Fantasy picks & captain — 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.

Ranked player picks

Every player in the squad scored and ranked by predicted fantasy value — a blend of expected points, top-6 probability, and ceiling. Separates safe floor picks from explosive ceiling picks.

pickspick_scorerank

Captain pick

The single highest-ceiling player, chosen by a 90th-percentile model — because captaincy doubles points and rewards upside, not average. Captain-hit rate 35.6%, more than double random.

captain_pickceiling_pts

Per-player probabilities

Each player carries a top-6 probability, an expected-points figure, and a ceiling — so a lineup builder can balance a safe core with high-variance differentials.

p_top6expected_pts

Where it comes from

Built on 129,000 player-innings.

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.

129,000 player-innings

Every batting and bowling innings from 4,683 T20 matches, with full fantasy scoring reconstructed ball-by-ball.

trained

Ensemble architecture

Three models — expected points, P(top-6) classifier, and a ceiling quantile model — blended, not a single naive mean.

proprietary methodology

Batting-position aware

Order in the innings is extracted from ball data and fed as a feature — the single biggest driver of fantasy output.

feature-engineered

Validated out-of-sample

Captain-hit and top-6 rates measured on matches held out of training, not fitted.

out-of-sample

Sample output

What comes back.

{
  "captain_pick": "V Kohli",
  "picks": [
    { "rank": 1, "player": "JJ Bumrah", "p_top6": 0.565, "expected_pts": 33.6, "ceiling_pts": 75.4 },
    { "rank": 2, "player": "V Kohli", "p_top6": 0.372, "expected_pts": 33.8, "ceiling_pts": 87.4 }
  ]
}

Who calls it

Use cases.

For autonomous agents

Fantasy bot

Build a lineup

Score all 22 players and auto-assemble a contest lineup — floor picks for the core, ceiling picks for differentials.

Contest optimizer

Pick the captain

The ceiling model names the captain that maximizes doubled points, not just the highest average.

Tipster agent

Auto-generate tips

Turn ranked picks into published fantasy tips every match, with no human projection work.

For people & teams

Fantasy app

Power a picks feature

Offer users AI captain and pick suggestions without building a projection model in-house.

Creator / tipster

Back your calls

Ground published tips in a validated model instead of gut feel.

Contest player

Sharpen your edge

See which players carry ceiling vs floor before locking a lineup.

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

Questions

FAQ.

How is the captain chosen?

By a 90th-percentile ceiling model, not average points — because a captain doubles points, so upside is what matters. Captain-hit rate is 35.6% (the pick lands in the real top-3 scorers over a third of the time), more than double random.

What scoring system does it use?

Dream11-style T20 fantasy scoring — runs, boundaries, strike-rate bonuses, wickets, economy, and milestone bonuses — reconstructed ball-by-ball over 129,000 player-innings.

Is single-match fantasy really predictable?

Only partly. Single-innings points are genuinely noisy, so this ships ranked probabilities (top-6, ceiling) rather than a false-precision points number. The honest edge is in ordering picks and captaincy, which it does measurably better than the naive baseline.

What do I pass in?

The list of players in the squad and whether the team is chasing. Venue is optional context.

Fantasy picks & captain.