| Time | Rating | Record | % | Units |
|---|---|---|---|---|
| Since 2005 | 3 star or better | 72-65-5 | 52.6% | +0.5 |
| Time | Rating | Record | % | Units |
|---|---|---|---|---|
| Last 100 Picks | 2 star or better | 52-46-2 | 53.1% | +1.3 |
| Time | Rating | Record | % | Units |
|---|---|---|---|---|
| Since 2007 | 3 star or better | 25-19-2 | 56.8% | +3.7 |
| Last Week | All Picks | 9-6-0 | 60.0% | +2.2 |
| Since Week 5 | 3 star or better | 6-4-0 | 60.0% | +1.5 |
| This Season | 3 star or better | 6-4-0 | 60.0% | +1.5 |
| Time | Rating | Record | % | Units |
|---|---|---|---|---|
| Last 250 Picks | 2 star or better | 103-147-0 | 41.2% | +21.1 |
| Time | Rating | Record | % | Units |
|---|---|---|---|---|
| Since 2005 | All Picks | 784-429-0 | 64.6% | -- |
Our Similar Games model uses multivariate data algorithms to identify relevant historical game situations. In making predictions, the model examines how statistically similar teams have fared when they played in similar contextual scenarios.
This particular model emphasizes power ratings and the Vegas spread as predictive factors. It was designed for all around performance across all pick types and phases of the season, as opposed to being more specialized for a certain type of pick.
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.


