Prioritize a new warehouse proposal with data

Stakeholders are deciding whether to construct a new fulfillment center (FC). You have incomplete data: daily demand by metro area, existing FC capacities and variable cost per FC, average delivery time as a function of distance, and lease/CapEx alternatives. 1) Lay out the end-to-end analysis plan for recommending build vs. lease vs. defer: the demand forecasting approach, service-level targets, network optimization objective (for example, minimize total cost while meeting 95% next-day coverage), and the main constraints. 2) Present a back-of-the-envelope model with stated assumptions to estimate five-year NPV, including cannibalization and ramp curves. 3) Describe the experiment or quasi-experiment you would run before committing (geo holdouts, incrementality through synthetic control, or simulation using historical replays), along with success metrics and stopping rules. 4) Give a sensitivity analysis: which three parameters create the greatest risk to the decision and how you would constrain them with more data. 5) Draft a one-slide stakeholder narrative containing the recommendation and the top two risks with mitigations.

Overview: This question tests demand forecasting, network optimization, five-year NPV financial modeling, experiment and quasi-experiment design for incrementality estimation, sensitivity analysis, and stakeholder communication in the analytics and experimentation area for data science roles focused on warehouse/fulfillment center decisions.