PSMA Programme aids policing through applied modelling and data science

In 2020, the NIHR Applied Research Collaboration for the South West Peninsula (PenARC) piloted the Police Service Modelling Associates (PSMA) Programme. This programme has taught Devon and Cornwall Police analysts a range of computer modelling and data science skills to help further inform their policing work in-house. 

The Context

In 2016, PenARC launched the Health Service Modelling Associates (HSMA) Programme. Here, NHS staff learn data analytics and computer modelling skills to address essential questions within their organisation. 

Following the success of the HSMA programme and the increased interest in modelling solutions for organisational problems, PenARC wanted to open the programme up to a cohort of policing staff to help them tackle issues in policing and wider health systems. 

Delivered in partnership with the Devon and Cornwall Police, and with funding from the University of Exeter’s Policing Lab Fund, this became the PSMA project through a successful bid by Dr Daniel Chalk, Senior Research Fellow in Applied Healthcare Modelling and Analysis, PenARC, University of Exeter and Gavin Bardsley, the then Head of Performance and Analysis at Devon and Cornwall Police.

The programme aims to improve health and policing outcomes by increasing the volume and quality of research in the South West, providing them with evidence-based solutions. 

The Programme

The programme is split into two phases. Phase One takes the cohort through three months of training in Operational Research and Data Science techniques. They acquire skills in programming, learn a range of modelling and forecasting methods, and develop knowledge of Artificial Intelligence approaches.

Attendees are also supported to develop a project proposal that addresses an issue of importance for their organisation and will lead to a significant impact. At the end of Phase One, PSMAs pitch their proposal and a number are selected to be taken forwards as projects in Phase Two. 

During the second phase, attendees receive ongoing mentoring. They get support from an experienced academic and organisational supervision from their PSMA Workplace Supervisor, helping them develop their project and lead a research team. 

One of the selected proposals was the Devon and Cornwall Police project, ‘Using Network Analysis to Better Understand the Relationships Between Offenders and their Victims.’ 

Fiona Bohan, Performance and Analysis Manager at Devon and Cornwall Police, commented on the project: “The need for Social Network Analysis is clear. Criminal and exploitative networks are a huge and costly issue for police, partner agencies and the community.

“Social Network Analysis, using minimal resource, can identify children at current and future risk of exploitation, as well as those key players within the network who pose the greatest risk. By targeting and removing these key players and concentrating limited, early intervention resources on protecting those at stake in the future, there are potentially significant savings in terms of child harm and partnership spending. 

“This proof of concept has highlighted the significant benefits of embedding this approach in force and, in my view, will play an important part in policing in the future.”

The Impact

During the PSMA Programme, they realised that operational policing issues share many similarities with those in health and social care and therefore benefit from the same approaches. There is also a huge appetite and enthusiasm for adopting these methods in supporting policing analytics. 

Due to this, PenARC will permanently integrate the HSMA and PSMA programmes, developing collaborative project opportunities between health, social care and policing. 

With the project’s growth, the training programme now offers over 140 hours of training content spanning across nine modules. The current round of the programme has been opened up to the whole of England and is currently supporting 80 associates. 

Dr Daniel Chalk, Lead for the Programme, said: “We’re incredibly excited to be offering our highly successful HSMA programme to anyone working in health, social care and policing organisations in England. 

“Over the last five years, the work of the HSMAs in the South West has led to significant real-world impact for services and their patients and led to a transformative generational leap in the skills of analysts. By expanding the reach nationally, the programme aims to tackle some of the key national issues faced by health, social care and policing organisations across the country in the wake of the COVID-19 pandemic. 

“We look forward to seeing national collaborative projects in action that can make a real difference, help rebuild our services, and tackle system-wide issues.”

Background

Dr Daniel Chalk is a Senior Research Fellow in Applied Healthcare Modelling and Analysis in the NIHR Applied Research Collaboration for the South West Peninsula (PenARC), based in the University of Exeter Medical School. Dr Chalk’s primary role is leading the HSMA Programme, but he also has interests in Discrete Event Simulation, behavioural modelling using Agent-Based Simulation and Natural Language Processing to automate the extraction of information from free text. Dr Chalk is a Computer Scientist by background and has experience in ecological modelling from his PhD in Biosciences – both studied at the University of Exeter.

Gavin Bardsley is currently seconded to the Performance Management Coordinating Committee to develop the capacity and capability of analysis and performance management within policing. Gavin has 20 years of police staff career development, starting out as a Forensics Intelligence Analyst at West Midlands Police before moving to Devon and Cornwall Police in 2007. Since then, he has progressed in roles within the Performance & Analysis Department and was Head of Department at the time of this project. He commenced a MSt. Degree in Applied Criminology and Police Management at Cambridge in 2019 and graduated in October 2021.

For more information please contact: