Intelligent risk management: natural language processing real-time triage of police calls for service

Abstract

Can an intelligent call center improve the deployment of a safe and effective diversified response (e.g., differential police response, coresponse and Alternate First Responders)? This article examines a proof-of-concept intelligent call center for enhanced 911 call processing, at the City of Seattle (Washington, USA). This study employed common commercial technology to 1) transcribe incoming 911 call audio, 2) render a real-time forecast of call risk and 3) visualize the results for personnel handling the call as “intelligent decision support.” This project proves a “human-inthe- loop” application of Machine Learning (ML) can support the professional judgement of experienced human operators with a precise, low-latency forecast of call risk. Further, the demonstrated system is designed to learn. As a diversified response system evolves, statistical feedback is incorporated using the Risk Managed Demand framework. Implications for risk management, the opportunity for diversified response, and the ethics of ML are discussed.