Design a Churn-Prediction and Retention Model for TaskFlow
Overview
What this challenge is about.
Build a churn-prediction model for a B2B software platform, engineer features, and identify top churn drivers to earn your verifiable certificate.
The scenario
TaskFlow is a 40-person business-software company moving from self-service, sign-up-led growth toward a sales-led model that targets larger enterprise accounts, where each lost renewal carries far more revenue weight.
The Brief
What you'll do, and what you'll demonstrate.
Identify the factors that most strongly drive customer cancellations and design a logistic regression model that flags at-risk accounts before they churn.
Earning criteria — what you'll demonstrate
- Translate a business retention question into a well-specified classification problem
- Engineer predictive features from raw monthly account data and justify each choice
- Fit and validate a logistic regression model and judge it with AUC-ROC and a confusion matrix
- Interpret logistic regression coefficients as odds ratios for a non-technical audience
- Convert model insights into prioritized, feasible retention actions
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Aligned coursework coming soon.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
- Logistic Regression
Apply logistic regression to solve real industry problems and demonstrate production-level capability.
- Classification
Apply classification to solve real industry problems and demonstrate production-level capability.
- Feature Engineering
Apply feature engineering to solve real industry problems and demonstrate production-level capability.
- Model Evaluation
Apply model evaluation to solve real industry problems and demonstrate production-level capability.
Careers
Career paths this challenge builds toward
Completing this challenge demonstrates skills that transfer directly to these roles:
Customer Analytics Analyst
This challenge mirrors the core work of a customer analytics analyst: turning behavioral account data into a churn model and retention insights that a Customer Success leader can act on, including the interpretation skills that make findings credible to non-technical stakeholders.
This challenge sharpens
- logistic-regression
- feature-engineering
- model-evaluation
Data Scientist (Retention/Growth)
Building, validating, and interpreting a classification model against a real business target reflects the day-to-day of a retention-focused data scientist, who must balance predictive performance with explanations the business trusts and can operationalize.
This challenge sharpens
- classification
- model-evaluation
- feature-engineering
Business Intelligence Analyst
Framing a vague business worry as a measurable prediction problem and communicating odds ratios as plain recommendations is exactly the bridge a BI analyst builds between raw data and decisions made by operations leaders.
This challenge sharpens
- logistic-regression
- classification
- model-evaluation