• Souglman Kabirou Kanlanfeyi
• Keshav Kishore

Defined as an action or omission which constitutes an offence and is punishable by law, the crime is a phenomenon that is the heart of the authorities and whose measures are very adequate are taken to reduce or stop. Some predictions can be made in order to detect and prevent by using machine learning algorithms such as Regression algorithms and Classification or by using Deep Learning with Recurrent Neural Networks. In this document, after doing a multivariate analysis of different important features affecting occurrence of crime, we will first use a classic machine learning classification algorithm which is Random Forest and then introduce a classification model based on Neural Networks with the Keras framework and its KerasClassifier wrapper provided by Google. In order to increase the quality of the network by find the optimum combination of Hyperparameters, Grid Search CV method will be used. The Neural Network architecture that will be considered is the Recurrent Neural Network with the Long Short Term Memory technique. The objective is to compare the performances of these techniques used for the prediction of crimes by giving a comparison table and difference confusion matrices. The output of our study showed that Deep Learning Architectures especially LSTM techniques takes the lead over other ones on predicting type of crime by considering date and location information.

Crime Prediction, Machine Learning, Deep Learning, RNN, LSTM

"USING MACHINE LEARNING AND RECURRENT NEURAL NETWORKS FOR EFFICIENT CRIME DETECTION AND PREVENTION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.395-402, June 2019, Available :http://www.jetir.org/papers/JETIR1906K45.pdf

"USING MACHINE LEARNING AND RECURRENT NEURAL NETWORKS FOR EFFICIENT CRIME DETECTION AND PREVENTION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp395-402, June 2019, Available at : http://www.jetir.org/papers/JETIR1906K45.pdf