These are statistical projections and shouldn’t be the only thing that factors in to betting on a team, the stats only tell part of the story. 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.

Like what you see? Please subscribe or follow me on Twitter (@AnalyticsB2) for the latest news and post info. Want to support the statistical data or have suggestions for improvement, feel free to send me an email (B2SportsStats@gmail.com) or you can donate via the website, Venmo (@B2stats) or Cashapp ($B2stats).

*Updated with 4 June Projections

Note: Home vs Away is not accounted for in the projections. With fans returning the Home vs. Away should be factored in (My personal opinion is home court is worth about 2-3 points).

Note: A majority of the stats pulled are from the regular season and don’t account for things like Lebron turning up the intensity in the playoffs. There isn’t really a stat that can account for that. Also, playing the same opponent every night, a good coach can make adjustments from game to game that cause the games to swing back and forth, that won’t show up in the regular season stats either.

Records

Top Performing Models

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

Team Trends

Second half of the season:

This shows teams that played better the second half of the season than the first half. (Ignore the labels that say last 8 games, its actually last 36 games.

This image has an empty alt attribute; its file name is nba_trends_second_half.png

Team Variance

Variance stats Updated in Sundays reports.

This image has an empty alt attribute; its file name is nba_var-3.png

What this chart is showing is each teams Variance & Standard Deviation (Std Dev). Variance and Std Dev are calculated from the season stats (need a larger sample size than 8 games). The list is ordered from lowest team variance to most team variance. The variance is how wide spread the data is, a team that scores between 100 and 102 points every night will have very low variance, whereas a team that scores anywhere from 75 to 145 on a given night will have very high variance. The Std Dev is the square root of the variance and is a good measure for how consistent a team is… NOT how good or bad a team is, but how consistent they are. Std Dev shows the amount a teams score typically deviates from the average on a given night. The Kings score (typically) will deviate about 9.66 points from there average on a given night, where the Wizards score (typically) will deviate 14.09 points from their average on a given night. Obviously the lower the Std Dev the easier it is for my models to project the score and provide higher probabilities.

Summary of Projections

Summary of Model Projections

Second Half of Season Stats:

Full Season Stats:

Today’s Projections

1. Random Forest (R.F.)

Model Projections – Second Half of Season Stats

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 – Second Half of Season Stats

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.

Model Projections – Full Season

Betting Edge – Full Season

2. Basic Model (B2 Model)

Model Projections – Second Half of Season Stats

Betting Edge – Second Half of Season Stats

Model Projections – Full Season

Betting Edge – Full Season

3. Neural Network (NN)

Model Projections – Second Half of Season Stats

Betting Edge – Second Half of Season Stats

Model Projections – Full Season

Betting Edge – Full Season

Series Projections – Round 1

Each series was run through the machine learning algorithms to project the score. Rather than using the last 8 games for team stats like I used all season for daily projections, these projections leveraged stats from the full season and the second half of the season.

I ran 500 Monte Carlo simulations to project how the series would go. If you don’t know what a Monte Carlo sim is, it’s basically just running the matchups 500 times using a teams Variance to come up with 500 different game results. Using the 500 Games, I counted the first team to 4 wins to get the expected series winner and counted the number of times a team won the series and the series score when a given team won.

The number of wins and win percentage is fairly easy to understand, its just the number of games out of the 500 that a particular team won and its corresponding win %.

The average game margin can tell you how close or how tight the games were. A larger average scoring margin says there were more blowout in favor of that team. a value close to 0 indicates a lot of closer games or an equal number of blowouts form each side.

The average margin of victory in games won tells you how close the games were in games that a team won. A large number typically means that when they did win, they usually crushed them. a small number means that when they did win, it was typically a close game.

Average score is just the average score by each team across all Monte Carlo Sims and the Game total is the average amount of goals scored by both teams across all simulations.

[LR = Linear Regression, kNN = k-Nearest Neighbor, RF = Random Forest, SVM = Support Vector Machine, NN = Neural Network, Ada Boost = Adaptive Boosting]