About this document

Machine Learning for Crime Hotspot Prediction by k vandana is a document available to read on EtoBox.

This paper compares different machine learning algorithms for predicting crime hotspots using historical crime data from a city in China from 2015 to 2018. The paper finds that an LSTM model outperformed KNN, random forest, SVM, naive Bayes and CNN models at predicting crimes. However, future prediction could be improved by incorporating additional data from criminological theories as covariates along with historical crime data. The proposed system uses random forest, KNN and SVM algorithms to predict crime

Author

k vandana

Language

EN