DATA-DRIVEN SPORTS INSIGHTS

Model the Game. Find the Edge.

Independent predictive models for baseball, basketball, and football. Every forecast is locked before the game, graded afterward, and kept on the record.

View today’s predictions →Explore Premium

Data-driven models

Thousands of simulations power our probabilistic projections.

Verified performance

Every pick is graded in public. Nothing is hidden.

Market awareness

We compare our numbers to the market to find real edges.

Research first

Continuous testing and validation keep our models sharp.

MethodologyHow the NCAAB model works

A percentile-rank ensemble across a dozen measures of how a team actually plays, anchored on tempo-free efficiency, converted to a projected margin through a calibrated non-linear transformation.

What it reads

Tempo-free adjusted efficiency (points per 100 possessions, both ends)
Shooting, rebounding, turnover and free-throw rate differentials
Schedule quality, valued by the rank of the opponent
Recent form, and a cap on how far a team can move in a day
Venue effects measured per team from its own results, not one national average

What it produces

A composite strength score across all Division I
Projected spread and projected total
Win probability from the margin distribution
Tournament odds from bracket simulations in March

What we publish

Spread against the market, the primary product
Over/under
Rankings and bracket projections

Not claimed

The signal is in the architecture, not in the weights: audit testing found the weight surface essentially flat, so re-tuning the inputs buys almost nothing. The edge concentrates in games where the model most disagrees with the market.

See the NCAAB record →