Abstract
Crime is one of the most alarming and disturbing aspects of our society. Crimes happen anywhere at anytime. These many different crimes, sometimes life threatening, render many people insecure. This makes crime prevention a very important task all around the world. One of the ways in preventing crime is the ability to predict potential crimes. With the recent advancements in Artificial Intelligence (AI) and the abundance of data, it is worth looking into this problem and solving them in a more efficient way. This work is devoted to studying the possibility of predicting crime using machine learning, an AI technique. The combination of crime data and machine learning methods show a high prospect in solving the task of predicting future crime incident efficiently. In this paper, we find out about this prospect, what models fit this objective in the best way and how results could be practically used and finally, we test the reliability of the results achieved from the model. By analyzing existing sources of information related to this topic, we figure out what factors influence crime probability, collect data about these factors and crime incidents, clear it from noise, do exploratory analysis, detect noticeable features and compare results of several machine learning models. We show the model with the highest accuracy and discover the possible ways of its future improvements and usage.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Farrington, D., Welsh, B.: The Oxford Handbook of Crime Prevention. Oxford University Press, Oxford (2012). ISBN: 978-0-19-994078-3. https://doi.org/10.1093/oxfordhb/9780195398823.001.0001 [Online]. Available: https://www.oxfordhandbooks.com/view/10.1093/oxfordhb/9780195398823.001.0001/oxfordhb-9780195398823 (visited on 01/07/2022)
Alves, L.G.A., Ribeiro, H.V., Lenzi, E.K., Mendes, R.S.: Distance to the scaling law: a useful approach for unveiling relationships between crime and urban metrics. PLOS ONE 8(8), e69580 (2013). ISSN: 1932-6203. https://doi.org/10.1371/journal.pone.0069580 [Online]. Available: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0069580 (visited on 01/07/2022)
Cotte Poveda, A.: Violence and economic development in Colombian cities: a dynamic panel data analysis. J. Int. Dev. 24(7) (2012). ISSN: 1099-1328. https://doi.org/10.1002/jid.2819 [Online]. Available: https://onlinelibrary.wiley.com/doi/abs/10.1002/jid.2819 (visited on 01/07/2022)
Hojman, D.E.: Inequality, unemployment and crime in Latin American cities. Crime Law Soc. Change 41(1), 33–51 (2004). ISSN: 1573-0751. https://doi.org/10.1023/B:CRIS.0000015327.30140.8d [Online] (visited on 01/07/2022)
Curtis-Ham, S., Walton, D.: Mapping crime harm and priority locations in New Zealand: a comparison of spatial analysis methods. Appl. Geogr. 86, 245–254 (2017). ISSN: 0143-6228. https://doi.org/10.1016/j.apgeog.2017.06.008 [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0143622816305045 (visited on 01/07/2022)
Predictive Policing for Crime Analysts—PredPol [Online]. Available: https://www.predpol.com/analysts/ (visited on 01/07/2022)
Public Safety Cloud (2021). Available: https://www.ibm.com/industries/government/public-safety (visited on 01/07/2022)
Ingilevich, V., Ivanov, S.: Crime rate prediction in the urban environment using social factors. Procedia Comput. Sci. 136, 472–478. In: 7th International Young Scientists Conference on Computational Science, YSC2018, 02–06 July2018, Heraklion, Greece (2018). ISSN: 1877-0509. https://doi.org/10.1016/j.procs.2018.08.261 [Online]. Available: https://www.sciencedirect.com/science/article/pii/S1877050918315667 (visited on 01/07/2022)
Almanie, T., Mirza, R., Lor, E.: Crime prediction based on crime types and using spatial and temporal criminal hotspots. Int. J. Data Min. Knowl. Manag. Process 5(4), 01–19 (2015). ISSN: 2231007X, 22309608. https://doi.org/10.5121/ijdkp.2015.5401. Available: http://arxiv.org/abs/1508.02050 (visited on 01/07/2022)
Kang, H.-W., Kang, H.-B.: Prediction of crime occurrence from multimodal data using deep learning. PLOS ONE 12(4), e0176244 (2017). ISSN: 1932-6203. https://doi.org/10.1371/journal.pone.0176244 [Online]. Available: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0176244 (visited on 01/07/2022)
Abouelnaga, Y.: San Francisco crime classification (2016) [Online]. Available: http://arxiv.org/abs/1607.03626 (visited on 01/07/2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Saleh, H., Sakunova, A., Abbas, A.J.F., Mahmood, M.S. (2022). Machine Learning-Based Crime Prediction. In: Czarnowski, I., Howlett, R.J., Jain, L.C. (eds) Intelligent Decision Technologies. Smart Innovation, Systems and Technologies, vol 309. Springer, Singapore. https://doi.org/10.1007/978-981-19-3444-5_44
Download citation
DOI: https://doi.org/10.1007/978-981-19-3444-5_44
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-3443-8
Online ISBN: 978-981-19-3444-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)