Re-segment a SaaS Customer Base by How Accounts Actually Use the Product
Overview
What this challenge is about.
Re-segment a SaaS Customer Base by How Accounts Actually Use the Product. Intermediate challenge in analysis. Analyzing real datasets and building models tha...
The Brief
What you'll do, and what you'll demonstrate.
Group 3,400 paying accounts into four to six behavior-based segments that the customer success team trusts and can act on, replacing segmentation by contract size alone.
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 features that express usage depth and engagement rather than raw activity volume
- Compare clustering algorithms on stability and interpretability and defend a final cluster count
- Translate quantitative clusters into account segments a non-technical team can recognize and act on
- Reconcile model output with domain expert knowledge and iterate based on the disagreement
- Design a lightweight, sustainable plan to detect when a segmentation has drifted
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.
- Clustering
Apply clustering to solve real industry problems and demonstrate production-level capability.
- K Means
Apply k means to solve real industry problems and demonstrate production-level capability.
- Hdbscan
Apply hdbscan 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.
- Stakeholder Communication
Apply stakeholder communication to solve real industry problems and demonstrate production-level capability.
- Data Storytelling
Apply data storytelling 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:
Data Scientist (Customer Analytics)
Customer analytics roles live or die on turning behavioral data into segments the business will act on. This challenge rehearses exactly that: choosing features, defending a clustering method, and shipping segments tied to revenue playbooks rather than a notebook nobody reads.
This challenge sharpens
- clustering
- feature-engineering
- data-storytelling
Machine Learning Engineer
Machine learning engineers must pick and justify unsupervised methods and keep them healthy in production. Comparing K-means, hierarchical, and HDBSCAN on stability and then designing a drift-monitoring plan mirrors the model-selection and maintenance work the role demands.
This challenge sharpens
- k-means
- hdbscan
- clustering
Customer Success Operations Analyst
Success operations analysts translate account data into the segments and playbooks the team runs on. Validating clusters against field notes and writing a memo that maps each segment to an engagement plan is the core of bridging analytics with frontline customer success work.
This challenge sharpens
- feature-engineering
- stakeholder-communication
- data-storytelling