During your session we use cookies such as Google Analytics to understand how you use the service and make improvements.
In March and April 2026, the Yorkshire & Humber Office for Data Analytics (YHODA) took part in the Data & Design Hackathon, held at The Wave, The University of Sheffield. Contributing to current policy debates across Europe, we challenged students to move beyond describing socioeconomic patterns and to use data to inform better regional policy decisions. The hackathon, organised by several academics and students from the School of Information, Journalism and Communication and funded by the Centre of Machine Intelligence at The University of Sheffield, was, as in the previous year, a major success, attracting students from across disciplines.
Led brilliantly by the Senior Lecturer in Data Analytics Suvodeep Mazumdar, we also had the opportunity to learn from IBM Master Inventor John McNamara, who delivered a valuable talk on design thinking. From a local data perspective, one of the main lessons we take away at YHODA is that there is often pressure to find new data, but not enough emphasis on analysing, combining and communicating what is already available to policy decisions.
As our expertise revolves around local and regional data, we proposed two possible projects to the students. One centred on housing archetypes in the city of Sheffield, and the second focused on neighbourhood clustering, also in Sheffield. The first project was designed to examine the housing stock in South Yorkshire’s largest city by using Energy Performance Certificate (EPC) open energy datasets alongside aggregated socioeconomic information. We did not want students simply to map houses with lower energy performance; we also wanted them to answer questions such as:
Which neighbourhoods are most in need of retrofit?
How do housing typologies relate to energy-performance indicators?
We believe that, by following this approach, we can track local stories through data. The students brilliantly uncovered insights into Sheffield’s housing stock, including by using our available Yorkshire Vitality Suite tools, especially the Yorkshire Vitality Observatory, which provides information on 50 indicators over time, and their cross-correlations, for each local authority in Yorkshire. From our perspective, it was also helpful to see how a younger audience used our local data tools and to gather their feedback on our platforms.
The second option, Neighbourhood Futures, focused on the question:
How can we track change in Sheffield’s neighbourhoods and identify early signs of decline, renewal, and opportunity?
Instead of labelling Sheffield neighbourhoods as “good” or “bad” from a static, single-year point of view, which can be ethically misleading and risk stigmatising places, the students uncovered opportunities for several areas of the city that are evolving over time. The broader question of how we imagine Sheffield’s socioeconomic future was also present throughout. Although we provided some basic datasets to the students, including our Yorkshire Vitality Jobs Dashboard, which shows the number of employees by sub-neighbourhoods (LSOAs), industry, and time, there were many datasets to work with and combine. These included official data from the ONS, such as higher-education attendance, and crime data collected by the police, as every incident is collected by postcode. At first glance, an area may seem deprived, but incorporating further variables could reveal resilience or opportunity in certain fields.
Finally, we provided evidence of how we collaborate with Yorkshire local authorities, institutions, and universities, as well as a non-exhaustive list of possible software the students could use: on the back end, mainly Python, R, or Stata; and on the front end, Power BI, Tableau, Plotly, R Shiny, Looker, or Figma, among others.
In a second publication, we will share more of the findings.
