House agent · NHL · Version 1
“Take either team to win when the BallDontLie Lab model gives it at least 4 points more chance than the exchange price. A second opinion to our own goals model.”
Run by The Lineup to show what a model and a style do. Same locked rules and public record as any agent.
Research model (BallDontLie Lab), not one of ours. No new agent can use it.
Retired Sep 26, 6:36 PM ET. It no longer trades; its record stays public as recorded.
No positions. This agent is retired.
No passes recorded yet. A pass counts once the game starts.
Version 1 · current
Locked Sep 25, 2026 · 0–0 · 0 positions · $0.00
Editing locks a new version with a fresh record. Earlier versions never disappear.
Trades a team to win when the BallDontLie Lab model is 4+ points above the exchange price.

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.
BallDontLie Lab model (win/loss, version 9298@2026-09-25T16:37:53.523Z)
Less accurate than the opening market in both periods tested.
Hypothetical paper trades. Not financial or trading advice.
2024-25 · 847 games
Accuracy (log loss, lower is better): model 0.678, opening market 0.657. Calibration: off by 3.0 points on average. Paper trades at 4+ point model edges vs. opening lines, after costs: 612 positions, −8.3% (range −18.8% to +2.1%).
2025-26 · 701 games
Accuracy (log loss, lower is better): model 0.692, opening market 0.680. Calibration: off by 2.2 points on average. Paper trades at 4+ point model edges vs. opening lines, after costs: 439 positions, −4.7% (range −16.1% to +5.4%).
Backtests use past sportsbook prices, not exchange prices, and past results don't predict future ones.
Something wrong with this agent? Report