Analyzing Mass School Shootings in the U.S. from 2019 to 2024 with Machine Learning

Public safety is vital to every country, especially school safety. In the United States, students and educators are concerned about school shootings. There are critical needs to understand the patterns of school shootings. Without this understanding, we cannot take action to prevent school shootings. Existing research that includes statistical analysis usually focuses on public mass shootings or just shooting incidents that have occurred in the past and there are hardly any articles focusing on school mass shootings. Here we firstly evaluate mass school shootings events for 26-year (1999-2024). Compared with the number of mass school shootings in COVID-19 period, we predict the number of mass school shooting events in the US will be reduced through four machine learning models. We also identify that mass school shootings usually take average 31 minutes with Preparation Stage (15 mins), Attack Stage (three mins), Response Stage (four mins), and Aftermath Stage (24 mins). The annual probability of mass school shootings is 1.23×10<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">−5</sup> (or one in 81,604) per school. The shootings mostly occur inside buildings, specially classrooms and hallways. By interpreting these data and conducting various statistical analysis, this will ultimately help the law enforcement and schools to reduce the future school shootings. The research data sets could be downloaded via the website: https://publicsafetyinfo.com