Day 1: Customer Churn Prediction with XGBoost + SHAP | 28 Projects in 28 Days (AI for Business)

Описание: 🚨 Project 1 of 28 in my “28 Projects in 28 Days” series — showing real-world AI/ML solutions that solve actual business problems.

In this video, we tackle Customer Churn Prediction using:

📦 XGBoost for accurate classification

📊 SHAP for explainability

🧼 Data preprocessing and one-hot encoding

✅ Evaluation using confusion matrix and classification report

The dataset is modeled after Telco/Subscription services (think Netflix, Spotify, banking apps). We build an end-to-end churn prediction pipeline using Python, scikit-learn, and SHAP.

💡 Use Case: Understand why customers are leaving and take action before they churn!

📁 Dataset: Telco Customer Churn (public sample data)

💻 Tech Used: Python, Pandas, Scikit-learn, XGBoost, SHAP, Seaborn

Github: https://github.com/mariamcs/Customer_...

🔥 Subscribe and follow the entire challenge!

#28Projects28Days #ChurnPrediction #XGBoost #SHAP #DataScience #MachineLearning #AIforBusiness