My project partner in Austin said my AI model was 'overfit to my own data' and it stung but he was right

We were building a tool to predict local traffic patterns, and I was super proud of my 98% accuracy. He pointed out I'd only trained it on my own commute data for two weeks, so it just memorized my specific route. I scrapped it and gathered data from 500 different users across the city for a month. Has anyone else had to totally rebuild a model after a simple critique like that?

3 comments

3 Comments

williamt443mo ago

That 98% number is a classic trap. Did you end up testing the first model on any new routes at all before your partner called it out, or did the high score just feel too good to question?

avery6293mo ago

Remember when @williamt44 got too confident about his fantasy football algorithm and it blew up?

grace_hunt841mo ago

Maybe it's just me but my "90% success rate" was mostly just blind luck on familiar streets.