Bright Loan Bot

Inspiration

Borrowers want to know if they qualify for a loan in a convent way; loaners want to quickly determine who to loan to.

What it does

The bot uses artificial intelligence to determine if a borrower should get a loan via a message bot.

How we built it

The bot was built on top of python 3.6 with machine learning libraries, Amazon Lex and Lambda functions

Challenges we ran into

We had to find a way to quickly train the data and create an efficient, accurate prediction model.

Accomplishments that we're proud of

We created a functional proof of streamlining a solution to a common problem.

What we learned

We learned how to integrate our skill sets to create someone unique. We learned the intricacies of AWS Lambda.

What's next for Bright Loan Bot

In addition to notifying the borrower whether he qualifies for a loan, we can let unqualified borrowers know what to improve on to get a loan in the future. We plan to extend our solution for the loaner's side, so the loaning party can quickly determine how qualified a borrower is to obtain a type of loan. This can be accomplished by using deep learning for improved accuracy.

Built With

• artifical-intellgience
• gradiant-boosting
• lambda
• lex
• matplotlib
• numpy
• pandas
• python
• random-forests
• scikit-learn
• seaborn