A Graph-Based Method for Identity Resolution to Assist Police Force Investigative Process

The ability to prove an individual identity has become crucial in social, economic, and legal aspects of life. Identity resolution is the process of semantic reconciliation that determines whether a single identity is the same when being described differently. This paper introduces a novel graph-based methodology for identity resolution, designed to reconcile identities by analysing the similarity of attribute values associated with different identities within a policing dataset. The proposed methodology employs graph analysis techniques, including centrality measurement and community detection, to enhance the identity resolution process. This paper also presents a new identity model for identity resolution. SPIRIT policing dataset was used for testing the proposed methodology. This dataset is an anonymised dataset used in SPIRIT project funded by EU Horizon. It contains 892 identity records and among these, two 'known' identities utilize different names but actually represent the same individual. The presented method successfully recognised these two identities. Additionally, another experimental evaluation was conducted on a refined and extended version of the dataset and the false identities were successfully detected. This method can assist police forces in identifying criminals and fraudsters using fake identities and has applications across finance, marketing, and customer service.