Use case on the churn dataset

Dataset churn

Machine Learning Task: Binary classification

This is a churn dataset. A dataset relating characteristics of telephony account features and usage and whether or not the customer churned.

Available at OpenML:

Category: Marketing

# Rows: 5,000 # Columns: 20

Target: class


Numeric: state, account_length, phone_number, number_vmail_messages, total_day_minutes, total_day_calls, total_day_charge, total_eve_minutes, total_eve_calls, total_eve_charge, total_night_minutes, total_night_calls, total_night_charge, total_intl_minutes, total_intl_calls, total_intl_charge

Nominal: area_code, international_plan, voice_mail_plan, number_customer_service_calls

Machine Learning Use Case Marketing

Area Under ROC Curve (AUC)

Churn Auc

Accuracy (ACC)

Churn Acc

Balanced Accuracy (BALACC)

Churn Balacc

Cross-Entropy Loss (LOGLOSS)

Churn Logloss

« Back to Machine Learning Algorithms Comparison