APBRmetrics

Hi,

In my latest post, I create a machine learning scout for the Miami Heat and track how it fares after 5 games.

Producing the machine learning scout takes under an hour:

Gather data, format data, run it through algorithm to get winning/losing factors = 10 minutes

Find data backed evidence to support the factors, set targets, write scout = 45 minutes

All up the machine learning based scout is put together in under an hour. It would interesting to compare against the traditional process that scouting/coaches go through especially on back to back games where time is of the essence.

Check out the results at http://www.zigzaganalytics.com/home/tra ... e-learning

Maybe contact Ben Falk, D Oliver or other former insiders for reaction? They could respond on own, but I dunno how likely it is without or with extra prompting. Dean's roboscout might have some similarities but he hasn't shared details in past.

Also your machine learning findings have a similar character to the "tips" found at hoopsstats.com. Such as http://www.hoopsstats.com/basketball/fa ... ips/18/1/1 Not sure how are generated. Site owner has posted here before but years ago. Could try to contact, if there is a reason.