Supply Chain Optimization(24h Datathon)

Project Overview

In a 24-hour datathon, we converted messy GPS shipments into a tractable hub-and-corridor network and ran a prescriptive, multi-objective optimisation (Gurobi MIP) that trades off Cost, On-time, and CO₂. The output is a clear decision story with three executable policies, corridor flow maps, and scheduling lists that managers can act on immediately.

Methods

• Network construction: KMeans clustering yields 12 hubs; each hub connects to its 3 nearest neighbours to form realistic, sparse corridors. This compresses raw points into a computable network while preserving geography.
• Arc coefficients: for every corridor we estimate unit shipping cost (c_ij), expected delay hours (d_ij), a CO₂ proxy from fuel consumption (e_ij = fuel × 3.16 kg CO₂e/L), and capacities — all stored in an optimisation-ready table.
• Prescriptive optimisation: minimise λ₁·Cost + λ₂·Delay + λ₃·CO₂ under supply/demand, flow conservation, capacity, SLA/delay caps, and emission caps. Traverse the frontier either by tuning weights (λ’s) or by imposing hard constraints.
• Policy simulation: switch weights/caps to realise Cost-first, On-time-first, and Low-carbon-first regimes. Under tighter SLA/CO₂ caps, cost rises and some instances become infeasible — the slope of that curve is the marginal cost of stricter targets.

What I Did

• Framed the case as an optimisation problem rather than a pure forecasting task. I broke the business question down into cost, delivery reliability, carbon impact, capacity limits, and route feasibility, then translated these factors into model inputs and constraints.
• Led the optimisation model design and calculation. I defined the objective function, built the corridor-level coefficients, set up the MIP structure in Gurobi, and tested different weight and constraint settings to compare realistic operating policies.
• Connected the model output back to business decisions. Instead of only reporting the lowest-cost route, I helped turn the results into three decision options — Cost-first, On-time-first, and Low-carbon-first — so managers could understand the trade-offs behind each policy.
• Prepared the final decision materials, including policy comparison tables, corridor flow maps, routing schedules, and the storyline explaining why the recommended network was practical under time, cost, and sustainability targets.

Reflection

• Balanced network: small deltas (±~1%) across policies indicate a reasonably balanced corridor system — optimisation still clarifies day-to-day choices.
• From prediction to prescription: GBM/ARIMA (R²≈0) struggled in noisy conditions; prescriptive optimisation turns signals into actions.
• Frontier intuition: tuning λ’s or adding hard caps makes the cost of SLA/ESG explicit — a teachable curve for stakeholders.
• Data → trust: estimating c_ij/d_ij/e_ij from first principles improved explainability and reviewer confidence.
• Stress tests: tightening delay/CO₂ caps surfaced feasibility boundaries early, valuable for scenario planning.
• Story matters: clear maps/tables/schedules + a crisp narrative moved the decision faster than algorithms alone.