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

Graph-Spectral Forecast Ensemble

by Hema Srikar Ankem

Python
Compare
4.7563 Sharpe Ratio
47.56% Annual Return
-5.15% Max Drawdown

Performance Ranking

Better than 93.8% of the 96 other models

Performance Metrics

Primary Rankings

Sharpe Ratio Sharpe Ratio Risk-adjusted return: annualized return divided by annualized volatility. 4.7563
Rank Rank Position on the leaderboard, ordered by Sharpe ratio. #7

Returns

Annualized Return Annualized Return Average yearly return, after scaling the portfolio to the 10% volatility target. This model: Better than 94% of the 96 other models. 47.56%
Best 12M Return Best 12M Return The best compounded return over any 12 consecutive months of the test period. This model: Better than 63% of the 96 other models. 121.60% Jun 1994 – May 1995
Worst 12M Return Worst 12M Return The worst compounded return over any 12 consecutive months of the test period. This model: Better than 84% of the 96 other models. -0.20% Dec 2019 – Nov 2020

Risk

Max Drawdown Max Drawdown Largest peak-to-trough decline during the test period. This model: Better than 96% of the 96 other models. -5.15%
Downside Deviation Downside Deviation Standard deviation of negative monthly returns only. This model: Better than 58% of the 96 other models. 1.358%
Annualized Downside Dev Annualized Downside Deviation Downside deviation in annual terms. This model: Better than 58% of the 96 other models. 4.70%

Risk-Adjusted Performance

Sortino Ratio Sortino Ratio Return per unit of downside risk: like Sharpe, but only negative volatility counts. This model: Better than 85% of the 96 other models. 10.1111
Calmar Ratio Calmar Ratio Annualized return divided by the maximum drawdown. This model: Better than 97% of the 96 other models. 9.2393
Win Rate Win Rate Share of months with a positive return. This model: Better than 91% of the 96 other models. 91.4%

Distribution

Skewness Skewness Asymmetry of returns. Positive skew means more large gains than large losses. 0.028 (Near-symmetric)
Kurtosis Kurtosis Tail thickness. Higher values mean more extreme months, in either direction. 0.619 (Thin tails)

Volatility Targeting

Raw Volatility Raw Volatility Volatility of the portfolio before it was scaled to the 10% target. 5.32%
Scaling Factor Scaling Factor Multiplier applied to the portfolio to reach the 10% volatility target. 1.878
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. 0.05
Alpha (ann.) Alpha (ann.) Average yearly return not explained by market exposure (the monthly regression alpha × 12). This model: Better than 94% of the 96 other models. 46.76%
Information Ratio Information Ratio Annualized alpha per unit of residual risk: alpha ÷ std(residuals) × √12. This model: Better than 93% of the 96 other models. 4.7219
R² R² Share of the return variance explained by market movements. 2.2%
Alpha t-stat Alpha t-stat Statistical significance of the alpha estimate. A |t| above about 2 suggests it is not chance. 27.20

Benchmark Comparison

vs. Benchmarks

Graph-Spectral Forecast Ensemble
4.7563
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. 4.7563 2.5539 5.1475 +86.2% (better)
Sortino Ratio Sortino Ratio Return per unit of downside risk: like Sharpe, but only negative volatility counts. 10.1111 5.7974 18.7421 +74.4% (better)
Calmar Ratio Calmar Ratio Annualized return divided by the maximum drawdown. 9.2393 2.7589 12.0498 +234.9% (better)
Information Ratio Information Ratio Annualized alpha per unit of residual risk: alpha ÷ std(residuals) × √12. 4.7219 2.5235 5.1127 +87.1% (better)
Win Rate Win Rate Share of months with a positive return. 91.4% 77.5% 93.4% +17.9% (better)
Annualized Return Annualized Return Average yearly return, after scaling the portfolio to the 10% volatility target. 47.56% 25.54% 51.47% +86.2% (better)
Max Drawdown Max Drawdown Largest peak-to-trough decline during the test period. -5.15% -16.89% -3.51% +69.5% (better)

Model Details

Language Python
Competition Year 2024
First Submitted Oct 31, 2026
Scored Nov 2, 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 Graph-Spectral Forecast Ensemble
Have ideas for making this page more useful? Share your suggestions