Machine learning prediction of law enforcement officers' misconduct with general strain theory

Abstract

The main objective of this study is to develop a machine learning prediction model on employee misconduct that signals the failure of the integrity of law enforcement officers in performing their duties and responsibilities. Using a questionnaire survey of two hundred eighty-six participants, from senior officers to rank and file police officers, this study presents the fundamental knowledge on the design and implementation of a machine learning model based on four selected algorithms; generalized linear model, random forest, decision tree and support vector machine. In addition to demographic attributes, the performance of each machine learning algorithm on the employee's misconduct has been observed based on the attributes of general strain theory namely financial stress, work stress, leadership exposure, and peer pressure. The findings indicated that peer pressure was the most influencer in the prediction models of all machine learning algorithms. However, random forest is the most outperformed algorithm in terms of prediction accuracy.