5 Potential Datasets for Customer Churn Prediction

1. Telco Customer Churn Dataset (Kaggle)
   • Description: This dataset contains data for a telecommunications company, including customer demographics, account information, and usage data. It’s designed for predicting customer churn based on features like contract type, monthly charges, and customer service interactions.
   • Features: Customer ID, gender, senior citizen status, partner status, dependents, tenure, phone service, multiple lines, internet service, online security, tech support, monthly charges, total charges, churn status (binary: churned or not).
   • Source: Kaggle – Telco Customer Churn Dataset
2. IBM HR Analytics Employee Attrition & Performance
   • Description: This dataset is suitable for predicting employee attrition (a type of churn) in a corporate setting. It includes HR-related features such as job satisfaction, education level, and work-life balance, to predict whether an employee will leave the company.
   • Features: Age, gender, education, job role, environment satisfaction, work-life balance, overtime, hourly rate, distance from home, years at company, attrition status (binary: yes/no).
   • Source: IBM HR Analytics Dataset
3. Retail Customer Churn Prediction (UCI Machine Learning Repository)
   • Description: A dataset of retail customer interactions and behavior, designed for predicting customer churn in the retail industry. This dataset includes information about customer demographics, purchasing patterns, and past interaction history.
   • Features: Customer age, gender, transaction frequency, product categories purchased, loyalty program membership, customer satisfaction, churn status.
   • Source: UCI Machine Learning Repository
4. Bank Customer Churn Prediction Dataset (Kaggle)
   • Description: This dataset contains information about bank customers and their services, including whether or not they have churned. The task is to predict the likelihood of a customer leaving based on factors such as balance, number of products, and tenure.
   • Features: Customer ID, age, balance, number of products, credit score, geography, gender, tenure, estimated salary, has credit card, is active member, churn status (binary: yes/no).
   • Source: Kaggle – Bank Customer Churn Prediction
5. Netflix Movie Rating and User Data
   • Description: Although this dataset is more focused on user preferences and ratings, it can be adapted for churn prediction in a streaming service context. It includes data on user ratings, watch history, and other factors that can influence user retention or churn.
   • Features: User ID, movie ID, rating, timestamp, genres, membership duration, user subscription type, churn status.
   • Source: MovieLens Dataset