Crime Analysis and Forecasting Using Machine Learning

Year 2023, Volume: 2 Issue: 2, 270 - 275, 27.12.2023

Aslınur Doluca Horoz , Hilal Arslan

Abstract

Crime is one of the most common and alarming attitudes all over the world. The number of crimes is increasing day by day, which affects the life of people negatively. Thus, analyzing and preventing crime is a crucial task. With the advent of developing new technologies, machine learning methods reach admirable performance in all fields of crime prediction. Accurate prediction of crime that may arise in the near future can help police units prevent crime before it happens. The ability to forecast any crime based on location may aid in obtaining useful information regarding strategic perspective. Therefore, the analysis and prediction of the crime are significant in identifying and diminishing future crimes. In this study, we apply various machine learning algorithms to predict where crime will take place to prevent future crimes as well as diminish crime rates in society. For this purpose, we perform decision tree, k-nearest neighbor, support vector machines, neural networks, logistic regression, and ensemble learning methods. The dataset used in this study includes 49030 samples with 12 attributes including the borough of arrest, the date of the criminal's arrest, offence description, sex, age as well as race information, coordinates, etc. Historical data on different crimes that took place in 2019 in New York State, published by the NYPD, is used. When the results are evaluated in terms of time and accuracy, decision tree methods achieved higher performance in 2 seconds with an accuracy of about 99.9. To sum up, awareness regarding risky locations aids police units to predict future crimes in a definite location.

Keywords

crime prediction, crime analysis, machine learning

References

• Chun, S. A., Avinash Paturu, V., Yuan, S., Pathak, R., Atluri, V., R. Adam, N. (2019, June). Crime prediction model using deep neural networks. In Proceedings of the 20th Annual International Conference on digital government research (pp. 512-514). doi: https://doi.org/10.1145/3325112.3328221
• Dietterich, T. G. (2000, June). Ensemble methods in machine learning. In International workshop on multiple classifier systems (pp. 1-15). Springer, Berlin, Heidelberg. doi: https://doi.org/10.1007/3- 540-45014-9_1
• Gardner, M. W., Dorling, S. R. (1998). Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences. Atmospheric environment, 32(14-15), 2627-2636. doi: https://doi.org/10.1016/S1352-2310(97)00447-0
• Jain, V., Sharma, Y., Bhatia, A., Arora, V. (2017). Crime prediction using K-means algorithm. GRD Journals-Global Research and Development Journal for Engineering, 2(5), 206-209. https://grdjournals.com/uploads/article/GRDJE/V02/I05/0176/GRDJEV02I050176.pdf
• Llaha, O. (2020). Crime Analysis and Prediction using Machine Learning. In 2020 43rd International Convention on Information, Communication and Electronic Technology (MIPRO) (pp. 496-501). IEEE. doi: https://doi.org/10.22214/ijraset.2023.50310 NYPD Arrests Data Historic 2006 - 2020, List of every arrest in NYC going back to 2006 through the end of the year 2020. [Online]. Available: https://www.kaggle.com/datasets/okettaeneye/nypdarrests-data-historic-2006-2020
• Rish, I. (2001, August). An empirical study of the naive Bayes classifier. In IJCAI 2001 workshop on empirical methods in artificial intelligence (Vol. 3, No. 22, pp. 41-46). https://www.cc.gatech.edu/home/isbell/classes/reading/papers/Rish.pdf
• Safat, W., Asghar, S., Gillani, S. A. (2021). Empirical analysis for crime prediction and forecasting using machine learning and deep learning techniques. IEEE Access, 9, 70080-70094. doi: https://doi.org/10.1109/ACCESS.2021.3078117
• Song, Y. Y., Ying, L. U. (2015). Decision tree methods: applications for classification and prediction. Shanghai archives of psychiatry, 27(2), 130. doi: https://doi.org/ 10.11919/j.issn.1002-0829.215044
• Tamir, A., Watson, E., Willett, B., Hasan, Q., Yuan, J. S. (2021). Crime Prediction and Forecasting using Machine Learning Algorithms. International Journal of Computer Science and Information Technologies, 12(2), 26-33. https://ijcsit.com/docs/volume12/vol12issue02/ijcsit2021120201.pdf
• Wettschereck, D., Aha, D. W., Mohri, T. (1997). A review and empirical evaluation of feature weighting methods for a class of lazy learning algorithms. Artificial Intelligence Review, 11(1), 273- 314. https://link.springer.com/article/10.1023/A:1006593614256
• Witten, I. H., Frank, E., Trigg, L. E., Hall, M. A., Holmes, G., Cunningham, S. J. (1999). Weka: Practical machine learning tools and techniques with Java implementations. https://researchcommons.waikato.ac.nz/bitstream/handle/10289/1040/uow-cs-wp-1999- 11.pdf?sequence=1&isAllowed=y
• Zhang, X., Liu, L., Xiao, L., Ji, J. (2020). Comparison of machine learning algorithms for predicting crime hotspots. IEEE Access, 8, 181302-181310. doi: https://doi.org.tr/ 10.1109/ACCESS.2020.3028420