Scope a Demand-Forecasting Model with Operations Stakeholders
Overview
What this challenge is about.
Map stakeholder pain to ML problems, score impact vs. feasibility, and scope a V1 forecast model. Finish with a verifiable certificate.
The scenario
The chain (around 320 stores in central and southern Mexico, around 12,000 SKUs per store) currently loses an estimated 4-6% of fresh-category revenue to spoilage and out-of-stock events.
The Brief
What you'll do, and what you'll demonstrate.
Translate operations-team pain into a tightly scoped, measurable ML forecasting problem the data team can start building.
Earning criteria — what you'll demonstrate
- Translate vague stakeholder pain into a measurable ML problem statement
- Choose evaluation metrics that map to a real operational decision
- Document explicit non-goals to avoid scope creep
- Apply a lightweight prioritization framework to a candidate backlog
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Machine Learning in Practice
Master · Machine Learning
Strong alignment
This challenge maps to Machine Learning in Practice at the Master level. It sharpens the same practical skills your coursework expects — but in a real industry context with actual constraints and deliverables.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
- Stakeholder Framing
Apply stakeholder framing to solve real industry problems and demonstrate production-level capability.
- Ml Problem Scoping
Apply ml problem scoping to solve real industry problems and demonstrate production-level capability.
- Metric Design
Apply metric design to solve real industry problems and demonstrate production-level capability.
- Prioritization
Apply prioritization to solve real industry problems and demonstrate production-level capability.
- Requirements Writing
Apply requirements writing to solve real industry problems and demonstrate production-level capability.
- Exploratory Data Analysis
Apply exploratory data analysis 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:
AI Product Manager
Stakeholder discovery, ML problem scoping, and metric-to-decision mapping are the daily craft of an AI PM at any operations-heavy company.
This challenge sharpens
- stakeholder-framing
- ml-problem-scoping
- prioritization
Applied AI Scientist
Choosing the right metric for the operational decision is what separates applied AI work from textbook ML and is graded in every applied-AI interview loop.
This challenge sharpens
- metric-design
- ml-problem-scoping
- stakeholder-framing
AI Solutions Architect
Producing a sized backlog grounded in stakeholder pain is the entry deliverable for solutions architects scoping ML engagements at consulting firms.
This challenge sharpens
- requirements-writing
- prioritization
- ml-problem-scoping