Inspiration

The inspiration for me to build this web app was to first look into the Zimbabwean market, and I see that we don't have something of this kind, so I then created it.

What it does

It predicts if a client will be able to pay back their loan according to their historical information.

How we built it

I collect data from the Zimbabwean Statistic Association and from Zimbabwean banks, also. I then cleaned that data, did some feature engineering, and trained a lot of models until I chose the highest accuracy.

Challenges we ran into

As a student, I didn't have time to create it, and I may have removed precious data during feature engineering.

Accomplishments that we're proud of

The web app is running

What we learned

We learned a lot about how the Zimbabwean banks work, how to create a web app and how to do modelling also.

What's next for Loan Defaults Prediction

If I got the money, I could create the application.

Built With

  • catboost
  • css
  • html
  • openai
  • streamlit
  • tabpfn
Share this project:

Updates