Inside the minds of recruits?

So, it turns out there’s this thing out there that purports to help a school analyze which recruits it’s pursuing are likely to sign and which are likely to spurn.

The company founded by the four Northwestern undergraduates, called Zcruit, essentially borrows that same mentality, one of putting numbers behind what have long been gut-based decisions, and applies it to the recruiting landscape.

Think of this way: Every program in the Football Bowl Subdivision is chasing after the same pool of recruits; most programs recruit the same region as countless others; some programs offer hundreds of recruits to sign just 25 future student-athletes.

Boiled down, Zcruit’s goal is to assist a program’s efforts by streamlining the process — by taking all the streams of data at their disposal and creating a formula for recruiting success, in the same way a university’s admissions office attempts to pinpoint the best and most likely fits for the student body at large.

Three baseline factors are taken into account. The first is demographic information: background information, such as where a recruit is from. The second is a prospect’s interactions with the school, such as how many visits he has made on campus, whether he attended any camps or when the scholarship offer was tendered.

The third is the prospect’s interactions with other schools. Is he showing any interest? When was he offered by another school, when did he visit, how many times did he visit? In the end, the data compiled by Zcruit creates a threshold, for lack of a better word, between whether a program should recruit a player — if the data suggests he’s gettable — or whether it should move on to another prospect.

Zcruit claims a pretty good success rate, too.

Zcruit worked alongside Bowers and the coaching staff during this current recruiting cycle, helping the Wildcats identify and evaluate a number of recruits at positions of need. With one week until national signing day, the algorithms created by Zcruit have predicated which recruits would not sign with Northwestern with 94% accuracy; the same algorithms predicted which recruits would sign with the Wildcats with 80% accuracy.

Man, a program that could have predicted what my teenage daughters wouldn’t do over 90% of the time sure would have come in handy back then.  Just sayin’.

More power to you, guys.

Advertisements

10 Comments

Filed under Recruiting, Science Marches Onward

10 responses to “Inside the minds of recruits?

  1. DugLite

    With a 21 yo daughter and a 15 yo daughter, I feel ya.

    Liked by 1 person

  2. ApalachDawg

    Four daughter here…

    Like

  3. mwo

    One 23 year old daughter, and one 16 year old daughter. The eldest has managed through transfers, changed majors, etc. to cram a 4 year finance degree into 5 and 1/2 years. She has a nice place on Talmadge, though. The 16 year old is a Gator fan, where did I go wrong?

    Like

  4. SCIllinois

    Those statistics about their successful predictions are biased upwards — if you hire this firm and they say “Chase recruit X, but don’t chase recruit Y.” You follow their advice, and lo and behold, X signs and Y doesn’t. Is that because of ZCruit’s magic or because you followed their advice, chased X and didn’t chase Y?

    This bias increases as you get closer and closer to signing day (see last paragraph).

    I suspect that a model that uses two inputs: (1) did you offer and recruit this kid and (2) has he verbally committed to another school, would be about 40% accurate in its predictions within a week of signing day. So that’s half of their value-added at that point in time, right there.

    I’m very, very skeptical of anything claiming to be able to predict, ex ante, the behavior of high schoolers with any degree of accuracy.

    Liked by 1 person

  5. Go Dawgs!

    I think I could predict “which recruits would not sign with Northwestern” with a much better success rate than 94%…

    Liked by 1 person

  6. Far too late to help with my group of former teen age girls. Gads, that was stunning to behold. Hormones on parade day and night.

    Like