Hacker News new | past | comments | ask | show | jobs | submit login

We have another component of the same outlier detection system that does this type of fitting, identifying low probability events using a Bayesian model + Markov Chain Monte Carlo. It hasn't gained nearly as much traction internally (yet) as the clustering approach here.

Cool. Have you found the MCMC approach to be less robust than clustering? It seems like this may be the case due to probability model assumptions.

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