Case study

How GXO is transforming logistics using data & AI

1-2%

basic cost savings

compared to industry standard tools

10%

cost savings with constraint flexing

retailers helped

The upshot

How AI is revolutionising logistics

Datasparq developed an AI-powered vehicle route optimisation tool for GXO that delivers significant cost savings—between 1-2% against the industry-standard Paragon baseline and up to 10% with additional constraint flexing.

What began as a targeted proof-of-concept has evolved into a comprehensive solution deployed across multiple sectors including grocery, hospitality and retail. The optimiser has transformed GXO's approach to transport planning, delivering substantial annual savings for major retailers while providing additional benefits like improved operational stability, better peak period management and enhanced contingency planning capabilities.

Key benefits:

Cost savings of 1-2% against industry standard tools, up to 10% with constraint flexing
Successfully implemented across grocery, hospitality and retail sectors
Improved operational stability and contingency planning
Enhanced peak period management
Reduced environmental impact through more efficient routes

Datasparq's route optimiser

The opportunity

Breaking the planning bottleneck

For retailers partnering with logistics leaders like GXO, transport networks represent one of the most significant operational costs. Planning efficient routes is enormously complex—requiring planners to juggle countless variables within tight timeframes. The traditional approach demanded significant manual trial-and-error, severely limiting the potential improvements that could be discovered.

GXO recognised that addressing this challenge required a fundamentally different approach using artificial intelligence. They needed a solution that could generate more efficient schedules, handle complex constraints, and work across diverse customer networks—all while delivering tangible benefits to their retail partners.

With rising fuel costs and increasing pressure to reduce carbon emissions, the stakes were particularly high. Any solution would need to deliver measurable cost savings while maintaining or improving service levels across different sectors.

The challenges we faced:

Complex planning processes with numerous constraints
Limited schedule exploration with traditional tools
Rising transport costs affecting retailers
Need for consistent, objective schedule creation
Increasing sustainability demands

The solution

Exploring thousands of potential routes every second

We developed a vehicle route optimiser capable of processing thousands of schedule iterations per second during overnight runs—tasks that would take human planners months to accomplish manually. The system handles complex constraints while incorporating advanced features like wait time optimisation and delivery compactification.

Testing the concept

Our journey began with a supermarket depot where even our basic prototype beat industry standards. Transport leaders were impressed by a solution that outperformed their existing software from the start.

Proving it in action

We took on a major retailer's busiest depot, trying new approaches to deliveries and time windows. The results spoke for themselves—yearly savings that continue today and have made a real difference to their bottom line.

Expanding its capabilities

Next came a tougher challenge—a network with many depots, union drivers, and two-person deliveries. The system handled it all, showing it could work with any operational setup.

Achieving scale

We started to turn our project into a platform that works for more retail networks by making the data handling consistent. When we added it for a home improvement retailer, new features like wait time and delivery bundling doubled its performance.‍

1. Proof of concept

First testing with a supermarket depot demonstrated capabilities beyond established industry tools, impressing transport leadership with performance that surpassed existing SaaS solutions.

2. First deployment

Applied to a major retailer's largest and most complex depot, exploring delivery types and time window flexing. This phase delivered substantial annual savings that continue to benefit operations today.

3. Extended capabilities

Extended to a more challenging network with multiple depots, handling unionised workforces, two-person deliveries and a wider variety of vehicle types. This phase demonstrated the optimiser's adaptability to different operational constraints.

4. Enterprise-ready

Standardised data formats and pipelines to create a system applicable across diverse customer networks, with further optimisation for a home improvement retailer adding wait time and compactification features that doubled performance.

Interactive example

Try it for yourself

Explore how the science works in this PlayML data science notebook

The impact

For people, the planet and profit

The optimisation solution has delivered transformative results across multiple dimensions, creating value for both GXO and their retail partners.

A major supermarket has realised significant annual savings for consecutive years, while enjoying more stable schedules that reduce missed delivery windows. The system has particularly proven its worth during challenging peak periods—where intelligent load balancing between depots helps maintain service levels despite increased volume.

In just one implementation, the optimiser helped save over 720 tonnes of CO2 emissions and 250,000 litres of fuel through substantial reductions in miles driven. These impressive results from a single depot demonstrate the enormous potential when deployed across multiple retailers and distribution networks.

Key impacts:

Significant annual savings for major retailers
720 tonnes of CO2 and 250,000 litres of fuel saved in a single implementation
More stable and reliable delivery schedules
Enhanced service during peak trading periods
Data-driven decision making replacing subjective scheduling
Better strategic planning through scenario modelling

If you're interested in exploring how we could help you improve your operations, get in touch.

Call us when you're ready

Work with us

Join our team

Say hello