NBA Line Projections – 28 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).

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. kNN – 64%
  2. Random Forest – 61%
  3. Ada Boost – 57%
  4. Neural Net – 57%
  5. SVM – 55%
  6. Basic Model – 51%
  7. Linear Regression – 49%
  8. SGD – 46%

Summary of Projections

ATS Projections

O/U Projections

Player and Team News

Lakers are on the second night of a back to back, last night in Philly and tonight in Detroit, rough travel. Detroit is also on a back to back (both at home), but may get Blake Griffin back after missing a few games.

Portland is still without Nurkic and McCollum which wont be fully reflected in the stats. C. Wood is expected to be back for the Rockets after a 2 game absence.

Clippers are still hit with COVID issues, missing Kawhi, Paul George, and Pat Beverly for a third straight game. That wont be fully reflected in the L8 stats. Miami on the back end of a back to back (both home), but they may get some players back from COVID protocol including Jimmy Butler, these players have been out for a while and their impact will not be reflected in the stats.

Warriors and Suns are both on the second night of a back to back, Warriors in San Francisco last night (rough travel), both Suns games at home. Devin Booker could miss his third straight which wont be fully reflected in the stats.

*Jimmy Butler is now out. Tyler Herro is cleared to play, but may be on a minutes restriction.

*Devin Booker officially ruled out for the suns.

*Anthony Davis now ruled out for the Lakers

Sharp Report

Early Money

Not enough game data is available on todays games.

Mid Day

ATS – Some Sharp action has come in on the Pistons (+10.5) & Clippers (+4.5, small).

O/U – Some Sharp money on the Blazers/Rockets over (228.5).

Late Afternooon

ATS – More money on the Pistons, but this is likely due to the Anthony Davis news. Some Sharp action has come in on the Rockets (-2.5).

O/U – Some money has come in on the Lakers/Pistons Under (217.5), but like the ATS swing this is likely due to the AD news. There isn’t any noticeable sharp action on the O/U.

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

Record: 62% ATS, 66% O/U.

Just started tracking percentages on 25 Jan, I will keep them updated on here from now on.

ATS
O/U

Model Projections

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. 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, 68% O/U.

Just started tracking percentages on 25 Jan, I will keep them updated on here from now on.

ATS
O/U

Model Projections

The Random Forest has been pretty good at O/U projections and had a recent cold spell on ATS projections. Last year Random Forest ended the season with a ~58% 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 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. 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

Record: 59% ATS, 54% O/U.

Just started tracking percentages on 25 Jan, I will keep them updated on here from now on.

ATS
O/U

Model Projections

This is the first time I’m using Ada Boost for basketball.

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).

4 comments

  1. How do you determine a loss and win in your model projections? Trying to understand where you got 9-2 on the o/u from the previous day in model RF?

    Like

    1. The model went 9-3 overall, 9-2 for one between 55-75% (I went back and checked this morning). If it says there is a >55% chance for either the over or under and it lands on that side then it marks it as a winner. If you think there is an error in the math please let me know so i can check it and fix it ASAP.

      Like

    2. I did some digging into it and found that it wasn’t properly throwing out games it should have consistently (<55%), but instead counting them against the record. I updated the record formulas to account for this. thanks for the heads up.

      Like

      1. Awesome no problem, you got great stuff here as I was stayed up till 2:30 in the morning trying to understand this. Keep up the good work my man

        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