The real-time probability that the chasing team wins a T20 run chase, updated every ball. A gradient-boosted model trained on 475,000 ball-states from 4,406 real chases — AUC 0.88, beating the standard required-run-rate heuristic by 8.6 points. The in-play signal a betting bot or live dashboard needs, without building and calibrating its own win model.
Pass the match state; receive a complete, model-backed read.
A true, calibrated probability the chasing side wins from the exact match state — trained with log-loss, validated on Brier score. Beats the run-rate heuristic by 8.6 accuracy points.
HSH·Intelligencechasing_team_win_probdefending_team_win_probRuns needed, balls remaining, current and required run rates, and wickets in hand — the complete state returned alongside the probability.
runs_neededballs_remainingrequired_rrAppropriately uncertain in the powerplay and confident by the death overs — accuracy climbs from 73% to 88% as the chase resolves.
current_rrwickets_in_handTrained on 4,683 real T20 matches from Cricsheet — free, legal, ball-by-ball — then validated on unseen matches. No fragile live-feed dependency; the intelligence is in the model.
{
"chasing_team_win_prob": 0.489,
"defending_team_win_prob": 0.511,
"situation": {
"runs_needed": 60, "balls_remaining": 30,
"current_rr": 6.67, "required_rr": 12.0, "wickets_in_hand": 8
}
}dod.hshintelligence.com/mcp or the /x402/catalog.USDC on Base. Fixed deterministic price.# call the chase-winprob tool curl -H "X-Payment: <x402-usdc-base-payload>" \ "https://dod.hshintelligence.com/mcp" \ -d '{"tool":"hsh-cricket-chase-winprob","input":{...}}'