Page 85 - Procurement guidelines for smart sustainable cities - A U4SSC deliverable

It is also essential to guarantee that digital products and service purchased within smart/sustainable
environment (cities, villages, communities) are digitally accessible (in line with the ICT accessibility
guidelines, principles and standards) to ensure that are inclusive to all its intended users. This is
critical to avoid increasing the digital divide (since all services are supposed to be primarily available
in digital formats) and ensure that the smart/sustainable cities are inclusive for all people.

The ITT did not specify AI but focused on the use of technologies that would deliver the most
effective outcomes. The aim of the procurement was to contract for digital services and capabilities
that would help the DVSA team identify and deploy the right tools and systems to address the
delivery challenges of improving the inspection of authorized garages that conduct MOTs.

The project started with a set of mini discoveries the insights from which would help the DVSA to:

• improve the quality of MOTs by better supporting testers;

• know which garages presented the greatest risks of testing poorly;
• identify those applying to be involved in MOT that may present risks to the integrity of the MOT
service.

As the DVSA did not have labelled data it used unsupervised machine learning, where a computer
finds patterns in data without any prior information about what it should be looking for. In
collaboration with supplier partners, the DVSA applied a “Local Outlier Factor” clustering model
against garage test data from a three-month period.

Figure 25: Examples of different shapes of data clusters

Procurement guidelines for smart sustainable cities | May 2023 71