: In the figure annotation, "*" denotes multiplication.