Abstract
The rise in crime rate poses significant problems to societies around the world. Departments responsible for public security spend significant time looking for ways of combating crime and adapting policing techniques to curb rising crime rates. The application of artificial intelligence for crime forecasting through optimized parameters of gradient tree boosting using dragonfly algorithm (DA-GTB) has recently attracted research attention. However, the DA-GTB is affected by a loss function that calculates pseudo-responses-value, in which by default uses the least absolute deviation (LAD) loss function. Motivated by the role and limitation of loss function, this research sought to determine DA-GTB crime forecast model using a loss function that improves the model’s predictive performance. Three crime type data from Tanzania Police force that cover 10 years was used and four-candidate loss functions (Wang et al., 2020, Annals of Data Science, 9, 187–212), were identified and applied experimentally to determine the best performing loss function. The evaluation showed that Huber loss function with optimal alpha (α): 0.15, 0.09, and 0.15 parameters with respect to theft, robbery, and burglary crime types, respectively, outperformed other loss functions by an average of 2%, achieving the lowest error rate. Thus, the Huber loss function with the attained α parameters improves the DA-GTB model crime forecast performance.
References
Kaur, N. (2016). Data mining techniques used in crime analysis. A Review - International Research Journal of Engineering and Technology, 3(8), 1981–1984.
Mittal, M., Goyal, M., Sethi, K., & Hemanth, J. (2019). Monitoring the impact of economic crisis on crime in India using machine learning. Journal of Computational Economics, 53(4), 1467–1485.
Stec, A., & Klabjan, D. (2018). Forecasting crime with deep learning (pp. 1–20). Cornell University.
Khairuddin, R., Alwee, R., & Haron, H. (2019). A review on applied statistical and artificial intelligence techniques in crime forecasting. IOP Conference Series: Materials Science and Engineering, 551, 012030.
Catlett, C., Cesario, E., Talia, D., & Vinci, A. (2018). A data-driven approach for spatio-Temporal crime predictions in smart cities. In Proceedings-IEEE International Conference on Smart Computing, SMARTCOMP (pp. 17–24). IEEE. https://doi.org/10.1109/SMARTCOMP.2018.00069
Kumar, M., Athulya, S., Mary, M., Vidya, V., Aiswaria, L., Anjana, S., & Manojkumar, K. (2018). Forecasting of annual crime rate in India: A case study. In International Conference on Advances in Computing, Communications and Informatics, ICACCI (pp. 2087–2092). IEEE. https://doi.org/10.1109/ICACCI.2018.8554422
Khairuddin, R., Ali, A., Alwee, R., Haron, H., & Zain, M. (2019). Parameter optimization of gradient tree boosting using dragonfly algorithm in crime forecasting and analysis. Journal of Computer Science, 15(8), 1085–1096.
Khairuddin, R., Alwee, R., & Haron, H. (2020). A proposed gradient tree boosting with different loss function in crime forecasting and analysis. Advances in Intelligent Systems and Computing, 1073, 189–198.
Nair, S., Soniminde, S., Sureshbabu, S., Tamhankar, A., & Kulkarni, S. (2019). Assist crime prevention using machine learning. SSRN Electronic Journal, 1–5.
Cheng, D., Gong, Y., Zhou, S., Wang, J., & Zheng, N. (2016). Person re-identification by multi-channel parts-based CNN with improved triplet loss function. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 1335–1344). https://doi.org/10.1109/CVPR
Wang, Q., Ma, Y., Zhao, K., & Tian, Y. (2020). A comprehensive survey of loss functions in machine learning. Annals of Data Science, 9, 187–212.
Yuki, J., Mahfil Quader Sakib, M., Zamal, Z., Habibullah, K., & Das, A. (2019). Predicting crime using time and location data. In ACM International Conference Proceeding Series (pp. 124–128). https://doi.org/10.1145/3348445.3348483
Yerpude, P., & Gudur, V. (2017). Predictive modelling of crime dataset using data mining. International Journal of Data Mining & Knowledge Management Process (IJDKP), 7(4), 43–58. https://doi.org/10.5121/ijdkp.2017.7404
Waad, B. (2015). On feature selection methods for credit scoring. PhD Thesis. https://doi.org/10.13140/2.1.3354.1443
Acknowledgments
The authors are grateful to UDSM for providing supportive research environment and to the TPF for granting permission for use of its data for this research.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Justo, G.N., Binamungu, L.P., Clemence, F.S. (2024). Improving Robustness of Optimized Parameters Gradient Tree Boosting for Crime Forecast Model. In: Marx Gómez, J., Elikana Sam, A., Godfrey Nyambo, D. (eds) Artificial Intelligence Tools and Applications in Embedded and Mobile Systems. ICTA-EMOS 2022. Progress in IS. Springer, Cham. https://doi.org/10.1007/978-3-031-56576-2_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-56576-2_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-56575-5
Online ISBN: 978-3-031-56576-2
eBook Packages: Business and ManagementBusiness and Management (R0)