The NCAA Evaluation Tool, which will be known as the NET, relies on game results, strength of schedule, game location, scoring margin, net offensive and defensive efficiency, and the quality of wins and losses. To make sense of team performance data, late-season games (including from the NCAA tournament) were used as test sets to develop a ranking model leveraging machine learning techniques. The model, which used team performance data to predict the outcome of games in test sets, was optimized until it was as accurate as possible. The resulting model is the one that will be used as the NET going forward.

Division I Men’s Basketball Committee adopts new ranking system

The NCAA Changing from RPI to 'the NET' Won't Matter if Committee Keeps Same Mentality

But regardless of those concerns, my biggest concern is that this is shuffling the deck chairs and ultimately won’t matter much at all if the Selection Committee mentality does not change. That mentality includes overvaluing volume of big win opportunities, so that teams that played lots of tough teams, and won a couple of them, were perceived as better than others who did not get as many chances. As I pointed out last year, the Cinderella runs of the last decade would have largely not occurred if selection continues the way it is going.

I am sure it was tested to make sure that Power conferences are favored

That's probably a good assumption, but will get the top teams in there because it's more logically derived. If you deserve it, you'll get in. Otherwise, you have to earn it the harder way. The best team in any league usually wins the tourney in the final except for like the ACC where they often get slack knowing they're in already. That's been the case recently in the CAA although NE really blew a great chance last year.

Computer rankings like Pomeroy don't like mid majors. 'm a little worried about the change.

Mid majors will definitely have to up their scheduling tactics to have any chance. That means resurrecting the bracket busters on our own terms and agreeing to home and homes with other top mids. Sometimes it will work out in a given year, others it wont. But the schools need to really start relying on that type of scheduling if they want to make the NCAA. Otherwise you will be relying on the CAAT only, at which point it makes little difference who you schedule. Most schedules at our level at put together year by year so this should not be too difficult to work on scheduling teams that will be good in a given year or two, for the return game. I know we all want home games but a road buy game, if you can get one, will become important for these metrics.

I think you will see a lot more of the Kentucky/Duke/Kansas type games or major versus major early in the year to force the computers to like the majors more, so that when their conference slate comes around it stays status quo for the majors.

Abolishing RPI a step forward, but new NCAA basketball metric a mystery

Alas, the NCAA didn’t share its most compelling numbers: how the NET and RPI compared in past seasons. Are the differences stark? Minimal? Do teams from outside major conferences such as the ACC, Big 12 and Big East fare better, or worse, in the NET?

The NCAA will unveil the first NET data early next season, first with weekly updates, then daily. Until then, we’re left hoping for the best.

“It really would have been nice for them to publish the ratings from previous seasons,” Pomeroy said. “That would be the easiest way for someone to judge. … I feel confident it will be better. It’s just needlessly confusing right now how this works and how much different it is.”