search

mapbox / gabbar

Guarding OpenStreetMap from harmful edits using machine learning
MIT License
19 stars 7 forks source link

Harmful changests of types manually not seen before #80

Closed bkowshik closed 7 years ago

bkowshik commented 7 years ago

With the current supervised learning based classifier, we train the model on changesets labelled 👍 and 👎 Soon, a classifier will start predicting new changesets based on training on the labelled dataset. But, we have not manually 👀 all types of harmful changesets, maybe we never will as new kinds of problematic edits come along.

So, ideally in the future we will need some kind of an unsupervised classifier which is not limited by the subset of labelled samples in the dataset instead can make use of each and every changeset that comes along on OpenStreetMap.

cc: @anandthakker @batpad @geohacker

bkowshik commented 7 years ago

So, ideally in the future we will need some kind of an unsupervised classifier which is not limited by the subset of labelled samples in the dataset instead can make use of each and every changeset that comes along on OpenStreetMap.

With https://github.com/mapbox/gabbar/issues/88, we have an anomaly detection model for highways that is in a way not limited by the labelled dataset of highways. 🎉 The anomaly detection prototype is something we will iterate on for a couple of weeks. Let's re-open this issue when new ideas come along.