Hunting for the new Netflix algorithm

Lately, I’ve been thinking a lot about how to use reputation as a tool for creating better social experiences online. As I’ve said before, to do any sort of reputation system, you have to track a lot of user actions and then feed them into the right algorithm. The second part is by far the hardest to accomplish since you actually have to discover what the right algorithm is. A great example of this process in the real world is the Netflix prize. Wired has an interesting recent article on this here. I was excited to learn that one of the entrants is actually using human behavioral principles to better inform his algorithm. It’s a fantastically interesting read.

Couldn’t a pure statistician have also observed the inertia in the ratings? Of course. But there are infinitely many biases, patterns, and anomalies to fish for. And in almost every case, the number-cruncher wouldn’t turn up anything. A psychologist, however, can suggest to the statisticians where to point their high-powered mathematical instruments. “It cuts out dead ends,” Potter says.