https://github.com/soumilgit/xyz-bank-customer-churn-predictor

A modular bank customer churn predictor ML project leveraging Groq API, Streamlit, Supabase, SciPy, Plotly and EmailJS, alongside libraries - NumPy, Pandas, Utils, OS, Base64, Re, Pillow & DateTime.
https://github.com/soumilgit/xyz-bank-customer-churn-predictor

decision-tree-classifier emailjs fintech html-css-javascript jupyter-notebook mlops naive-bayes-classifier openai pickle-file pillow-library python qwen3-32b rag-pipeline random-forest-classifier scikit-learn smote streamlit supabase svm-classifier xgboost-classifier

Last synced: about 1 month ago
JSON representation

A modular bank customer churn predictor ML project leveraging Groq API, Streamlit, Supabase, SciPy, Plotly and EmailJS, alongside libraries - NumPy, Pandas, Utils, OS, Base64, Re, Pillow & DateTime.

• Host: GitHub
• URL: https://github.com/soumilgit/xyz-bank-customer-churn-predictor
• Owner: Soumilgit
• License: mit
• Created: 2025-02-01T06:09:20.000Z (8 months ago)
• Default Branch: main
• Last Pushed: 2025-08-25T17:34:16.000Z (about 2 months ago)
• Last Synced: 2025-08-25T19:28:41.015Z (about 2 months ago)
• Topics: decision-tree-classifier, emailjs, fintech, html-css-javascript, jupyter-notebook, mlops, naive-bayes-classifier, openai, pickle-file, pillow-library, python, qwen3-32b, rag-pipeline, random-forest-classifier, scikit-learn, smote, streamlit, supabase, svm-classifier, xgboost-classifier
• Language: Jupyter Notebook
• Homepage: https://cust-churn-pred-bank.streamlit.app/
• Size: 13.7 MB
• Stars: 21
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • Funding: .github/FUNDING.yml
  • License: LICENSE

Awesome Lists containing this project

README

          
# Bank Customer Churn Predictor

## Architecture



## Description + stats

- Bank customer churn prediction application utilizing:

| Name of model                        | Accuracy   |

|--------------------------------------|------------|

| Decision Tree                        | 79.13%     |

| K-Nearest Neighbors (KNN)            | 82.00%     |

| Naive Bayes                          | 82.25%     |

| Random Forest Classifier             | 83.75%     |

| Support Vector Machine (SVM)         | 84.13%     |

| XGBoost Classifier                   | 84.25%     |

| XGBoost + SMOTE Classifier           | 83.87%     |

| Voting Classifier                    | 83.63%     |

| Qwen3 32B LLM [OpenAI]               | —          |

- It ingests 4000 entries to predict churn risk with visual insights, AI-generated explanations and emails.

## Tech Stack

| Purpose              | Technologies |

|----------------------|--------------|

| **Core Tech** | ![Python](https://img.shields.io/badge/Python-3776AB?style=for-the-badge&logo=python&logoColor=black) ![scikit-learn](https://img.shields.io/badge/scikit--learn-F7931E?style=for-the-badge&logo=scikit-learn&logoColor=black) ![OpenAI](https://img.shields.io/badge/OpenAI-8968CD?style=for-the-badge&logo=openai&logoColor=black) ![Plotly](https://img.shields.io/badge/plotly-7A76FF?style=for-the-badge&logo=plotly&logoColor=black)|

| **Frontend & Framework** | ![HTML](https://img.shields.io/badge/HTML5-E34F26?style=for-the-badge&logo=html5&logoColor=black) ![CSS](https://img.shields.io/badge/CSS3-0080FE?style=for-the-badge&logo=css&logoColor=black) ![JavaScript](https://img.shields.io/badge/JS-F7DF1E?style=for-the-badge&logo=javascript&logoColor=black) ![Streamlit](https://img.shields.io/badge/Streamlit-FF4B4B?style=for-the-badge&logo=streamlit&logoColor=black) |

| **Backend + DB** | ![Supabase](https://img.shields.io/badge/Supabase-3FCF8E?style=for-the-badge&logo=supabase&logoColor=black) ![EmailJS](https://img.shields.io/badge/EmailJS-FF9A00?style=for-the-badge&logo=mailboxdotorg&logoColor=black) |

| **Other Libraries** |  ![NumPy](https://img.shields.io/badge/NumPy-7285A5?style=for-the-badge&logo=numpy&logoColor=black) ![Pandas](https://img.shields.io/badge/Pandas-A865B5?style=for-the-badge&logo=pandas&logoColor=black) ![SciPy](https://img.shields.io/badge/SciPy-8CAAE6?style=for-the-badge&logo=scipy&logoColor=black) ![Pillow](https://img.shields.io/badge/Pillow-D3D3D3?style=for-the-badge&logo=imagedotsc&logoColor=black) |

## Database + authentication

https://github.com/user-attachments/assets/9aea195d-7073-4813-9a08-3648790b84ce

## Quick Start

1. Clone repo  

2. ```

   pip install -r requirements.txt

   ```  

3. Store below in a secrets.toml file under a .streamlit folder :

```

GROQ_API_KEY = ""

SUPABASE_URL = ""

SUPABASE_SERVICE_ROLE_KEY= ""

EMAILJS_PUBLIC_KEY= ""

EMAILJS_TEMPLATE_ID= ""

EMAILJS_SERVICE_ID= ""

```

4. ```

   streamlit run main.py

   ```

## Research references + custom dataset badge-links



  

    

  

  

  

    

  


  

  





## License

This project is licensed under the [MIT License](https://github.com/Soumilgit/Datathon_Team-DataP1ac3X.c0m/blob/main/LICENSE).