S10 / Logistics and supply chain
Delivery sequencing that combines optimization and driver experience
A last-mile operator needs feasible routes that balance travel efficiency with practical delivery order. Test whether learning from historical high-quality routes improves a constraint-based routing baseline.
Planned topic
Proposed design & source
Constrained routing; learning-to-rank; inverse-optimization ideas
Use the provided travel-time matrix, stop/package features and documented constraints. Compare nearest-neighbor and classical local-search baselines with learned sequence preferences inside a constrained routing solver. Preserve an untouched route-level benchmark split and use station holdouts as a transfer test where feasible.
Evaluation: Use the official sequence-quality metric, constraint-violation counts, supplied travel-time totals and computation time. Ablate learned preferences and test travel-time perturbations. Show when a shorter route deviates from expert order rather than treating historical behavior as a globally optimal solution.
Boundary: Locations are obfuscated and route labels do not measure realized wage or fuel savings. Show geographic displays as schematic when appropriate and keep cost conversions explicitly assumed.
Amazon Last Mile Routing Research Challenge ↗
S11 / Logistics and supply chain
Delivery promises and early exception prioritization
An e-commerce operations team needs to identify orders likely to miss their delivery promise early enough to respond. Estimate both lateness probability and a delivery-time distribution at order approval.
Planned topic
Proposed design & source
Quantile boosting; survival/competing events; capacity-aware triage
Join orders, items, seller information and coarse origin/destination geography with explicit grain checks. Use only fields available at approval; compare quantile boosting with a censoring-aware time-to-delivery model. Separate cancellation from delivery rather than treating undelivered orders as on-time.
Evaluation: Use chronological order holdouts and seller-held-out checks. Compare against the promised date and historical lane medians. Report interval coverage, late-order precision/recall at queue capacity and regional calibration; treat later reviews as outcomes, never predictors.
Boundary: The data do not show the causal effect of proactive contact or expedited shipping. Respect the dataset's noncommercial/share-alike terms and avoid publishing raw customer records.
Brazilian E-Commerce Public Dataset by Olist ↗
S12 / Logistics and supply chain
Regional freight resilience under capacity shocks
A supply-chain planning leader must understand dependence on particular corridors, modes and regions. Identify where a disruption concentrates exposure and compare hypothetical diversification plans.
Planned topic
Proposed design & source
Network flows; robust optimization; CVaR stress analysis
Build a commodity-specific origin-destination flow network from a pinned FAF release. Distinguish estimated base-year flows from projections. Formulate an interregional transportation problem with explicitly assumed modal capacities, transfer penalties and demand scenarios; add physical infrastructure data only as a separately documented extension.
Evaluation: Compare current shares, proportional diversion and optimized diversification under the same scenarios. Verify conservation and feasibility; report unserved tonnage, concentration and scenario cost. Test rank stability across releases and commodity definitions; validate projections against later observations only where comparable vintages exist.
Boundary: FAF is an estimated aggregate flow system, not shipment traces or a physical road network. Capacity, rerouting feasibility and costs cannot be inferred from tonnage alone.
Freight Analysis Framework ↗
