Skip to content

Parnika798/Customer-Segmentation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

ย 

History

85 Commits
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 

Repository files navigation

๐Ÿ“Š Customer Behavior Analysis & Churn Predictor Dashboard

๐Ÿš€ Link: ๐Ÿ”— Built with Streamlit | Powered by Gradient Boosting | Accuracy: 81.37%


Overview

This interactive Streamlit dashboard provides actionable insights into:

  • Customer Demographics
  • User Behavior Patterns
  • Purchase Transactions
  • Churn Prediction using Machine Learning (Gradient Boosting Classifier)

It's designed to assist businesses in optimizing user engagement, improving conversions, and proactively reducing churn.


Dataset Features

Column Description
User_ID Unique identifier for each customer
Gender Customer's gender
Age Age in years
Location Customer's location
Device_Type Device used for browsing (Mobile, Tablet, Desktop)
Product_Browsing_Time Total minutes spent browsing
Total_Pages_Viewed Number of product pages viewed
Items_Added_to_Cart Number of items added to cart
Total_Purchases Number of successful purchases

Dashboard Features

Demographics Analysis

Behavioral Trends by Device

Conversion Funnel (Browse โ†’ Add to Cart โ†’ Purchase)

Churn Prediction (81.37% Accuracy)

Intuitive Visualizations & Filters


ML Model Summary

  • Algorithm: Gradient Boosting Classifier
  • Preprocessing: Label Encoding, Standardization
  • Target: Customer Churn (Yes/No)
  • Accuracy: 81.37% on validation data
  • Deployment: Integrated with Streamlit for real-time predictions