Techbanq
Logistics

Horizon Logistics Last-Mile Intelligence

A national parcel carrier replaces a 12-year-old rules-based routing engine with adaptive AI optimisation — collapsing per-stop cost and lifting on-time delivery in the same quarter.

Client
National last-mile carrier delivering 2.4M+ parcels weekly
Category
Logistics
Engagement
7-month engagement, regional rollout
Services delivered
AI strategy & implementation, Data & AI systems, Operational intelligence
The Challenge

The challenge

The organisation faced a routing economics problem with a structural cause: the legacy routing engine had been built for a delivery network that no longer existed. When 80% of volume was business deliveries on predictable rounds, the system worked. Now the same network ran majority residential, with cash-on-delivery windows, customer reschedule requests, and a mixed fleet of vans, two-wheelers, and gig drivers. Each operational change had been patched onto the previous one until no one could explain why a particular route had been chosen or how to improve it systematically.

What we found

Discovery

We spent the first four weeks across three depots — Riyadh, Jeddah, Dammam — working alongside drivers and watching dispatch in detail, then reconstructing what actually happened on each route against what the system had planned. The variance was the finding: drivers were silently rerouting around 31% of stops because the system had no knowledge of parking constraints, building access requirements, or the customer time windows the call centre had renegotiated that morning. The routing problem was an information problem.

How we did it

Our approach

1

Routing architecture redesign: replaced the static routing engine with a learning optimiser that ingests live traffic, parking-availability data, customer reschedule events, and per-driver historical performance

2

Dispatch intelligence build: designed and built a single dispatch surface letting the depot supervisor see the optimiser's plan, driver-suggested deviations, and the cost-of-change for any manual override

3

Continuous learning programme: built a model-evaluation pipeline that replays each completed day against the plan and feeds the variance back into the next training cycle — closing the feedback loop the legacy system had never had

4

Phased rollout with change management: rolled out depot by depot with a 21-day stabilisation window in each, so depot managers could develop confidence in the system before committing to it operationally

What we built

The Outcome

The engagement delivered a routing platform that improves week over week from the depot's own delivery data, with a dispatch surface that incorporates the operational knowledge of drivers and supervisors rather than overruling it. Adoption was built through visibility, not mandate — supervisors could see the cost consequence of every change they considered making.

Measured Impact

The results

-19%
Reduction in cost per delivered parcel against the trailing-12-month baseline
+9pp
Improvement in on-time delivery rate, from 84% to 93%
14%
Increase in stops per driver shift with no overtime growth
6 wks
Time from first depot go-live to all-network rollout
“The old system told the drivers what to do. The new one works with them. That is what changed — and the operating numbers followed.”
D
Director of Last-Mile Operations
National Parcel Carrier
Technologies & PlatformsAdaptive vehicle routing with reinforcement-learning feedbackLive traffic and parking-heuristic ingestionDriver and supervisor dispatch consoleDaily replay pipeline for continuous evaluation
Next case studyDelta Container Terminal Yard IntelligenceA deepwater container terminal moves from manual yard planning to AI-assisted stack and crane scheduling — adding effective capacity without pouring concrete.

Next step

Have a project like this?

We would love to hear what you are building. Let us explore how we can help.