Several studies have been conducted based on utilizing local crime data to explain racial disparities and differences in fatal police shootings. We use data mining and machine learning techniques to incorporate more factors rather than only crime data. This paper is available on arxiv.org under CC BY-NC-ND 4.0 DEED license.
WP fatal police shooting dataset insight
Fatal police shooting rate and victims race prediction
Several studies have been conducted based on utilizing local crime data to explain racial disparities and differences in fatal police shootings. Mentch (2020) [8] implemented resampling procedures to take factors like local arrest demography and law enforcement density into account. He found substantially less racial disparity after accounting for local arrest demographics.
On the contrary, Ross (2015) [9] built a multi-level Bayesian model to investigate the extent of racial bias in the recent shooting of civilians by police. He concluded that racial discrimination observed in police shootings is not explainable due to local-level race-specific crime rates. Noticeably, Mentch and Ross had reached contradictory conclusions. But they inspired us to use data mining and machine learning techniques to incorporate more factors rather than only crime data to understand fatal police shootings in the US better.