Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Credit risk analysis for credit card applicants
| Date | Stars |
|---|---|
| 2026-07-24 | 310 |
| 2026-07-25 | 310 |
| 2026-07-28 | 310 |
| 2026-07-30 | 310 |
| 2026-08-06 | 310 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
 Banner [source](https://banner.godori.dev/)      [](https://colab.research.google.com/drive/1CfV6yEsHBjFiJbTKwY72k2g4AvszcF5R) [](https://share.streamlit.io/semasuka/credit-card-approval-prediction-classification/main/cc_approval_pred.py) [](https://github.com/ellerbrock/open-source-badges/) Badge [source](https://shields.io/) # Key findings: People with the highest income, and who have at least one partner, are more likely to be approved for a credit card. ## Authors - [@semasuka](https://www.github.com/semasuka) ## Table of Contents - [People with the highest education level, and who are either husbands or wifes make more money](#people-with-the-highest-education-level-and-who-are-either-husbands-or-wifes-make-more-money) - [Authors](#authors) - [Table of Contents](#table-of-contents) - [Business problem](#business-problem) - [Data source](#data-source) - [Methods](#methods) - [Tech Stack](#tech-stack) - [Quick glance at the results](#quick-glance-at-the-results) - [Lessons learned and recommendation](#lessons-learned-and-recommendation) - [Limitation and what can be improved](#limitation-and-what-can-be-improved) - [Run Locally](#run-locally) - [Explore the notebook](#explore-the-notebook) - [Deployment on streamlit](#deployment-on-streamlit) - [App deployed on Streamlit](#app-deployed-on-streamlit) - [Repository structure](#repository-structure) - [Contribution](#contribution) - [License](#license) ## Business problem This app predicts if an applicant will be approved for a credit card or not. Each time there is a hard enquiry your credit score is affected negatively. This app predict the probability of being approved without affecting your credit score. This app can be used by applicant who wants to find out if they will be approved for a credit card without affecting their credit score. ## Data source - [Kaggle credit card approval prediction](https://www.kaggle.com/rikdifos/credit-card-approval-prediction) ## Methods - Exploratory data analysis - Bivariate analysis - Multivarate correlation - S3 bucket model hosting - Model deployment ## Tech Stack - Python (refer to requirement.txt for the packages used in this project) - Streamlit (interface for the model) - AWS S3 (model storage) ## Quick glance at the results Correlation between the features.  Confusion matrix of gradrient boosting classifier.  ROC curve of gradrient boosting classifier.  Top 3 models (with default parameters) | Model | Recall score | |------------------- |------------------ | | Support vector machine | 88% | | Gradient boosting | 90% | | Adaboost | 79% | - ***The final model used is: Gradient boosting*** - ***Metrics used: Recall*** - Why choose precision as metrics: Since the objective of this problem is to minimize the risk of credit default for the financial institution, the metrics to use depends on the current economical situation: - During the time of a bull market (when the economy is expending), people feel wealthy and usually are
Excerpt of 10,726 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:1e52fb81608ca50e, topic:streamlit