Global Factor Data
Global Factor Data
Global Factor Data
Global Factor Data

XGB+MLP + two risk models (beta neutral)

by Abhinav Keshri

Python
Compare
4.7680 Sharpe Ratio
47.68% Annual Return
-5.01% Max Drawdown

Performance Ranking

Better than 94.8% of the 96 other models

Performance Metrics

Primary Rankings

Sharpe Ratio Sharpe Ratio Risk-adjusted return: annualized return divided by annualized volatility. 4.7680
Rank Rank Position on the leaderboard, ordered by Sharpe ratio. #6

Returns

Annualized Return Annualized Return Average yearly return, after scaling the portfolio to the 10% volatility target. This model: Better than 95% of the 96 other models. 47.68%
Best 12M Return Best 12M Return The best compounded return over any 12 consecutive months of the test period. This model: Better than 81% of the 96 other models. 143.26% Oct 1999 – Sep 2000
Worst 12M Return Worst 12M Return The worst compounded return over any 12 consecutive months of the test period. This model: Better than 98% of the 96 other models. 8.04% Aug 2022 – Jul 2023

Risk

Max Drawdown Max Drawdown Largest peak-to-trough decline during the test period. This model: Better than 97% of the 96 other models. -5.01%
Downside Deviation Downside Deviation Standard deviation of negative monthly returns only. This model: Better than 95% of the 96 other models. 0.927%
Annualized Downside Dev Annualized Downside Deviation Downside deviation in annual terms. This model: Better than 95% of the 96 other models. 3.21%

Risk-Adjusted Performance

Sortino Ratio Sortino Ratio Return per unit of downside risk: like Sharpe, but only negative volatility counts. This model: Better than 96% of the 96 other models. 14.8463
Calmar Ratio Calmar Ratio Annualized return divided by the maximum drawdown. This model: Better than 98% of the 96 other models. 9.5200
Win Rate Win Rate Share of months with a positive return. This model: Better than 89% of the 96 other models. 91.2%

Distribution

Skewness Skewness Asymmetry of returns. Positive skew means more large gains than large losses. 0.198 (Near-symmetric)
Kurtosis Kurtosis Tail thickness. Higher values mean more extreme months, in either direction. -0.034 (Thin tails)

Volatility Targeting

Raw Volatility Raw Volatility Volatility of the portfolio before it was scaled to the 10% target. 2.32%
Scaling Factor Scaling Factor Multiplier applied to the portfolio to reach the 10% volatility target. 4.317
Observations Observations Number of monthly returns used for the evaluation. 408 months

Market Exposure (CAPM)

Beta Beta Sensitivity to market movements. 1.0 moves one-for-one with the market. 0.02
Alpha (ann.) Alpha (ann.) Average yearly return not explained by market exposure (the monthly regression alpha × 12). This model: Better than 95% of the 96 other models. 46.89%
Information Ratio Information Ratio Annualized alpha per unit of residual risk: alpha ÷ std(residuals) × √12. This model: Better than 95% of the 96 other models. 4.7337
R² R² Share of the return variance explained by market movements. 2.1%
Alpha t-stat Alpha t-stat Statistical significance of the alpha estimate. A |t| above about 2 suggests it is not chance. 27.27

Benchmark Comparison

vs. Benchmarks

XGB+MLP + two risk models (beta neutral)
4.7680
Benchmark: Markowitz-ML
2.5212
Benchmark: Instrumented PCA factor portfolio
1.9481
Benchmark: Kozak-Nagel-Santosh rank-weighted factors portfolio
1.4195
Benchmark: Kozak-Nagel-Santosh L2
1.1832
Benchmark: Minimum Variance
0.9470
Benchmark: Factor-ML
0.8901
Benchmark: Equal-weight portfolio
0.4912

Performance Radar

Each axis shows the model's percentile rank within the leaderboard (outer edge = best). Customize the metrics using the dropdowns below.

vs. Leaderboard

Metric This Model Average Top Model vs. Avg
Sharpe Ratio Sharpe Ratio Risk-adjusted return: annualized return divided by annualized volatility. 4.7680 2.5539 5.1475 +86.7% (better)
Sortino Ratio Sortino Ratio Return per unit of downside risk: like Sharpe, but only negative volatility counts. 14.8463 5.7974 18.7421 +156.1% (better)
Calmar Ratio Calmar Ratio Annualized return divided by the maximum drawdown. 9.5200 2.7589 12.0498 +245.1% (better)
Information Ratio Information Ratio Annualized alpha per unit of residual risk: alpha ÷ std(residuals) × √12. 4.7337 2.5235 5.1127 +87.6% (better)
Win Rate Win Rate Share of months with a positive return. 91.2% 77.5% 93.4% +17.6% (better)
Annualized Return Annualized Return Average yearly return, after scaling the portfolio to the 10% volatility target. 47.68% 25.54% 51.47% +86.7% (better)
Max Drawdown Max Drawdown Largest peak-to-trough decline during the test period. -5.01% -16.89% -3.51% +70.3% (better)

Model Details

Language Python
Competition Year 2024
First Submitted Sep 17, 2026
Resubmitted Nov 8, 2026
Scored Nov 10, 2026

GitHub Badge

Add this model to a GitHub profile or repository README. The badge shows the model's Sharpe ratio, links to this page, and updates with the leaderboard.

JKP CTF leaderboard badge for XGB+MLP + two risk models (beta neutral)
Have ideas for making this page more useful? Share your suggestions