London’s Queen Elizabeth Olympic park using AI for better planning

From policy goals to KPIs

Policy makers, stacked with bold, innovative policies for our cities, often find themselves without KPIs. This proves problematic for numerous reasons. It makes transparency and accountability more difficult, leverage for policy-making and resource-allocation more scarce, and benchmarking less rooted in fact. Even with KPIs on hand, the process of creating them is often costly, requiring extensive surveys, and their quality is often dubious.

Specific questions, specific answers

In 2021, our urban research and innovation lab worked with Fyma to develop KPIs for the London Legacy Development Corporation (LLDC), the planning authority for the Queen Elizabeth Olympic Park. By using Fyma’s platform, we were able to develop KPIs that would have otherwise been too laborious – and indeed, in most cases, simply impossible – to extract data for. The cooperation made the power of Fyma’s platform plain to see: KPIs grounded in real data are required to address real questions, and Fyma’s platform provides real data, live, spatially, and at scale. This meant a new – and welcome – approach to urban analysis, one in which strategic KPIs were grounded in moving, dynamic, but now, thanks to Fyma, measurable urban data.

With access to approximately 30 cameras, the coverage of areas surrounding the Queen Elizabeth Olympic Park was extensive. This meant that specific, strategic questions about the use of spaces in the area could be asked and answered.

For example, one of the goals of the LLDC was to understand the modal share of specific areas. With the modal share KPI, we knew that vehicles accounted for 67.7% of traffic, and active mobility for the rest. But thanks to Fyma’s platform, we could get even more exact. For example, we could look at the London Stadium area, a cluster of cameras, at specific times. The only times in which pedestrian activity came close to vehicular activity in the area were weekends, where certain activities – football matches, particularly after August – attracted large crowds.

Another goal was to understand patterns of traffic along a local school’s access road in order to address concerns of road safety. Leveraging the granularity of Fyma’s data, we could, for example, look specifically at the modal share KPI during the start of the summer holiday at the school. This allowed us to make the trivial – but otherwise difficult and costly – an observation that the start of the summer period coincided with both an increase in the modal share and a decrease in the volume of cars, with the exception of Saturday, at the school.

The efficacy of understanding how space is used

These were two examples of the kind of questions that we could ask and the kind of answers that we could extract with our KPIs. To be sure, the KPIs that we developed and continue to develop together make it possible to understand, in detail, how spaces are used: during weekends, during summer holidays, at night, in response to restrictions and reopenings. They shed a fresh, direct perspective on a tired – but crucial – question: how best to allocate resources and make policy to better serve strategic goals? Fyma’s novel, exacting, GDPR-compliant data, packaged as strategic KPIs, is the ultimate leverage when attempting to answer it. It promises to make well-intentioned, human-centric policy-making toward our cities more tenable than ever before.

This article was written by our collaboration partner SPINUnit – https://spinunit.org/

Get started
Your request has been submitted!
Something went wrong! Please try again later.
Ready to chat?

See how Fyma can help you gather accurate occupancy insights right from the start.

Object detection
and recognition


Specific location