Hacker News Reader

Developed a sales forecasting algorithm that turned out to be within 5% of actual sales numbers over a 18 month period.

Note: I don't know how its performing now because I switched jobs.

Would you mind talking about this with me?

jpwagner [at> mit <dotty] edu

Thanks!

Isn't it weird leaving that sort of thing behind? I also built a "purchase prediction model" right before I left a startup. It did really well on the test portion of the data (which wasn't included when building the model), but I have no idea how it's performing in the wild. It's stranger than leaving something like a program that has a clear function, because it's not necessarily obvious how well the model is performing compared to how well it "could" be performing.

Have you thought about getting ahold of them to find out how it performs now, just for curiosity's sake?

Actually yes it was weird and kind of sad because the developers that I left to maintain it are kind of morons (IMHO).

I never really considered asking them how it was doing now; I have been so busy working on other projects but I would like to know.

Reply on news.ycombinator.com