NBA Line Projections – 23 Feb 21

As always, keep an eye on injuries, back to backs, COVID Issues, and players returning from injury. 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 “*”.

I made some minor edits to the preprocessing of the training data and the training data the models use last Wednesday and have been tracking the models performance over the last 6 days. I got similar returns on O/U (only 1 more loss for each model on average than the old model in that time), but I got significantly better ATS results (NN & kNN were ~59-60% ATS over the last week, the old model they were closer to 52%). Random Forest and Ada Boost had pretty much the same performance for both models. R.F. had 1 more loss on both ATS and O/U with the new Model and Ada Boost having the same O/U and 1 more win ATS. I will be using this “new” model moving forward. All of the records below reflect the older training data and models and although the R.F. had the best record after yesterday’s results, I will still list NN as the top model in anticipation for its increased performance with the modified model I will be using starting today.

For today, I will post the old model below for comparison since most of you are familiar with the old model. I will continue to try to provide the best data and projections I can and will make edits as needed to (hopefully) increase the performance of the models.

Advertisements

Records

Here is how the models have been performing.

ATS Record

O/U Record

Top Performing Models

Based on Average Win % between ATS and O/U.

  1. Neural Net – 54%
  2. Random Forest – 54%
  3. Ada Boost – 52%
  4. kNN – 52%
  5. Basic Model – 51%
  6. SVM – 48%
  7. Linear Regression – 48%
  8. SGD – 46%
Advertisements

Summary of Projections

ATS Projections

O/U Projections

Advertisements

Player and Team News

Teams on a back to back: Mavs (Home), Blazers (Pho to Den), & Wizards (LA).

Hawks/Cavs: The Cavs are still without Drummond and Prince, who have missed 4 games and 3 games respectively. Their absences will be partially reflected in the stats. The Cavs have been dreadful lately failing to cover in 13 straight games and on a 10 game losing streak. Without Drummond the Cavs have scored 103 PPG and have allowed 123.5 PPG. Without both Drummond and Prince the Cavs offense is even worse scoring 100.6 PPG. The Hawks aren’t much better going just 3-7 straight up in the last 10, 4-6 ATS, and 9-1 to the over. The season series between these teams is 1-1.

Pistons/Magic: Blake Griffin has missed 4 straight games and is out for tonight, his impact will be partially reflected in the stats. Delon Wright will miss his second straight game for the Pistons, his absence will not be reflected in the stats. Fournier returned from injury and has played the last 3 games, which all resulted in wins, since missing 4 games due to injury. His impact will be partially reflected in the stats. Magic averaged 101 PPG in the four games Fournier missed and are averaging 112 PPG in his 3 games since returning from injury. The Pistons are 3-7 straight up, 5-4-1 ATS, and 4-6 to the over in the last 10. The Magic are 5-5 straight up, 6-4 ATS, and 4-6 to the over in the last 10 games. These two teams played a couple of days ago with the Magic winning 105-96.

Celtics/Mavs: Porzingis missed yesterdays game with back spasms, if he can’t go tonight his absence will not be reflected in the stats. Celtics and Mavs have not come close to meeting preseason expectations this year and have largely been overvalued in point spreads, which is evident by their ATS record, Celtics: 15-15, Mavs: 12-17. The Celtics are 4-6 straight up and ATS, and 6-4 to the over in the last 10. The Mavs are 6-4 straight up, 3-7 ATS, and 8-2 to the over in the last 10 games.

*Porzingis has played in 2 of 4 back to backs, resting the other 2. The Mavs are 0-4 on the second night of the back to back for the season.

*Porzingis and Kleber are officially out for today, their absences wont be reflected in the stats.

Kings/Nets: Robinson is out for the Kings for the third straight game, his absence will not be reflected in the stats. Barnes is questionable for the Kings after missing the last 3 games. the Kings are 0-3 in those 3 games and his absence will be partially reflected in the stats if he can’t go. Durant is out for the fifth straight game and has missed 7 of the last 8 for the Nets, his absence will be reflected in the stats. The Nets are rolling lately going 7-3 straight up and ATS, and 6-4 to the over. The Kings are 3-7 straight up and ATS, and 8-2 to the over in the last 10 games.

Warriors/Knicks: Wiseman and Looney both participated in practice yesterday and are considered game time decisions after a significant amount of time out. If either or both can play their impacts wont be reflected in the stats. Steph Curry left last game just before tip off, but is considered probable for todays game. The Knicks are without their big man Mitchell Robinson for the 5th straight game, his absence will be partially reflected in the stats. The Warriors are 5-5 straight up and ATS, and 5-4-1 to the over in the last 10 games. The Knicks are 6-4 straight up, 7-3 ATS, and 3-7 to the over in the last 10 games.

76ers/Raptors: Kyle Lowry is listed as questionable for todays game after missing the last 3 games. If he can’t go his absence will be partially reflected in the stats. These 2 teams played a couple days ago with the Raptors winning 110-103. The 76ers are 5-5 straight up, 3-6-1 ATS, and 6-4 to the over in the last 10. The Raptors are 7-3 straight up and ATS, and 6-4 to the over in the last 10 games.

Wolves/Bucks: DeAngelo Russell and Jrue holiday remain out and have missed 7 and 8 games respectively for the Wolves and Bucks. Both players absences are reflected in the stats. KAT has played in the last 7 games so his impact will be reflected in the stats. The Wolves are 1-6 since KAT has returned (and Russell has went down). The Bucks have struggled without Holiday, going 3-5, with only 1 of those wins against a team above .500. The Wolves are 2-8 straight up, 4-5-1 ATS, and 5-5 to the over in the last 10 games. The Bucks are 5-5 straight up, ATS, and to the over in the last 10 games.

Blazers/Nuggets: Millsap has missed the last 4 games and remains out today, his absence will be partially reflected in the stats. The Nuggets are 1-3 in those 4 games. The Blazers are on the second night of an away to away back to back with the second game coming in Denver. The elevation coupled with the back to back may get the best of the Blazers and they may fade down the stretch. The Blazers are 3-2 on the second night of a back to back. The Blazers are 7-3 straight up and ATS, and 6-4 to the over in the last 10 games. The Nuggets are 4-6 straight up, 3-7 ATS, and 6-4 to the over in the last 10.

Wizards/Clippers: Westbrook has played in 1 game on the second night of a back to back all season. The Wizards are 4-3 on the second night of a back to back. The Wizards are 6-4 straight up and ATS, and 4-6 to the over in the last 10 games. The Clippers are 6-4 straight up, 5-5 ATS, and 6-3-1 to the over in the last 10.

Advertisements

Sharp Report

Early Money

Not a lot of betting data is available this morning.

ATS – Some Sharp money has come in on the Knicks (+3.5), Kings (+8), & Clippers (-10).

O/U – Some Sharp money has come in on the Hawks/Cavs Under (229) & Wolves/Bucks Under (234).

Mid Day

ATS – Some Sharp money has come in on the Magic (-2.5), Raptors (+2, small), & Celtics (-1, small).

O/U – Some Sharp money has come in on the Warriors/Knicks Over (215), 76ers/Raptors Under (223.5), & Wizards/Clippers Under (234.5, small).

Late Afternoon

ATS – Some Sharp buyback has come in on the 76ers (-1.5).

Advertisements

Model Projections

1. Neural Network (NN)

Record

Record: 51% ATS, 57% O/U.

ATS
O/U

New 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”.

Old Model Projections

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.

Advertisements

2. Random Forest (R.F.)

Record

Record: 49% 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”.

Old Model Projections

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.

Advertisements

3. Adaptive Boosting (Ada Boost)

Record

Record: 54% ATS, 51% 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”.

Old Model Projections

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.

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s