NBA Line Projections – 25 Jan 21

As always keep an eye on injuries and COVID Issues. All stats pull from the Last 8 games (L8), so be aware of teams stats that don’t reflect recent injuries, recent returns, and recent trades. I will regularly post updates throughout the day and annotate with a “*”.

Residual absences from previous games could be skewing some results (for example, Zion, Lonzo, and Ingram missed a few games for the Pelicans within the L8 which could be negatively affecting their line projections since stats are pulled from L8).

I will only post the top 3 scoring models, but I will keep track on how every model is doing and keep record up to date right here.

Sometime within the next week I will do a writeup on how each one works and include that in a report.

Records

Here is how the models have been performing. So far most of the Machine Learning Models have performed well… but it’s been a small sample size.

ATS Record

O/U Record

Top Performing Models

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

  1. kNN – 74%
  2. Ada Boost – 62%
  3. Random Forest – 61%
  4. Neural Network – 59%
  5. SVM – 57%
  6. Basic Model – 51%
  7. Linear Regression – 50%
  8. SGD – 48%%

Summary of Projections

ATS Projections

These Consensus ATS picks seem odd that they are all on the same side, but with some teams impacted by injuries, COVID, and teams on a back to back, I will be fading some of these picks.

O/U Projections

Player and Team News

Teams on a back to back: Hornets @ Magic, Toronto @ Indians (both played each other lastnight). Cavaliers (Bos to Cle), Spurs (SA to NO), Celtics (BOS to Chi), Blazers (Home), & Thunder (LA to Por).

*Lowry is in the starting lineup, Siakam is Out! Lowry and Siakam are both GTD for the Raptors. If they miss it will not be reflected in the stats.

D. Rose is out for the Pistons.

Miami has been hit hard by injury and COVID. They are missing a large chunk of their team and it appears Jimmy Butler and Tyler Herro will still be out.

** Al Horford is now listed as out! Horford is expected to return for the Thunder. His impact wont be reflected in the stats.

Nurkic and McCollum are still out for the Blazers. Their impact wont be fully reflected in the stats.

*Covington is now out for the Blazers.

Jason Tatum is expected to return for the Celtics but Kemba is out for rest on the back to back.

*Aaron Gordon is active for the Magic tonight.

KAT is still listed as out for the T-Wolves and DeAngelo Russel is now listed as doubtful.

*Joel Embiid is out for the 76ers!

Sharp Report

Early Money

limited games have betting data available.

ATS – Sharp Money has come in on the Nuggets (+2) & Thunder (+6.5).

O/U – Not enough data is available on over/unders

Mid Day

ATS – Sharps have pounded the Bulls from +8 down to +4.5. Some Sharp money has also come in on the Raptors (+2.5) and the Thunder (+6, small).

O/U – Some Sharp money has come in on the Hornets/Magic Under (213.5), Lakers/Cavs Under (215), and Warriors/T-Wolves Over (225).

Late Afternooon

ATS – Some Sharp money has continued in on the Bull, all the way down to +3.5 now. Sharp money has picked back up on the Nuggets and pushed line to Nuggets -2. Some Sharp money has also come in on the Magic (-1) and some take back on the Pacers pushing the line back to Pacers -2.5.

O/U – Some Sharp action has come in on the Thunder/Blazers Over (225) but nothing too big. not much else in the way of Sharps on totals.

Model Projections

1. 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: 74% ATS, 75% O/U.

Model Projections

The kNN model is off to a hot and fast start, let’s hope it keeps it going. The success has been too good for any model and this is likely do for a regression. Last season the kNN ended the year at about a ~61% ATS winning percentage.

Betting Value

If you don’t understand what you are looking at, please read my post about betting tips. The percentages represent value for that particular number. Good value alone doesn’t mean you should 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).

2. Adaptive Boosting (Ada Boost)

I did not learn boosting in Grad School, but I know this is some form of boosted tree algorithm. But I had the code and the data I already had didn’t need to be re-formatted so we will see how this 100 tree estimator performs together.

Record: 73% ATS, 50% O/U.

Model Projections

The ATS predictions have been the driving force for this model and it has been poor at correctly projecting Over/Under numbers. I did not use Ada Boost last year so we will see how it does in its first NBA season.

Betting Value

If you don’t understand what you are looking at, please read my post about betting tips. The percentages represent value for that particular bet type, number, and price. Good value alone doesn’t mean you should 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).

3. 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: 60% ATS, 62% O/U.

Model Projections

The Random Forest has been good at both ATS and O/U projections. Last year Random forest ended the season with a ~58% winning percentag

Betting Value

If you don’t understand what you are looking at, please read my post about betting tips. The percentages represent value for that particular bet type, number, and price. Good value alone doesn’t mean you should 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).

7 comments

    1. If the cover probability is >55% and its is correct it counts it as a Win. If not it counts it as a loss. If the probability is <55% it considers it a toss up and throws it out (doesn’t count it whether it wins or loses). If you think something is wrong with the grading please let me know, the grading the picks is tedious and there is a decent chance I transposed something.

      Liked by 1 person

      1. Thanks B2. The grading is fine…Are you counting records by yourself or is an automated process?
        1.Cavs@Boston: 55.55% Over- W
        2. Charlotte@Orlando: 68.48% Over- L
        3. Wsh@SAS: 74.42% Under- W
        4. Atlanta@Milwaukee: 85,65% Under- L
        So as per above I believe it should be 2:2 and this is the why I was curious. This was just a random 1-day check, but if you do this manually there could me more of it both ways. Just a frienndly heads-up.

        Like

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