Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I've experimented with classifying my own transaction history using n-grams and either naive Bayes or a neural network, the neural network worked better. I could train the nn to convergence in a few seconds and it was good enough to remove 95% of the classification work.


Consider applying for YC's Fall 2026 batch! Applications are open till July 27.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: