Over-by-over win-prob timeline — HSH Cricket Intelligence

How to buy

Two ways in — pick yours.

For people & teams

Buy credits with a card — no wallet, no crypto.
Get an API key emailed to you instantly.
Call this product with your key — credits debit per call.
Check your balance anytime via Check balance.

Buy credits with card →

For AI agents

Point your agent at the x402 endpoint, or describe the need in plain language.
Pay per call in USDC (Base or Solana) — no signup.
Receive the signal inline, settled on-chain.

View agent catalog →

What you get · 3 layers

The signal, in full.

Pass the match state; receive a complete, model-backed read.

Full win-prob curve

Win-probability at every over of the chase, returned as an ordered series ready to plot — the worm graph in data form.

curveoverchasing_win_prob

Score-tagged points

Each point carries the score and wickets at that over, so the curve annotates itself for a graphic or recap.

score

Model-consistent

Every point comes from the same validated AUC-0.88 chase model, so the curve matches the live win-probability product exactly.

Where it comes from

Sequenced from the chase model.

Trained 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.

The chase model, sequenced

Runs the validated win-probability model across the whole innings.

proprietary methodology

Plot-ready output

An ordered series, ready to render as a line chart with no post-processing.

per-call

Self-annotating

Each point carries its score/wickets for labelling.

structured

Consistent with live product

Matches what the live win-prob tool returns at each state.

out-of-sample

Sample output

What comes back.

{
  "target": 181,
  "curve": [
    { "over": 6, "score": "79/2", "chasing_win_prob": 0.83 },
    { "over": 9, "score": "118/5", "chasing_win_prob": 0.61 }
  ]
}

Who calls it

Use cases.

For autonomous agents

Match-report bot

Auto-generate the worm

Produce a win-probability graph for every match with no manual charting.

Media agent

Embed the curve

Drop a live-updating win-probability visual into an app or overlay.

Recap bot

Narrate the swings

Turn the curve's peaks and troughs into an automatic match narrative.

For people & teams

Broadcaster

On-air worm

Show the classic win-probability curve sourced from one API call.

Sports media

Illustrate reports

Add a credible win-probability graph to match reports.

Analyst

Study match shape

Examine exactly how and when a chase swung, over by over.

How to call it

Discover, pay, receive.

01 · Discover

Find the tool

Via MCP at dod.hshintelligence.com/mcp or the /x402/catalog.

02 · Pay

Pay per call

Send the x402 payment in USDC on Base. Fixed deterministic price.

03 · Receive

Get the signal

The signal returns inline — ready for your model, lineup, or strategy.

# call the timeline tool
curl -H "X-Payment: <x402-usdc-base-payload>" \
"https://dod.hshintelligence.com/mcp" \
-d '{"tool":"hsh-cricket-timeline","input":{...}}'

Questions

FAQ.

How is the curve generated?

By running the validated chase win-probability model across the sequence of over-end states you provide, producing a point per over.

Is it consistent with the live win-prob product?

Yes — same underlying model, so a point on the curve matches what the live product would return for that state.

What do I pass?

The target and an ordered list of over-end states (balls, wickets, runs).

Can I render it directly?

Yes — the output is an ordered, plot-ready series with scores attached for labels.

Over-by-over win-prob timeline.