As described in the title, I started an NBA model that spits out projected point spreads. I can go into details if anybody is interested, but for now I will just use this forum to track the picks. See what works and what doesn't. See if there are any tweaks that can be done to make it better. If anybody has any experience with NBA models, and how they translate box score data into points ATS, I'd love to hear it. Please note that the model is HIGHLY flawed in that it is ONLY taking into account prior games from this year. No previous season data, no specific player data, no injury adjustments, no home/away data etc. Pure, raw, box score numbers. It is not necessarily predicting what will happen in the next game, rather it represents what the exact point differential would be if both teams performed at exactly at their season averages in each category. It might be completely useless in all honesty, but it will be interesting to see if there is value when it shows a large discrepancy from the Vegas spread. If nothing else, maybe this will lead to discussion and some input from anybody else who is interested or who has an NBA point spread model of their own. On to the picks...