Criminalytics

Machine learning is proving to be a powerful tool in the fight against gun violence. A recent study from the National Bureau of Economic Research (NBER) demonstrates how predictive algorithms can identify individuals at high risk of being shot, enabling targeted interventions that could prevent victimization. By analyzing arrest and victimization records for nearly 644,000 people in Chicago, researchers trained…

Gun violence clearance rates have been dropping for decades, but a new approach is helping turn the tide. Crime Gun Intelligence Centers (CGICs) are revolutionizing how law enforcement solves and prevents shootings by leveraging real-time data and collaboration across agencies. These intelligence hubs use ATF tools like NIBIN, which links shell casings to firearms across crime scenes, and eTrace, which…

The Energetic Materials Research and Testing Center (EMRTC) in Socorro, NM, is revolutionizing law enforcement training by integrating Virtual Reality (VR) into its explosive threat preparedness programs. With the installation of a 3,500-square-foot V-Armed VR system, first responders can now train in realistic, immersive environments to identify and handle explosive devices safely. A key course, Initial Law Enforcement Response to…

A new study explores how Explainable Machine Learning can predict and analyze homicide clearance rates across the U.S. Using data from the Murder Accountability Project, researchers tested nine algorithms, with XGBoost emerging as the most accurate. The study also employed SHAP (a tool for AI explainability) to reveal key factors affecting case resolution, including victim demographics, weapon type, and crime…

Mesa Police are using infrared technology in their helicopter to track and capture fugitives in real time. In a recent case, officers swiftly arrested a suspect who had exposed himself at Skyline Park in east Mesa. As the suspect fled into a residential area, the infrared camera detected his heat signature—even when he attempted to hide in a trash can.…

Researchers have developed a Partially Generative Neural Network (PGNN) to enhance the classification of gang-related crimes, even when crucial data is missing. Traditionally, law enforcement officers manually analyze crime reports, suspect affiliations, and contextual details to determine gang involvement—a time-consuming and resource-intensive process. PGNN aims to automate this classification by generating missing data and making accurate predictions based on available…

Fairfield Police Department in Maine is revolutionizing drug detection with the TruNarc Handheld Narcotics Analyzer, a cutting-edge device that ensures safer and faster identification of narcotics. The device uses a laser to scan substances through their packaging, eliminating the need for direct handling and reducing officers’ exposure to dangerous drugs. With a database of over 400 substances, TruNarc can quickly…

Researchers from BRAC University and SINTEF Digital have introduced a groundbreaking hybrid AI model to detect stalking in real time using video footage. This advanced system combines CNN, LSTM, and MLP technologies to analyze facial landmarks, head movements, and spatial distances, achieving an impressive 89.58% accuracy. The approach addresses the alarming issue of physical stalking, often a precursor to serious…

The Colorado Springs Police Department (CSPD) has upgraded its body-worn camera systems with cutting-edge AI technology from Axon, aiming to enhance officer efficiency and reduce response times. This $2.5–$2.6 million annual investment, funded by grants and city revenue, features AI-powered auto-transcription to cut report writing time by 50–75%. Officers still review and verify reports to ensure accuracy, but the faster…

A new study from Purdue University and the University of Chicago introduces an innovative framework combining machine learning (ML) and queueing theory to enhance the management of incarceration-diversion programs. These programs aim to reduce recidivism by addressing root causes such as substance use and mental health issues. The research focuses on optimizing program size and staffing through a Decision Support…