As always, keep an eye on injuries and COVID Issues. All stats pulled are TEAM stats from the Last 8 games (L8) and don’t account for individual players. So be aware of new absences and players returning from an absence that could skew the L8 Team stats.
I will regularly post updates throughout the day and annotate with a “*”.
* Updated at 11:30am CST with updated lines.
Records
Here is how the models have been performing.
ATS Record
I made an error in entering yesterdays scores. RF was 1-2, kNN was 0-4, NN was 3-2. Overall records will be fixed and reflect corrected totals on tomorrows post.
O/U Record
I made an error in entering yesterdays scores. RF was 3-2, kNN was 2-2, NN was 5-0. Overall records will be fixed and reflect corrected totals on tomorrows post.
Top Performing Models
Based on Average Win % between ATS and O/U.
- Random Forest – 57%
- kNN – 56%
- Neural Net – 56%
- Ada Boost – 53%
- Basic Model – 52%
- Linear Regression – 51%
- SVM – 49%
- SGD – 47%
Summary of Projections
ATS Projections
O/U Projections
Player and Team News
Teams on a back to back: Pistons (Det to Bos), Celtics (Home), Blazers (Home), & Magic (SF to Sac).
NYK/Wizards: Bradley Beal is out tonight for the Wizards. His absence will not be reflected in the stats.
Wolves/Hornets: DeAngelo Russel is out for the second straight game, his absence wont be reflected in the stats. KAT returned for the Wolves last game, his impact on the court won’t be reflected in the stats.
Spurs/Hawks: LaMarcus Aldridge is out for the 5th straight game. His absence will be somewhat reflected in the stats.
Pistons/Celtics: Marcus Smart is out for his 6th straight game for the Celtics, his absence should be mostly accounted for in the stats.
Clippers/Bulls: Paul George and Lauri Markkanen are both out for the 4th straight game. Their absences will be somewhat reflected in the stats for their respective teams.
Thunder/Nuggets: Shae Gilgeous-Alexander is out for Thunder for the second straight and 4th of the last 8. His absence will be somewhat reflected in the stats.
Bucks/Jazz: Jrue Holiday and Mike Conley are both out for the 3rd straight game for their respective teams. Neither absence will be reflected in the stats.
Grizzlies/Lakers: Anthony Davis is considered a Game Time Decision. If he cant go he will miss his 3rd straight game and his absence wont be reflected in the stats.
Magic/Kings: Aaron Gordon is out for his 6 straight game, his absence wont be reflected in the stats. Keep an eye on Fournier, Anthony, and Mason for the Magic all considered a game time decision. Magic have struggled to score without Fournier on the floor. Anthony and Mason are the Magic’s two backup point guard’s, so if all 3 can’t go that’s a huge blow to the Magic.
*Kemba Walker is now out for tonight. His absence will not be reflected in the stats.
*Mason Plumlee is out for the Pistons, His absence will not be reflected in the stats.
Sharp Report
Early Money
Not a lot of betting data is available.
ATS – Some Sharp money has come in on the Spurs (+3.5), Bulls (+8.5), & Cavs (+7).
O/U – Some Sharp money has come in on the Spurs/Hawks Under (228).
Mid Day
ATS – Some Sharp money has come in on the Wolves (+4), Grizzlies (+7.5), Jazz (-2), & more on the Cavs (+5.5)
O/U – Some Sharp money is on the Grizzlies/Lakers Under (221.5), Knicks/Wizards Under (221), Pelicans/Mavs Under (233.5), Clippers/Bulls Under (228.5), & Bucks/Jazz Over (232.5).
Late Afternoon
No late Sharp report today.
Model Projections
1. Random Forest (R.F.)
[Nerd Talk] Best performance is capped at about 50 trees, anything more than that and the processing time/power required for a very minor improvement increases exponentially.
Record
Record: 53% ATS, 62% O/U.
ATS
O/U
Model Projections
How to read the projections: The model type is at the very top. Matchups are denoted by the alternating white/green pairings, away teams are on top, home teams on bottom. The model analyzes the matchup and projects the home and away teams score (Proj Score). The difference between the home teams score and the away teams score give us what the model says the line should be (Proj Line). The “Line” column is what the Vegas line is at the time I run the model. The “Line Diff” is the difference in the projected line and the Vegas line. A positive line diff means the projected line is in the away teams favor compared to the Vegas line, negative means the projected line is in the home teams favor. The “Cover Prob” uses a normal distribution and the teams variance to project each teams probability to cover the listed Vegas line. Same thing for totals, “Proj Total” is the sum of the projected scores, “Line Total” is the listed Vegas total for the game, the difference between the two, and the probability to go over or stay under denoted by “O” and “U”.
Betting Edge
If you don’t understand what you are looking at, I recommend reading my post about betting tips. The percentages show the betting Edge, which is the cover prob (from above) minus the implied probability (-110 odds implied prob is 52.4%). If a team has a 92.4% chance to win and a 52.4% implied probability (or -110 odds), the Edge is 40%. The Edge alone doesn’t mean you should blindly bet it. To quantify, >35% is great value, 20-35% is really good, 10-20% is decent, <10 is ok value, blanks are negative value. ML is moneyline.
2. k-Nearest Neighbor (kNN)
The lazy learner (That’s what my grad school prof called it). Nearest Neighbor has performed best with 30 Neighbors.
Record
Record: 54% ATS, 58% O/U.
ATS
O/U
Model Projections
How to read the projections: The model type is at the very top. Matchups are denoted by the alternating white/green pairings, away teams are on top, home teams on bottom. The model analyzes the matchup and projects the home and away teams score (Proj Score). The difference between the home teams score and the away teams score give us what the model says the line should be (Proj Line). The “Line” column is what the Vegas line is at the time I run the model. The “Line Diff” is the difference in the projected line and the Vegas line. A positive line diff means the projected line is in the away teams favor compared to the Vegas line, negative means the projected line is in the home teams favor. The “Cover Prob” uses a normal distribution and the teams variance to project each teams probability to cover the listed Vegas line. Same thing for totals, “Proj Total” is the sum of the projected scores, “Line Total” is the listed Vegas total for the game, the difference between the two, and the probability to go over or stay under denoted by “O” and “U”.
Betting Edge
If you don’t understand what you are looking at, I recommend reading my post about betting tips. The percentages show the betting Edge, which is the cover prob (from above) minus the implied probability (-110 odds implied prob is 52.4%). If a team has a 92.4% chance to win and a 52.4% implied probability (or -110 odds), the Edge is 40%. The Edge alone doesn’t mean you should blindly bet it. To quantify, >35% is great value, 20-35% is really good, 10-20% is decent, <10 is ok value, blanks are negative value. ML is moneyline.
3. Neural Network (NN)
[Nerd Talk] The activation function for this 100 layer NN is a linear function. The solver is an SGD.
Record
Record: 52% ATS, 60% O/U.
ATS
O/U
Model Projections
How to read the projections: The model type is at the very top. Matchups are denoted by the alternating white/green pairings, away teams are on top, home teams on bottom. The model analyzes the matchup and projects the home and away teams score (Proj Score). The difference between the home teams score and the away teams score give us what the model says the line should be (Proj Line). The “Line” column is what the Vegas line is at the time I run the model. The “Line Diff” is the difference in the projected line and the Vegas line. A positive line diff means the projected line is in the away teams favor compared to the Vegas line, negative means the projected line is in the home teams favor. The “Cover Prob” uses a normal distribution and the teams variance to project each teams probability to cover the listed Vegas line. Same thing for totals, “Proj Total” is the sum of the projected scores, “Line Total” is the listed Vegas total for the game, the difference between the two, and the probability to go over or stay under denoted by “O” and “U”.
Betting Edge
If you don’t understand what you are looking at, I recommend reading my post about betting tips. The percentages show the betting Edge, which is the cover prob (from above) minus the implied probability (-110 odds implied prob is 52.4%). If a team has a 92.4% chance to win and a 52.4% implied probability (or -110 odds), the Edge is 40%. The Edge alone doesn’t mean you should blindly bet it. To quantify, >35% is great value, 20-35% is really good, 10-20% is decent, <10 is ok value, blanks are negative value. ML is moneyline.
Are you shocked at how high the models probability scores are today? Haven not seen this many 90s and 100s in the two weeks coming to the site.
For the over/under projections its just a perfect storm where low variance teams are playing each other making the probabilities higher. The pistons/celtics line isnt out so those probabilities are thrown out. And personally i dont see the wizards only putting up 99 points.
Am i mistaken or was the R.F o/u model 3-2 yesterday, IND v DET was under and PHI v POR was over?
Good catch and thank you. I currently enter yesterdays scores by hand and made entered one of the scores wrong. I will fix the overall records and have them updated for tomorrow’s post. made a note of it in todays post.