Tennis Desk — Model Anchor Calibration Prompt

Context: Our MLB Player Props council (2026-04-03) established the universal framework: per-possession/per-PA rates as foundation, Bayesian shrinkage toward career prior, Log-Odds opponent adjustment, Gaussian copula for correlated combo props, dual-anchor system (sportsbook + model) tracked via Brier scores, confidence tiers. This prompt asks for the SPORT-SPECIFIC parameters to plug into that framework.

Tennis Desk — Model Anchor Calibration

We are building model anchors for tennis betting markets on Kalshi: match winner, set spreads, total games, set betting.

Questions:

1. What player metrics best predict match outcomes? (Elo, surface-specific Elo, serve/return points won?)
2. How should surface (hard/clay/grass/indoor) adjustment work? Surface-specific ratings?
3. How many matches until player Elo/rating stabilizes per surface? k values?
4. How should fatigue and tournament scheduling affect projections? (5-set Grand Slam vs 3-set ATP 250)
5. How to model total games? What distribution? How does it vary by surface?
6. How should head-to-head records factor in? Minimum matches threshold?
7. How should ranking differential translate to win probability? Logistic function?
8. How should recent form (last 10 matches) weight vs career rating?
9. How to handle retirement risk and mid-match injury?
10. Surface transition effects (clay season to grass)?
11. EWMA alpha for serve/return statistics?
12. Give specific numbers, formulas, and implementation-ready recommendations.