Analyze a Learning-Analytics Dataset for At-Risk Detection
Overview
What this challenge is about.
You receive an anonymized dataset of LMS engagement features (logins, assignment submissions, forum posts, video-watch time), grade history, and a binary label for end-of-semester at-risk status. Build a calibrated classifier (gradient-boosted tree baseline + a small MLP for comparison) using time-window features so predictions can be made by week 4. Run a fairness audit across protected attributes provided (gender, first-generation status). Report precision-recall at recall 80% and per-group performance. The memo recommends if + how to operationalize.
The Brief
What you'll do, and what you'll demonstrate.
Build a week-4 at-risk classifier that's accurate AND fair across protected groups, with an operationalization memo for the dean.
Earning criteria — what you'll demonstrate
- Engineer time-window features for learning-analytics tasks
- Calibrate a classifier and report precision-recall meaningfully
- Audit a learning-analytics model across protected attributes
- Communicate at-risk modeling to a dean's office audience
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
Careers
Roles this prepares you for.
Real titles. Real skill bridges. Pick the one closest to your trajectory.
Data Scientist
Learning-analytics modeling with a fairness audit is the canonical data-scientist project at universities and edtech companies.
This challenge sharpens
- learning-analytics
- classification
- fairness-metrics
Machine Learning Engineer
Calibrated classifiers with no-leakage time-window features and operationalization plans are the MLE shape at edtech shipping ML.
This challenge sharpens
- classification
- feature-engineering
- scikit-learn
AI Safety Researcher
Fairness auditing on consequential decision systems is the responsible-AI lens that safety researchers bring to vertical AI work.
This challenge sharpens
- fairness-metrics
- model-evaluation
- learning-analytics