Skip to contentSkip to content
Verified credentials. On-chain. Forever.Learn more
Ewance
Sign in
Cover image for Predict 30-Day Churn for a Direct-to-Consumer Cosmetics Brand
Analysis

Predict 30-Day Churn for a Direct-to-Consumer Cosmetics Brand

FreeVerified credential2 weeksIntermediate

Overview

What this challenge is about.

Predict 30-Day Churn for a Direct-to-Consumer Cosmetics Brand. Intermediate challenge in analysis. Analyzing real datasets and building models that drive dec...

CredentialBlockchain-anchored
ShareableLinkedIn-ready
LanguageEnglish
PaceSelf-paced

The Brief

What you'll do, and what you'll demonstrate.

Identify which subscribers are most likely to cancel within the next 30 days so the marketing team can intervene proactively with retention offers.

This is not a data exercise. It is the work an analyst does when stakeholders need answers from messy data. That distinction matters to every hiring manager who has seen candidates describe statistical methods and none who have extracted insight from messy, real-world data.

When you finish, you will have something most graduates do not: a real-world deliverable, verified by Ewance, that you can show to a hiring manager and say "I did this. Here is the proof."

Earning criteria — what you'll demonstrate

  • Engineer behavioral features from raw subscriber activity data that meaningfully predict churn without leaking the outcome
  • Train and tune interpretable classifiers in scikit-learn while correctly handling class imbalance
  • Evaluate a classifier with AUC-ROC and threshold-aware metrics on a held-out split, and justify the choices
  • Translate model feature importance into plain-language drivers and concrete retention actions for a non-technical audience

Program Fit

Where this fits in your program.

Sharpens the same skills your degree expects you to demonstrate.

Aligned coursework coming soon.

Careers

Career paths this challenge builds toward

Completing this challenge demonstrates skills that transfer directly to these roles:

Data Scientist

This challenge mirrors a core data science loop: framing a business problem, engineering features from behavioral data, and shipping an evaluated, interpretable model. It builds the judgment to balance accuracy with explainability that hiring teams probe for.

This challenge sharpens

  • feature-engineering
  • classification
  • scikit-learn

Machine Learning Engineer

Building a reproducible scikit-learn pipeline that handles imbalance and runs end to end develops the engineering discipline ML roles demand, bridging from exploratory modeling toward production-ready, maintainable prediction code.

This challenge sharpens

  • python
  • scikit-learn
  • classification

Marketing Analytics Specialist

Translating churn predictors into retention actions for a non-technical team is the heart of marketing analytics. The challenge strengthens the ability to turn model output into campaign decisions that move retention metrics.

This challenge sharpens

  • feature-engineering
  • logistic-regression
  • classification

One more thing

You can put a credential on your CV by Friday.