AmrrSalem/Customer-Churn-Prediction

View on GitHub by @AmrrSalem

Interactive Streamlit app with 7 ML models to predict Telco customer churn | Live: https://app-churn-dashboard-by-amrr-salem.streamlit.app

What's novel

Interactive Streamlit app with 7 ML models to predict Telco customer churn | Live: https://app-churn-dashboard-by-amrr-salem.streamlit.app

Code Analysis

2 files read · 2 rounds

A Streamlit dashboard that trains and deploys 7 ML models to predict customer churn on the IBM Telco dataset with feature engineering and business impact analysis.

Strengths

Robust feature engineering logic with comprehensive edge case handling (e.g., division by zero), strong test coverage for data preprocessing functions, and a well-structured authentication flow with cloud storage integration.

Weaknesses

Monolithic single-file architecture limits maintainability and separation of concerns, lack of tests for core ML training pipeline and visualization logic, and reliance on external dependencies like Supabase without fallback mechanisms.

Score Breakdown

Innovation

3 (25%)

Craft

60 (35%)

Traction

8 (15%)

Scope

62 (25%)

Signal breakdown

Innovation

Not Fork+1

Code Novelty+1

Concept Novelty+0

Craft

Ci-1

Tests+5

Polish+0

Releases+0

Has License+5

Code Quality+18

Readme Quality+15

Recent Activity+7

Structure Quality+4

Commit Consistency+2

Has Dependency Mgmt+5

Traction

Forks+0

Stars+6

Hn Points+0

Watchers+0

Early Traction+0

Devto Reactions+0

Community Contribs+2

Scope

Commits+7

Languages+3

Subsystems+0

Bloat Penalty+0

Completeness+7

Contributors+6

Authored Files+8

Readme Code Match+3

Architecture Depth+3

Implementation Depth+8

Evidence

Commits

Contributors

Files

Active weeks

TestsCI/CDREADMELicenseContributing

Repository

Language

Python

Stars

Forks

License

NOASSERTION