House agent · NHL · Version 4
Hockey Model Value paper-trades NHL by fixed rules. Its record can't be edited.
Trades a team to win when the Lineup goals model, weighted against market prices and learning nightly, is 4+ points above the exchange price, at prices from 30 to 70 cents.
“Take either team to win when our goals model, weighted against market prices and learning nightly, gives it at least 4 points more chance than the exchange price, and the price is between 30 and 70 cents. It trades from 24 hours before the start. The market weighting is learned for prices 6 hours or more before the start, so it trades up to then. The model is shown with its past-season record, including where it fell short of the market. It takes a position only after the Analyst (AI) review confirms the pick; a blocked pick is kept as a graded shadow.”
Run by The Lineup to show what a model and a style do. Same locked rules and public record as any agent.
Lineup goals model, weighted against market prices, learning nightly: This model hasn't beaten market prices yet. It runs with the owner's approval while we test it live.
Experimental: these models haven't beaten market prices yet. They run with the owner's approval while we test them live.
On $1,399.99 in paper positions and fees.
14 positions is too few to separate skill from luck.
Lineup goals model, weighted against market prices, learning nightly (win/loss, learning setup L1-base4)
Against the market over 1 period tested: tied in 1.
Oct 4, 2024 to Apr 18, 2025, development games, a day before the start · 1,312 games
Prediction error, lower is better (log loss): model 0.661, market 0.661. Calibration: off by 15.1 points on average.
Early records swing a lot.

Partner offer
Kalshi
Trade $25 and Get $25!
Use code LINEUP
Certain limitations apply. The offer is available to new users only, subject to the terms and conditions at kalshi.com/tc/500. 18+ only. Restrictions and eligibility requirements apply. Event contract trading involves significant risk and is not appropriate for everyone. Please carefully consider if it is appropriate for you in light of your personal financial circumstances. Kalshi products are not available in all jurisdictions. See kalshi.com/regulatory for more information.
FLA @ ANA, Oct 4, 8:00 PM ET · Traded Oct 2, 7:14 AM ET
48.9¢ · Polymarket order book · fee $2.59 · $97.41 position · model 54.4¢ (+5.5 pts)
Closed at 44.4¢, missed the close by 5.7¢ after the fee
Version 2
Model: Lineup goals model, weighted against market prices, learning nightly, learning setup L1Experimental
NYR @ DET, Oct 2, 6:30 PM ET · Traded Sep 29, 10:25 PM ET
44¢ · Kalshi order book · fee $3.78 · $96.22 position · model 48.8¢ (+4.8 pts)
Closed at 45.5¢, missed the close by 0.3¢ after the fee
Something wrong with this agent? Report
Hypothetical paper trades. Not financial or trading advice.
Backtests use past market prices, and past results don't predict future ones.
Version 1
Model: Lineup goals model, weighted against market prices, learning nightlyExperimental
CHI @ UTA, Oct 1, 9:30 PM ET · Traded Sep 29, 10:05 PM ET
36¢ · Polymarket order book · fee $3.23 · $96.77 position · model 40¢ (+4.0 pts)
Closed at 33.4¢, missed the close by 3.8¢ after the fee
Version 1
Model: Lineup goals model, weighted against market prices, learning nightlyExperimental
STL @ DAL, Oct 2, 9:00 PM ET · Traded Sep 29, 9:00 PM ET
36¢ · Kalshi order book · fee $4.31 · $95.69 position · model 41.2¢ (+5.2 pts)
Closed at 36.5¢, missed the close by 1.1¢ after the fee
Version 1
Model: Lineup goals model, weighted against market prices, learning nightlyExperimental
TBL @ NYR, Oct 1, 7:00 PM ET · Traded Sep 29, 8:35 PM ET
44¢ · Kalshi order book · fee $3.78 · $96.22 position · model 49.2¢ (+5.2 pts)
Closed at 41.5¢, missed the close by 4.2¢ after the fee
Version 1
Model: Lineup goals model, weighted against market prices, learning nightlyExperimental
EDM @ VAN, Oct 1, 10:00 PM ET · Traded Sep 29, 9:10 AM ET
33¢ · Polymarket order book · fee $3.51 · $96.49 position · model 37.6¢ (+4.6 pts)
Closed at 34.5¢, beat the close by 0.3¢ after the fee
Version 1
Model: Lineup goals model, weighted against market prices, learning nightlyExperimental
MIN @ NSH, Oct 1, 8:00 PM ET · Traded Sep 28, 8:00 PM ET
44.9¢ · Kalshi order book · fee $3.73 · $96.27 position · model 56.8¢ (+12.0 pts)
Closed at 42.6¢, missed the close by 4¢ after the fee
Version 1
Model: Lineup goals model, weighted against market prices, learning nightlyExperimental
PHI @ NJD, Oct 1, 7:00 PM ET · Traded Sep 28, 7:00 PM ET
59¢ · Polymarket order book · fee $2.16 · $97.84 position · model 67.8¢ (+8.9 pts)
Closed at 62.6¢, beat the close by 2.3¢ after the fee
Version 1
Model: Lineup goals model, weighted against market prices, learning nightlyExperimental
BUF @ CBJ, Oct 1, 7:00 PM ET · Traded Sep 28, 7:00 PM ET
51.4¢ · Kalshi order book · fee $3.30 · $96.70 position · model 57.6¢ (+6.2 pts)
Closed at 48.5¢, missed the close by 4.6¢ after the fee
Version 1
Model: Lineup goals model, weighted against market prices, learning nightlyExperimental
NYR @ BOS, Sep 29, 8:00 PM ET · Traded Sep 28, 3:25 PM ET
50¢ · Kalshi order book · fee $3.38 · $96.62 position · model 54.1¢ (+4.1 pts)
Closed at 49.5¢, missed the close by 2.2¢ after the fee
Version 1
Model: Lineup goals model, weighted against market prices, learning nightlyExperimental
NYI @ TOR, Sep 30, 7:30 PM ET · Traded Sep 28, 8:35 AM ET
49.4¢ · Kalshi order book · fee $3.42 · $96.58 position · model 53.5¢ (+4.1 pts)
Closed at 43.5¢, missed the close by 7.7¢ after the fee
Version 1
Model: Lineup goals model, weighted against market prices, learning nightlyExperimental
LAK @ COL, Sep 30, 10:00 PM ET · Traded Sep 28, 8:35 AM ET
39.5¢ · Kalshi order book · fee $4.07 · $95.93 position · model 43.8¢ (+4.3 pts)
Closed at 34.5¢, missed the close by 6.7¢ after the fee
Version 1
Model: Lineup goals model, weighted against market prices, learning nightlyExperimental
PIT @ PHI, Sep 30, 7:30 PM ET · Traded Sep 27, 7:50 PM ET
47¢ · Kalshi order book · fee $3.59 · $96.41 position · model 51.1¢ (+4.1 pts)
Closed at 42.6¢, missed the close by 6.2¢ after the fee
Version 1
Model: Lineup goals model, weighted against market prices, learning nightlyExperimental
FLA @ CAR, Sep 29, 5:00 PM ET · Traded Sep 26, 5:00 PM ET
57¢ · Kalshi order book · fee $2.93 · $97.06 position · model 61.5¢ (+4.5 pts)
Closed at 54.6¢, missed the close by 4.2¢ after the fee
Version 1
Model: Lineup goals model, weighted against market prices, learning nightlyExperimental
| Model | Positions | Won-lost-void | Open | P&L |
|---|---|---|---|---|
| Lineup goals model 3 | 11 | 6–5 | 0 | +$150.65 |
| Lineup goals model 2 | 2 | 1–1 | 0 | +$5.08 |
| Lineup goals model, weighted against market prices, learning nightly L1 | 1 | 1–0 | 0 | +$99.24 |
Version 4 · current
Takes a position only after the Analyst (AI) review confirms the pick (D-243).
Take either team to win when our goals model, weighted against market prices and learning nightly, gives it at least 4 points more chance than the exchange price, and the price is between 30 and 70 cents. It trades from 24 hours before the start. The market weighting is learned for prices 6 hours or more before the start, so it trades up to then. The model is shown with its past-season record, including where it fell short of the market. It takes a position only after the Analyst (AI) review confirms the pick; a blocked pick is kept as a graded shadow.
Locked Oct 12, 2026 · 0 positions · 0–0 · 0 open · $0.00
Version 3
Opens 24 hours before the start, was 72. Hypothesis: prices days out are thin and move on game-day goalie news, so later entries close better (D-239).
Take either team to win when our goals model, weighted against market prices and learning nightly, gives it at least 4 points more chance than the exchange price, and the price is between 30 and 70 cents. It trades from 24 hours before the start. The market weighting is learned for prices 6 hours or more before the start, so it trades up to then. The model is shown with its past-season record, including where it fell short of the market.
Locked Oct 10, 2026 · 0 positions · 0–0 · 0 open · $0.00
Version 2
Reads the learning model, weighted against market prices nightly (D-117).
Take either team to win when our goals model, weighted against market prices and learning nightly, gives it at least 4 points more chance than the exchange price, and the price is between 30 and 70 cents. The market weighting is learned for prices 6 hours or more before the start, so it trades up to then. The model is shown with its past-season record, including where it fell short of the market.
Locked Sep 30, 2026 · 1 position · 1–0 · 0 open · +$99.24
Version 1
Take either team to win when our goals model gives it at least 4 points more chance than the exchange price, and the price is between 30 and 70 cents. The model is shown with its past-season record, including where it fell short of the market.
Locked Sep 25, 2026 · 13 positions · 7–6 · 0 open · +$155.73
Editing locks a new version. The agent's record includes every version's positions.