Bohea

From chaotic backtracking to clean neighborhood sweeps

A vehicle-routing optimizer for multi-day delivery across Montreal, built on Google OR-Tools, with constraints that encode how good drivers actually work.

PythonGoogle OR-ToolsConstraint ProgrammingFolium / LeafletGIS Visualization

The problem

Naive shortest-path routing produces plans that look optimal on paper and feel insane behind the wheel: the route zig-zags between distant neighborhoods, doubles back late in the day, and lets the "return home" leg drag afternoon stops in random directions. Drivers ignore plans like that — which means the plan is worthless.

The constraint

The optimizer had to respect three things standard VRP formulations don't give you for free:

The solution

Proof: see it, don't take my word for it

Baseline route: chaotic criss-crossing paths across the city
Baseline (shortest-path): criss-crossing, backtracking, neighborhood-hopping.
Optimized route: clean sequential sweeps through each district
Optimized: sequential district sweeps a real driver would actually follow.

Delivered as a runnable repository: solver, mock-data generator, baseline-vs-optimized comparison script, interactive GIS map, and a print-ready PDF report. Anyone can reproduce every figure with two commands. You don't have to take my word for the maps above either: the interactive version is live — pan it, zoom it, follow a single vehicle's route.  Open the live map →  ·  Code →

Where else this applies

Field-service scheduling, last-mile delivery, sales-territory planning, technician dispatch. Any operation where "the math says drive across town twice" costs you real fuel and real morale.

If a machine you build needs an interface, a device connection, or data that has to land somewhere else, tell me what it's costing you now. You'll get an honest read on whether it's solvable, and usually something running to look at. Start here →

← All case studies