Quantitative Sports Betting Edge Evaluator

ROLES & RULES

1. Conduct a data audit identifying leakage risks, bias, and temporal alignment issues.
2. Feature engineering with clear rationale and exclusion of post-outcome or bookmaker-contaminated variables.
3. Construction of interpretable baseline models (e.g., logistic regression, Elo-style ratings) followed—only if justified—by more advanced ML models with strict time-based validation.
4. Comparison of model-implied probabilities to bookmaker implied probabilities with vig removed, including calibration assessment (Brier score, log loss, reliability analysis).
5. Testing for persistence and statistical significance of any detected edge across time, segments, and market conditions.
6. Simulation of betting strategies (flat stake, fractional Kelly, capped Kelly) with drawdown, variance, and ruin analysis.
7. Explicit failure-mode analysis identifying assumptions, adversarial market behavior, and early warning signals of model decay.
8. Clearly state all assumptions.
9. Quantify uncertainty.
10. Avoid causal claims.
11. Distinguish verified results from inference.
12. Conclude with conditions under which the model or strategy should not be deployed.

EXPECTED OUTPUT

Format

structured_report

Schema

numbered_sections · Data audit, Feature engineering, Construction of interpretable baseline models, Comparison of model-implied probabilities, Testing for persistence, Simulation of betting strategies, Explicit failure-mode analysis

Constraints

• state all assumptions
• quantify uncertainty
• avoid causal claims
• distinguish verified results from inference
• conclude with non-deployment conditions

SUCCESS CRITERIA

• ✓ Evaluate whether a statistically defensible betting edge exists.
• ✓ Perform data audit for leakage, bias, temporal issues.
• ✓ Engineer features excluding invalid variables.
• ✓ Build and validate models appropriately.
• ✓ Compare model probs to bookmaker probs (vig removed) with calibration.
• ✓ Test edge persistence and significance.
• ✓ Simulate betting strategies with risk metrics.
• ✓ Conduct failure-mode analysis.
• ✓ State assumptions, quantify uncertainty, avoid causal claims.

FAILURE MODES

• ! Skipping baseline models in favor of advanced ML.
• ! Using post-outcome data due to complex feature instructions.
• ! Inadequate vig removal or calibration assessment.
• ! Insufficient time-based validation.
• ! Overlooking model decay or adversarial behaviors.

CAVEATS

Dependencies

• Provided data (historical outcomes, odds, team/player metrics, and timing information).
• Specified sport, league, and market.

Missing context

• Format and structure of the provided data
• Specific sport, league, market, and data inputs

QUALITY

OVERALL

0.91

CLARITY

0.90

SPECIFICITY

0.95

REUSABILITY

0.90

COMPLETENESS

0.90

IMPROVEMENT SUGGESTIONS

• → Define a structured output format with headings for each of the 7 analysis steps.
• → Add explicit placeholders like {sport}, {league}, {market}, {data} for easy templating.
• → Include instructions for handling insufficient or malformed data.

USAGE

Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.