I just read his twitter thread Moses, I dont think he has updated his blog in a long time.

Its funny to read these modelers through the years on the think tank on major wager and sbr, Voulgaris had 15 people working on play charting every call from various places around the court from various referees in in the NBA for entire seasons. Next time anyone in the think tank posts about scraping stats and other minutiae for models, they should look into this guys set up and data .

This is a great quote on voulgaris on modeling and data.

"The data just helps you build models either through strict regression or through supposition.” He explains that the difference between database handicapping and predictive modeling is partly what sets Voulgaris apart from the pack in the world of NBA gamblers. “I think a lot of people have databases and they do things like ‘team x does x in a back to back situation’ and they mine their databases for information like that, but that information is by and large useless.”

What Voulgaris does is different. He simulates the outcomes based on the data in his database using his own model of what teams will do given particular matchups. Both his model and his database is extremely valuable. He has spent millions of dollars and countless hours developing it, more than most NBA franchises have spent on analytics. And he has seen many millions in returns because of it.

This is an interesting quote from voulgaris.

His predictive models rely on an immense amount of data that is constantly being updated. This requires him to watch a LOT of NBA games. “A lot of what I do is just watch more basketball than any other human,” he told Pokercast. “I watch about 400 games from beginning to end. I watch at least one or two quarters of maybe 85-90% of games. I may just watch every defensive possession or every offensive possession or just watch particular lineups or matchups.”