Prognostication of Crime Using Bagging Regression Model

Abstract

Crime is a social and economic problem that affects a country's quality of day-to-day life and economic growth. However, analyzing and forecasting crime is not a straightforward job for a law enforcement investigator to manually unravel the underlying nuances of crime data. To make this process easier and more automated, the authors present a machine-learning model for crime analysis and predictions. The authors used a London crime dataset and enhanced the data set by incorporating population density, percentage of economically inactive working age, and average monthly temperature. The pre-process step prepares the raw data and makes it suitable for the machine-learning model. Bagging and boosting ensemble techniques were used to find a better- machine-learning model. GridSearchCV was used to tune hyperparameters to find the best-performed model. Parameters were tuned as an iterative processes. Eventually, the researchers compared all the algorithms and selected the Random Forest bagging regression model as the best-performed algorithm.