Project

Healthcare Routing AI

A routing optimization system for healthcare operations that combines demand clustering with constraint-aware path planning.

This project reflects how Mohammed Rafique Kuwari approaches AI automation engineering: define the operational bottleneck, design a reliable data flow, and build outputs that are useful inside real business systems.

Business problem

Manual route planning could not efficiently handle changing demand, service windows, and resource constraints.

Approach

Modeled operational constraints including time windows and capacity limits.
Applied clustering to reduce route complexity and improve assignment quality.
Used CVRP-style optimization with domain-specific penalty tuning.
Built scenario simulation tools for planners to compare route strategies.

Tech stack

PythonOR-ToolsGeo APIsPandasLLM-assisted analytics

Architecture highlights

Demand preprocessing and geospatial normalization
Clustering and route candidate generation
Constraint-aware optimization engine
Planner dashboard with scenario comparison

Expected value

Enabled more efficient route planning and better decision support for healthcare logistics teams.