Applying Analytics to Fireground Rescue: Identifying Effective Strategies Through Large-Scale Data

Abstract

This study applies advanced analytical techniques to examine firefighter rescue operations using a large-scale dataset of real-world incidents. The purpose is to identify effective strategies that enhance operational performance and improve life-saving outcomes on the fireground. Drawing on firsthand reports from firefighters involved in actual rescues, the study analyzes 5,074 documented incidents, representing over 250,000 data points collected as of January 1, 2026. The dataset captures a wide range of variables, including incident conditions, environmental factors, victim characteristics, and tactical decisions. Using quantitative methods, the analysis identifies patterns, key predictors, and relationships associated with successful rescue outcomes. Particular attention is given to decision-making under high-risk conditions, resource allocation, and timing of interventions. To ensure data quality, the Firefighter Rescue Survey (FRS) has undergone multiple iterations over a six-year period, improving reliability and relevance while incorporating practitioner feedback. Although some variables reflect smaller subsamples due to survey evolution, the dataset remains robust for large-scale analytical assessment. Findings from this study contribute to the development of evidence-based practices in fireground operations by translating complex data into actionable insights. The results have implications for firefighter training, operational planning, and policy development, ultimately supporting improved efficiency, reduced risk, and enhanced survival outcomes in emergency response environments