Using Weighted Player Efficiency Rating to Predict the NBA Playoffs

By Neil Rangwani

This time of year means a few things in the world of sports: March Madness highlights take over ESPN, baseball stadiums start to fill up, and Knicks fans await their inevitable disappointment.

This NBA season looks remarkably competitive: the top of the league is crowded with legitimate contenders. The defending champion Heat and the Pacers, although sliding a bit recently, look to be the favorites in a weak East, while the Thunder, Clippers, and an extremely hot Spurs team each look like they could win the West.

In order to take a closer look at the playoff picture, we wanted to rank teams according to a metric that took into account various facets of a player’s game, so we decided to calculate a team equivalent of Player Efficiency Rating (PER). We took a relatively simple approach, since PER encompasses a number of basic statistics.

Introducing Weighted Player Efficiency Rating (WPER)

Using data for each player over the past four NBA seasons, we weighted each player’s PER by their playing time as a fraction of their team’s total playing time in order to account for a player’s actual usage. Then, we found each team’s Weighted Player Efficiency Rating (WPER) by summing the values for each player on each team.

After ranking the teams by WPER, I found the following rankings for each of the past four NBA regular seasons.

Screen Shot 2014-04-08 at 9.11.10 AM

*Note that teams in italics made the playoffs, and teams in bold made the Finals

The rankings here are pretty compelling. First off, the teams that have made the finals each of the past three years appear in the top eight of the rankings. Moving down the table gives a good approximation of where each team stood in the NBA hierarchy.

 However, we also see a few flaws in the table. Specifically, there’s a systematic overvaluing of offensive performance, and an undervaluing of defensive performance. This is probably most obviously seen in the Indiana Pacers, who rank 18th last year and 21st this year, and in the Denver Nuggets, who rank 3rd in 2011-2012 and 2012-2013. The bias is explained by the formula for PER – defensive performance is only factored into the PER through steals and blocks, which aren’t an accurate picture of a player’s defensive ability since they reward high-risk plays that often break a team’s defensive discipline.

 The previous table gives a measure of confidence in the WPER statistic. In the 2011-2012 season, the Thunder and Heat made the NBA Finals, and the next season, they posted the top two WPERs. That season, Russell Westbrook was injured in the playoffs, clearing the path for the Spurs to win the West and play the Heat in a 7-game Finals. This year, the Spurs and Heat are the top teams in WPER.

WPER’s Correlation with Win Percentage

Although the anecdotal evidence is supportive of the model, we decided to see just how correlated WPER is to team performance. We did a regression against the most tried-and-true metric of all – win percentage. This graph shows all team records over the past four years, and the associated WPER.

Screenshot 2014-04-07 00.46.10.png

The R2 of 71% is fairly strong, and suggests that WPER accounts for 71% of the variation in the win percentage.

Based on those results, we’d feel fairly comfortable using the WPER statistic to predict NBA playoff performance, along with a little bit of manual adjustment to account for the overemphasis on offensive play. The model predicts that the top two teams in the NBA are the Heat and Spurs – last year’s Finals contenders. A rematch of that epic seven-game series would present Tim Duncan with the chance to win his fifth ring and cement his legacy as one of the greatest players of all time, and would give LeBron James an opportunity to complete a three-peat. All that being said, it would be an exciting matchup, and it’s what I’m predicting here. Although not hugely controversial, based on the model, I’m picking the Heat in 6, although I’ve still got hope that the Knicks, lurking at #12 in WPER and just outside the playoff picture, will make some waves!

Special thanks to for the statistics used in this article.

Neil Rangwani hails from suburban New Jersey, and is a sophomore studying Operations Research and Financial Engineering at Princeton. A lifelong Giants and Knicks fan, he’s developed an immunity to the ups-and-downs of life.

4 thoughts on “Using Weighted Player Efficiency Rating to Predict the NBA Playoffs

  1. Interesting to see the 2011 heat at the same ranking of the 2013 heat, because I think most would agree that the 2013 team overall was much better and much more complementary than the first iteration of the “big 3” heat. Could this be because the big 3 (all posting great PERs) played more minutes in 2011 on a less balanced team, skewing the overall quality of the team?

  2. Aqeel – all three of the Big 3 saw a reduction in playing time from 2011 to 2013, with only Wade’s being a significant change. Also as expected, James’s PER rose significantly, while the other two saw slight drops. The combined effect of those changes is that the team’s WPER actually rose by almost a full point, from 16.3 to 17.2, which is a huge change. I believe that’s due to James’s ridiculous PER of 31.6 last season, which carried the team to new heights even as Wade and Bosh lost time to less efficient role players.
    Nick – I actually used regular season win percentage, since there is a lot more data there on teams with low WPER and I didn’t want to exclude them from analysis. I’ll follow up after the playoffs with a playoff win percentage chart.

Leave a Reply to 2014 NBA Playoff Schedule Cancel reply

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

You are commenting using your 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