Machine Learning
Milestone 1 of 7 ยท industry roleplay

Onboarding & the data audit

Your first week at Bluegum Health. Turn a vague request into a real ML problem, then find out what is wrong with the data before anyone trains a model. Includes 9 hands-on Python coding tasks (pandas, scikit-learn), checked by automated tests.

Rigour50Communication50Ethics50Impact50Teamwork50
Mon 9:00Welcome aboardMon 10:30Day one: set up your laptopMon 10:00Project kick-offMon 14:00Write the problem statementTue 11:20The data arrivesTue 14:00Code it: pull the training data with SQLTue 15:30Code it: history features with window functionsTue 14:00Code it: explore the data (1/3): size, types, missing valuesTue 15:00Code it: explore the data (2/3): summary statisticsTue 16:00Code it: explore the data (3/3): visualise itWed 9:30Audit the dataWed 11:00Code it: the cleaning functionWed 14:00Delete, replace or fill?Wed 15:00Code it: fix, fill and transformThu 15:00Code it: charts for the Friday updateThu 10:00Feature brainstormThu 14:00Code it: a leak-free history featureFri 16:00Friday update

Welcome to your first day

You have just joined Bluegum Health, a health-analytics startup, as a junior ML engineer. Over seven milestones you will take a project from a vague request to a live, monitored system, build an LLM assistant, and finish with a full interview loop, working with a real-feeling team. Choices matter, and some come back later.

Bluegum Health, Riverside Clinics and every person here are fictional. The decisions, tools and practices are modelled on how real ML teams work.

Ready