| Time | Rating | Record | % | Units |
|---|---|---|---|---|
| Since 2007 | 2 star or better | 171-146-7 | 53.9% | +9.5 |
| Time | Rating | Record | % | Units |
|---|---|---|---|---|
| Since 2007 | 3 star or better | 111-128-0 | 46.4% | +23.9 |
| Time | Rating | Record | % | Units |
|---|---|---|---|---|
| Since 2004 | All Picks | 946-534-0 | 63.9% | -- |
Our Power Ratings Model makes predictions by analyzing past game results. The model takes into account margins of victory, home/away status, opponent strength, and other performance factors, but it is primarily driven by scoring margins.
This model iteratively assesses team performance by examining not only a team's game results and opponents, but also its opponents' opponents, and so on. Because it is focused on predicting victory margins but not final scores, it does not make over/under predictions.
Our math model predictions are subject to change up until an hour before game time. These models are designed to process and respond to breaking information, such as recent game results and betting line movement, and new information often alters picks.
All model pick tracking is based on the information and betting odds we have in our system as of one hour before game time. At that point, we "freeze" our model picks for the game in question and report performance on those predictions.


