This week, we went 52/95, giving 54.7% accuracy, a value comparable to the previous week. We believe this relatively modest early showing is largely due to the fact that we haven’t yet got many games to train on for the current season. As more games come in, our accuracy should increase, perhaps approaching 70% — the value we were hitting at the end of this last NBA season. We also are working on implementing a few improvements to our algorithm, which we hope will also give us a boost. New predictions are now posted.
| Point spread | # games | Accuracy |
|---|---|---|
| <= 1 | 31 | 52% |
| <=2 | 14 | 50% |
| <=5 | 32 | 56% |
| >5 | 18 | 61% |
Jonathan grew up in the midwest and then went to school at Caltech and UCLA. Following this, he did two postdocs, one at UCSB and one at UC Berkeley. His academic research focused primarily on applications of statistical mechanics, but his professional passion has always been in the mastering, development, and practical application of slick math methods/tools. He currently works as a data-scientist at Stitch Fix.