House agent · NHL · Version 1
“Take the over or the under when our goals model gives that side at least 4 points more chance than the exchange price, at prices from 35 to 65 cents. Each total line is priced on its own.”
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: This model hasn't beaten market prices yet. It runs with the owner's approval while we test it live.
LAK @ COL · Sep 28, 3:50 PM ET
46.3¢ · Kalshi order book · fee $3.63 · $96.37 position · model 50.8¢ (+4.5 pts)
No verified close
Model: Lineup goals modelExperimental
Trades the over or under when the Lineup goals model is 4+ points above the exchange price, at prices from 35 to 65 cents.

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.
Lineup goals model (totals, version 3)
Less accurate than the opening market in both periods tested.
Hypothetical paper trades. Not financial or trading advice.
NYI @ TOR · Sep 28, 1:00 PM ET
43¢ · Kalshi order book · fee $3.85 · $96.15 position · model 48.5¢ (+5.5 pts)
No verified close
Model: Lineup goals modelExperimental
VAN @ EDM · Sep 27, 9:55 PM ET
52¢ · Polymarket order book · fee $2.44 · $97.56 position · model 56.8¢ (+4.8 pts)
No verified close
Model: Lineup goals modelExperimental
PIT @ PHI · Sep 27, 9:25 PM ET
58¢ · Kalshi order book · fee $2.86 · $97.13 position · model 64.8¢ (+6.8 pts)
No verified close
Model: Lineup goals modelExperimental
NYR @ BOS · Sep 27, 7:55 AM ET
55¢ · Kalshi order book · fee $3.07 · $96.93 position · model 59.3¢ (+4.3 pts)
No verified close
Model: Lineup goals modelExperimental
CHI @ VGK · Sep 27, 7:55 AM ET
55¢ · Kalshi order book · fee $3.07 · $96.93 position · model 59¢ (+4.0 pts)
No verified close
Model: Lineup goals modelExperimental
MTL @ TOR · Sep 26, 9:10 PM ET
51¢ · Kalshi order book · fee $3.32 · $96.68 position · model 56.5¢ (+5.5 pts)
No verified close
Model: Lineup goals modelExperimental
FLA @ CAR · Sep 26, 7:25 PM ET
49¢ · Kalshi order book · fee $3.45 · $96.55 position · model 53.1¢ (+4.1 pts)
No verified close
Model: Lineup goals modelExperimental
Kalshi: 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.
Polymarket: 18+ Only. Restrictions and eligibility requirements apply. Not available in all jurisdictions. Trading is risky. 100% loss can occur. See polymarket.com/tos for more information. The Polymarket US App serves as an independent software provider and affiliate of Polymarket US and Polymarket Clearing, the CFTC-regulated exchange and clearing organization.
No passes recorded yet. A pass counts once the game starts.
Version 1 · current
Locked Sep 25, 2026 · 0–0 · 8 positions · $0.00
Editing locks a new version with a fresh record. Earlier versions never disappear.
2020-21 to 2024-25, development seasons · 5,696 games
Accuracy (log loss, lower is better): model 0.693, opening market 0.692. Paper trades at 4+ point model edges vs. opening lines, after costs: 1,320 positions, −3.7% (range −9.1% to +2.0%).
2021-22 to 2024-25, development seasons · 5,010 games
Accuracy (log loss, lower is better): model 0.693, opening market 0.692.
Backtests use past sportsbook prices, not exchange prices, and past results don't predict future ones.
Something wrong with this agent? Report