Ministry of Justice Synthetic Data First Probation Iteration 2, England and Wales, 2014-2023

<div>The Ministry of Justice (MoJ) Data First Synthetic Data Project aims to improve engagement with Data First datasets by making synthetic versions of content available to enable more rapid development of research proposals and to thereby enhance the potential for linked administrative data to improve understanding and outcomes across justice systems. The project has led the development of two components: a dataset generation platform and an initial release of lo-fidelity, synthetic data tables.</div> <p>This study includes a synthetically-generated version of the Ministry of Justice Data First Probation datasets. Synthetic versions of all 43 tables in the MoJ Data First data ecosystem have been created. These versions can be used / joined in the same way as the real datasets. As well as underpinning training, synthetic datasets should enable researchers to explore research questions and to design research proposals prior to submitting these for approval. The code created during this exploration and design process should then enable initial results to be obtained as soon as data access is granted.</p> <p>The Ministry of Justice Data First probation dataset provides data on people <span>under the supervision of the probation service in England and Wales from 2014.  </span><span>This is a statutory criminal justice service that supervises high-risk offenders </span><span>released into the community. The data has been extracted from the management </span><span>information system national Delius (nDelius), used by His Majesty's Prisons and </span><span>Probation Service (HMPPS) to manage people on probation.</span></p> <p>Information is included on service users' characteristics and offence, and on their pre-sentence reports, sentence requirements, licence conditions and post-sentence supervision; for example, age, gender, ethnicity, offence category, key dates relating to sentence and recalls, activities and programmes required as part of rehabilitation (e.g. drug and alcohol treatment, skills training) and limitations set on their activities (e.g. curfew, location monitoring, drugs testing).</p> <p>Each record in the dataset gives information about a single person and probation <span>journey. As part of Data First, records have been deidentified and deduplicated, </span><span>using our probabilistic record linkage package, Splink, so that a unique identifier </span><span>is assigned to all records believed to relate to the same person, allowing for </span><span>longitudinal analysis and investigation of repeat interactions with probation. This </span><span>aims to improve on links already made within probation services. This opens up </span><span>the potential to better understand probation service users and address questions </span><span>on, for example, what works to reduce reoffending.</span></p> <p>The Ministry of Justice Data First linking dataset can be used in combination with <span>this and other Data First datasets to join up administrative records about people </span><span>from across justice services (courts, prisons and probation) to increase </span><span>understanding around users' interactions, pathways and outcomes.</span></p>

<div>英国司法部（Ministry of Justice, MoJ）数据优先合成数据项目（Data First Synthetic Data Project）旨在通过开放内容的合成副本，提升与数据优先数据集的交互效能，推动研究提案的快速研发，进而释放关联行政数据的潜力，以深化对司法系统的认知并优化整体司法成效。本项目已主导开发两大核心组件：数据集生成平台，以及低保真度（lo-fidelity）合成数据表的初始发布版本。</div><p>本研究包含英国司法部数据优先缓刑数据集的合成版本。现已生成英国司法部数据优先数据生态系统内全部43张数据表的合成副本，此类合成数据集可与真实数据集以相同方式进行使用与关联拼接。合成数据集除可支撑模型训练外，还能帮助研究人员在提交研究提案前探索研究问题、设计研究方案。在后续获得真实数据访问权限后，基于该探索与设计过程编写的代码即可快速生成初步研究结果。</p><p>英国司法部数据优先缓刑数据集涵盖2014年起英格兰与威尔士地区接受缓刑监管的人员相关数据。该服务为法定刑事司法服务，负责监管被释放至社区的高风险罪犯。数据源自英国皇家监狱与缓刑服务局（His Majesty's Prisons and Probation Service, HMPPS）用于管理缓刑人员的全国性管理信息系统——国家德柳斯（national Delius, nDelius）。</p><p>数据集涵盖服务对象的个人特征、犯罪情况，以及其审前报告、刑罚要求、缓刑监管条件与刑后监管等相关信息；例如年龄、性别、族裔、犯罪类别、与刑罚及缓刑召回相关的关键日期、康复所需的活动与项目（如药物成瘾治疗、技能培训），以及对其活动设置的限制措施（如宵禁、位置监控、药物检测）。</p><p>数据集中的每条记录对应一名个体及其缓刑监管历程。作为数据优先项目的一部分，研究团队使用概率记录链接工具包Splink对记录进行去标识化与去重处理：为所有被认定为同一人的记录分配唯一标识符，支持对个体开展纵向分析以及对其与缓刑机构的重复交互行为进行研究，该流程旨在优化缓刑机构内部已有的关联逻辑。此举有望助力更深入地认知缓刑服务对象，并解答诸如“何种措施可有效降低再犯率”等核心议题。</p><p>英国司法部数据优先关联数据集可与本数据集及其他数据优先数据集结合使用，将来自司法系统各环节（法院、监狱与缓刑机构）的行政记录进行关联整合，从而深化对服务对象的交互路径、从业轨迹与最终成效的认知。</p>