Another set of NBA Power Rankings is here after this week’s revelry. A few teams that had exceptional starts have found that regression to the mean is settling in a bit, but there’s more that needs to be uncovered. Last fortnight’s rankings are right here.
All team statistics are recorded as of games played on December 2nd. A few of the contests aren’t included in the model which marginally affects the results.
If you’d like to read these rankings’ methodology, then check the postscript at the end.
Here are the results after the seventh week of NBA action, some of which will be striking. But given how lopsided wins’ and losses’ impacts are diluted as the sample size grows, we should expect true contenders to emerge near the top of this ranking system by midseason.
Notes for this week’s rankings
- Golden State Warriors (1) – In both the random forest model and the hierarchical clustering model, Golden State stays ahead of the competition, meaning that in spite of their record, their offensive success, improving defense and generally stellar shooting percentages are conducive to large margin of victory and win tallies.
- Cleveland Cavaliers (5) – Derrick Rose leaves, and Cleveland gels, becoming a far stronger and more dependable defensive unit than they ever were last season. They finally project again as a 50-plus-win team.
- New Orleans Pelicans (13) – New Orleans is finding ways to generate fairly sustainable offensive production with its role players, such as Darius Miller, Rajon Rondo and E’Twaun Moore. It’s reflected statistically as they now project to become a 43-plus-win team.
- Memphis Grizzlies (22) – They’ve taken a precipitous drop given the coaching turmoil and Mike Conley’s injury. They’ve not weathered the storm at all and have quickly fallen out of playoff contention.
- Sacramento Kings (30) – In spite of its seven wins, the massive losses they’ve accrued have diminished their win projection.
Postscript: Frame of Reference for NBA Power Rankings
Once again: I’ve created two models. One that predicts team win percentage given a variety of statistics that I tested in a random forest model and another that’s based on hierarchical clustering. It isn’t a matter of who beat whom.
I should also stress that wins and losses that greatly affect a team’s net rating manifest in the final product. Therefore, if a team loses by 40, as the Magic did to the Jazz on Nov. 17, then their ranking could suffer and the opponent’s rating could flourish above expectation.
As a reminder, here’s a snapshot of the final result for 2016-17: 
