New College Basketball Model

College Basketball Best Bets:

New Model leads to 56% Best Bet winners last season!

I have been very profitable on my College Basketball Best Bets over the years (+368.8 Stars the last 23 seasons), and especially in the last 4 years when I started releasing most plays in the morning when lines are softer (54.7% and +81 Stars the last 4 seasons).

The results were even better last season, which was the first season that the College Basketball plays were based on a new model that tested incredibly well (832-636-29 for 56.7%) over the previous 4 seasons. The model was tested on 4 seasons not used to derive the model to avoid back-fitting. The first season using that predictive matchup model produced very good results on Best Bets (55.7%) despite winning only 40% of the close games (bets decided by less than 3 points).

 

2020-21 Season: Best Bets were 165-131-3 and Opinions were 153-131-5

2021-22 Season: Best Bets were 350-304-14 and Opinions were 211-169-6

 

College Basketball model – 56.7% on 4 test seasons!

When the 2020 college basketball season abruptly ended we set out to program a college basketball model to improve upon the methods I’ve been using for years, which were less sophisticated in terms of priors and in-season blending with priors, while automating the player adjustment factors that I’ve been calculating by hand for years.

The results on 4 test seasons not used in the derivation of the model were even better than we expected, going 832-636-29 (56.7%) on side plays, while having a play on 11.7% of the games in the sample (see the full results below).

The key to having a good college basketball model is having good priors, which are the expectation of each team’s performance level entering the season. Our college basketball priors are derived from a blend of program, coach, and player ratings. The program and coach ratings are based on year-to-year correlations across a variety of metrics. The player ratings are derived from recruiting rankings and aging curves. We project every player’s contribution per 100 possessions and then predict playing time for each player to come up with all of the player value priors. The combination of all three ratings (program, coach, player) measure the changes of the offseason, which mainly come from transfers, new players (freshmen and JUCO), and coaching moves.

Once the priors were perfected the model was built using the same model building principles used in building the current NFL model, which has produced great results (58.5% over 6 seasons).

The college basketball model was initially built using only data from the 2003-04 season through the 2015-16 season and then was tested on the next 4 seasons, which were not included in the derivation of the test model to avoid back-fitting.

The results of the model on the 2016 to 2020 seasons were incredibly good based on significant differences between our model prediction and the line (i.e. 3 ½ points or more difference).

 

2016-17: 217-149-5 (59.3%)

2017-18: 170-139-11 (55.0%)

2018-19: 244-18-7 (57.0%)

2019-20: 201-164-6 (55.1%)

 

Total: 832-636-29 (56.7%)

 

The model went live for the 2020-21 season with good results in a difficult environment with added variance due to Covid.

2020-21 Season: Best Bets were 165-131-3 and Opinions were 153-131-5

2021-22 Season: Best Bets were 350-304-14 and Opinions were 211-169-6

 

The results of the test seasons exceeded expectations, especially considering that the model was tested on closing lines and we will be releasing most games in the morning when the lines are soft. The model test also did not include any adjustments for player personnel changes (injuries, lineup changes, etc), which is something that will be adjusted for and has been a big part of the success of the NFL model.

The model parameter weightings have been updated to include the last 4 seasons that were initially excluded, and improvements were made to the model this offseason with the addition of offensive and defensive play style parameters and shot type distribution – so the model is fine-tuned for the upcoming season. I’m really excited about the model and expect to have great results in college basketball going forward.

We’ll have plays starting opening night based on priors which are certainly better than the market. The early season model plays (i.e. the first 25 days) based solely on our priors were 250-185-4 on sides (57.5%) in the 4 test seasons and last season, using the new model, the early season plays based solely on the priors were 41-26-1 on sides and 21-13 on totals.

 

  • Dr. Bob College Basketball Season

    All Plays are 1459-1217-45 the last 3 seasons with new matchup model.

    Receive all of my NCAA Basketball Best Bets and Opinions through the 2024 NCAA Tournament Championship game.

    $275.00 Subscribe

Share this