Our new series of updates on new studies relevant to policing practice have been published in the last few weeks. In this bulletin the research spans recruitment and organisational fairness, hotspot detection, violence against women and girls, investigative practice, policing technology, officer wellbeing, and the use of artificial intelligence in policing. Below is a selection of recent empirical studies and evaluations with potential implications for policing policy and practice. Have we missed anything? Let us know - coo@sebp.police.uk Police Vetting Decisions and Ethnicity Watson, Katus, Shah, Barnes, Melia & Sutherland Journal of Experimental Criminology (2026) Method:  Randomised vignette experiment with 1,778 vetting decisions by police vetting professionals This study examined whether ethnicity influences police vetting outcomes. Vetting professionals reviewed fictional applicant profiles where ethnicity was randomly varied. Across five of seven scenarios, ethnicity had no statistically significant effect on vetting decisions. However, in two scenarios involving more complex applicant backgrounds, minority ethnic applicants were less likely to be approved. The results suggest that vetting processes are largely consistent, but that bias may emerge when decision-making becomes more ambiguous. Monitoring outcomes and reviewing decision guidance may help ensure consistency in these situations. Tags:  recruitment, organisational fairness, legitimacy Link   A Globally Optimal Algorithm for Hotspot Detection Martin Boldt Crime Science (2026) Method:  Algorithm development and empirical evaluation of 1.75 million crimes across Malmö, Boston and New York This paper introduces a new algorithm designed to identify crime hotspots more effectively than commonly used spatial techniques. Using crime data from three cities, the algorithm captured a larger proportion of crimes within hotspot areas than standard kernel density approaches. The study also presents a faster “greedy” version that approximates the optimal solution while significantly reducing computation time. The approach may offer crime analysts improved tools for identifying priority patrol locations. Tags:  hotspot policing, crime analysis, resource allocation Link Invisible Harms: The Hidden Health Impact of Fraud Skidmore, Halkon, O’Connell, Meenaghan & Button Police Foundation / NIHR (2026) Method:  Survey (n=311) and qualitative interviews Fraud is the most common crime experienced in the UK, yet its health impacts remain poorly understood. This study surveyed fraud victims and conducted interviews across two police force areas. Most victims reported negative health impacts following victimisation, including stress, anxiety and sleep disruption. A substantial proportion reported behavioural changes such as withdrawal from activities, and a smaller group reported severe distress including thoughts of self-harm. The report argues that fraud should be treated as a significant public health issue and calls for policing and support services to recognise the wider harms experienced by victims. Tags:  fraud, victim support, wellbeing Link : Policing Violence Against Women and Girls: Trust and Engagement Aisha K. Gill & Sundari Anitha Policing & Society (2026) Method:  Mixed methods study: 52 police officers in focus groups, 55 case files, body-worn video review This study examines police engagement with racially minoritised victims of violence against women and girls. Researchers found that victims’ needs and expectations were not always fully met, and that inconsistent communication and investigative practices could undermine trust. However, the study also identified examples of promising practice, particularly where officers demonstrated empathy, proactive safeguarding and strong partnership working. The authors argue that improving trust requires both organisational learning and stronger engagement with affected communities. Tags:  VAWG, trust and confidence Link Investigating Intimate Partner Sexual Violence Cassandra Wiener, Andy Myhill & Merili Pullerits Policing & Society (2026) Method:  Qualitative study with practitioner interviews and case analysis This research examines how police investigate sexual violence within intimate relationships. The study argues that these cases are often poorly understood because they sit between domestic abuse and sexual offence frameworks. Forces that approached these investigations through a domestic abuse lens were better able to recognise coercive control dynamics and support victims effectively. The authors suggest that clearer investigative frameworks and training could improve outcomes for victims. Tags:  domestic abuse, sexual violence investigations Link Dynamic Guardianship and Residential Burglary van Sintemaartensdijk, Frerichs, Friehs & de Vries Journal of Experimental Criminology (2026) Method:  Behavioural experiments using virtual-reality burglary scenarios This research explores whether “dynamic guardianship” signals such as automated lighting, smart cameras and self-closing blinds, influence offender decision-making. Participants placed in simulated burglary scenarios responded differently to these signals. Cameras appeared to increase perceived risk, while other cues had weaker effects. The findings suggest that smart-home technologies may contribute to deterrence but should be considered complementary to traditional situational prevention measures. Tags:  burglary prevention, situational crime prevention Link   Measuring Police Burnout Using Brain Monitoring Chen et al. Scientific Reports (2026) Method:  Functional near-infrared spectroscopy (fNIRS) with machine learning Sample:  33 active police officers performing simulated operational tasks. Researchers used brain-imaging technology to measure stress responses in police officers during simulated tasks. A machine-learning model trained on the brain activity data was able to classify burnout levels with high accuracy. Although still experimental, the research suggests physiological indicators may eventually complement traditional self-report measures when assessing officer wellbeing. Tags:  wellbeing, burnout Link Social Media Campaigns and Adolescent Relationship Violence Seddig, Bartz, Bliesener, Rühs, Schauten & Thomsen Journal of Experimental Criminology (2026) Method:  Randomised survey experiment of 1,973 adolescents, 772 follow-up Researchers evaluated a social-media campaign (in Germany) promoting healthy relationships among young people. Participants exposed to campaign videos and audio content demonstrated improvements in knowledge and intentions to seek help. Attitude changes were smaller, but some effects emerged over time. The study suggests digital campaigns may increase awareness but may need to be combined with broader prevention efforts to achieve sustained behavioural change. Tags:  youth violence prevention, digital interventions Link : Natural Language Processing and Police Reports Lukmanjaya, Halmich, Butler, Cook & Karystianis Crime Science (2026) Method:  Scoping review of 61 studies This review examined how natural language processing techniques have been used to analyse police narrative reports. Across the studies reviewed, machine-learning models showed promising performance in tasks such as classifying domestic violence cases and extracting information from incident narratives. However, the authors highlight inconsistent reporting standards and limited discussion of ethical issues. They call for improved governance frameworks and shared benchmarks for applying NLP techniques to policing data. Tags:  AI, policing data, intelligence analysis Link Generative AI and Financial Crime Tiwari, Zhou & Lee Crime Science (2026) Method:  Quantitative systematic literature review (94 studies) This review examines how generative AI is influencing financial crime. The literature shows that offenders are increasingly using AI tools for fraud automation, voice cloning and synthetic identity creation. At the same time, law-enforcement agencies are beginning to apply AI techniques to detect suspicious transactions and identify emerging fraud patterns. The authors emphasise the importance of developing governance frameworks and analytical capabilities to respond to AI-enabled crime. Tags:  fraud, cybercrime, AI Link

The Police Graduate Research Showcase is now open for submissions. The online event, taking place on 6 May 2026 , will showcase high-quality, applied research conducted by police officers as part of the Police Constable Degree Apprenticeship (PCDA) or other policing-related degree programmes. The Showcase is hosted by the National Policing Education Research Hub and supported by the Society of Evidence Based Policing (SEBP) . We are inviting police officers who have completed research with clear practical relevance to policing to submit their work for consideration as speakers at the event. What we are looking for Submissions should be based on completed research that demonstrates practical application and learning for policing. Priority areas include research that supports: Safer Streets Violence Against Women and Girls Trust and Confidence in Policing Research from any other area of policing will also be considered, provided it offers clear operational, organisational, or policy relevance. Selection process and opportunity Applications will be reviewed by a panel drawn from the Higher Education Institutions Research Hub . Successful applicants will be invited to present their research at the online Police Graduate Research Showcase on 6 May 2026 . From these presentations, winners will be selected from each category . Those selected will : Receive a presentation slot at the National Evidence-Based Policing Conference in September 2026 Be shortlisted for the SEBP Emerging Talent Award , announced at the same conference This is a unique opportunity to share practitioner-led research with a national audience and to help shape the future of evidence-based policing. How to apply To submit your research access the submission form here 🗓 Deadline for submissions: 18 February 2026

This opinion piece is one of several I have recently written with the help of generative AI, which I use to organise ideas that have been sitting in my head for too long. The thoughts are mine; the tools help me get the first draft on the page. You should try it. Policing has historically struggled to base practice on rigorous evidence. Decisions were often guided by tradition, instinct, or perceived good practice rather than by robust evaluation or empirical testing. That is changing. Across operational meetings, professional practice forums, multi-agency partnerships, and applied academic conferences, police officers increasingly describe their work as data-informed and evidence-led. There is genuine interest in understanding what works, what does not, and what may cause unintended harm. This shift reflects a maturing profession that values the opportunity to learn from high-quality research and to deploy resources in ways that maximise public safety. At the same time, policing is entering a period of rapid technological expansion. Artificial intelligence has moved from niche analytical applications to a field of general-purpose tools with potentially transformative impacts. Generative AI promises efficiencies, novel forms of insight, and new capabilities for summarising, interpreting and interacting with vast volumes of information. The pressure to adopt these tools is significant. Resources are stretched, demands are rising and diversifying, and governments are actively encouraging police and other public services to explore and harness AI. This makes it more important than ever to draw a clear distinction between being data-driven and being evidence-based. A system that uses data is not inherently grounded in evidence. Data provides a record of what was observed. Evidence tells us if something works, if it is safe, if it is fair, and if it is likely to achieve the outcomes we claim. Too often, technological tools are adopted on the assumption that because they process data, they must be objective and effective. That is a category error. Evidence is established through transparency, scrutiny, evaluation, and replication. Without this, tools that happen to use data run the risk of becoming vehicles for harm. This distinction becomes especially critical where AI is embedded in policing. I am optimistic about the potential of AI. These tools can offer real value if they are deployed within practical governance frameworks, and if their effectiveness and impacts are systematically monitored and evaluated. There are opportunities to improve decision-making, reduce administrative burdens, support investigations, and generate insights that would otherwise be inaccessible. However, without careful evaluation and meaningful oversight, we risk sleepwalking into problems that could set policing back significantly. Ineffective or harmful technologies will damage public trust. They will drain already stretched resources. They will undermine the legitimacy of evidence-based practice. This challenge is further amplified by the speed and scale at which private sector vendors are moving into this space, often marketing powerful systems to forces whose capacity to appraise, test, and monitor what is being sold to them is limited. A single high-profile failure in deploying these new, potentially transformative AI applications could poison the well, making it far harder for genuinely beneficial tools to gain acceptance in the future. The task is therefore to ensure that AI adoption aligns with the principles of evidence-based policing. That means clearly defining the problem a tool is intended to solve; planning evaluations before deployment, not after; running trials and phased testing before scaling; and scrutinising accuracy, bias, operational impacts, proportionality, and public acceptability throughout. It also means learning from other sectors that have already faced similar challenges. Crucially, it means recognising that an AI tool is not evidence-based simply because it happens to use data. AI can genuinely deliver for policing and for society if we treat its adoption as an evidence-generation challenge, not as a procurement exercise. The goal should be to build a future where technology strengthens practice because it has been scrutinised, tested, and shown to work. That is how we avoid repeating past mistakes, protect fragile public trust, and realise the positive potential of AI in the long term. Dan Birks, Professor of Computational Social Science at the University of Leeds Dan is also Deputy Director and Data Science Lead at the ESRC Vulnerability & Policing Futures Research Centre, and Co-Director of the Yorkshire Policing-Academic Centre of Excellence (TYP-ACE), jointly hosted by the Universities of Leeds and York. TYP-ACE is one of nine nationally recognised Policing-Academic Centres of Excellence established by the NPCC and UKRI.

Events No events planned Check back in the future

Briefing, video and summary for the implementation webinar series "Easier Said Than Done" produced by the Society of Evidence Based Policing Easier Said Than Done 1: Deferred Prosecution 10th January 2025 Webinar Easier Said Than Done This webinar series addresses the sticky issue of putting evidence based ideas into practice. In this session, we were joined by four panelists with direct experience of doing Deferred Prosecution in real life. The Briefing Before each webinar, we send people a briefing sheet. You can download this one here . It's got all the background on what Deferred Prosecution is all about and details of the panelists. The Discussion You can view the whole 60 minute session right here: The Summary We've summarised 10 takeaways from the discussion into a handy list. You can download that here . Further information For any more information on Deferred Prosecution or if you would like to chat to any of the panellists, get in touch with us (coo@sebp.police.uk ) and we'll see what we can do!

About us Our mission Read about why we were founded and the core goals that guide us as an organisation. Our people Meet our national executive, regional co-ordinators and trustees. What is EBP? Understand evidence-based policing and the principles that underpin it. Our partners & supporters Learn about the organisations that make our work possible. Global collaboration Learn about our global coalition seeking to build new international networks. Donate Support our mission to make policing more effective, fair and evidence-based. BETA Contact us to help improve this site

In this introductory course, SEBP's Chief Operating Officer, Dr Matt Bland, aims to provide an introduction to the subject and offer a structured approach for further learning about EBP. The program begins with definitions and an overview of the scientific process. It then moves on to how research is put together and teaches tips on how to find and interpret evidence-based papers, the challenges of implementation and how to do EBP in an ethical way. The course is around 8 hours and involves cheat sheet resources, quizzes, and case studies.