We wanted to use machine learning to predict the priority of GitHub issues

What it does

How we built it

We built the model using the scikit-learn library and term frequency–inverse document frequency

Challenges we ran into

It was very difficult to query the data just due to the convoluted way it was stored.

Accomplishments that we're proud of

We're proud that our model ended up doing significantly better than a random guess.

What we learned

What's next for GitHub Issue Predictor

Share this project: