XYZ Bank Customer Churn Predictor
AI-Powered Bank Customer Churn Insights, Automated Retention
29 followers
AI-Powered Bank Customer Churn Insights, Automated Retention
29 followers
Full-stack Bank Churn Predictor analyzing 4,000+ records with SVM/XGBoost (84%+ accuracy), SMOTE-balanced. Features dashboards, LLM-powered churn insights (Qwen3 32B), & automated retention emails—built with Python, Supabase, HTML/CSS/JS, JSON & Streamlit.
Thanks for checking out Bank Customer Churn Predictor!
Built this full-stack FinTech tool to help banks and financial institutions predict & prevent customer churn with over 84% model accuracy.
It features:
1)AI/ML-powered predictions (SVM, XGBoost + SMOTE)
2)Custom dashboards via custom model deployed through Streamlit
3)LLM-based personalized insights (Qwen3 32B)
4)Auto-generated retention emails
Fully built with Python, Supabase, HTML/CSS/JS
Would love your thoughts, feedback, and suggestions!
Happy to answer any questions or dive deeper into the tech behind it.
𝗨𝗣𝗗𝗔𝗧𝗘: 𝗠𝗶𝗴𝗿𝗮𝘁𝗲𝗱 𝗱𝗮𝘁𝗮𝗯𝗮𝘀𝗲 to 𝗦𝘂𝗽𝗮𝗯𝗮𝘀𝗲.
🚨🚨𝗨𝗣𝗗𝗔𝗧𝗘: 𝗙𝗶𝘅𝗲𝗱 𝗲𝗺𝗮𝗶𝗹𝗶𝗻𝗴 through 𝗘𝗺𝗮𝗶𝗹𝗝𝗦 with updated settings‼️
Update: Added a Graphs page for churn visualizations & insights.
Latest updates on my Customer Churn predictor :
1)Added state & session management, ensuring that, even on page refreshes after login, the page stays in current state without reverting back to original state & getting logged out, overriding default behaviour.
2)Hiding topbar.
Demo: https://youtu.be/DAR2IoJdjeg .
UPDATE: Removed consistent display of sidebar breadcrumb strip, cleaned up UI & enhanced responsive functionality, alongside Streamlit version & library functions upgradation for compatibility.