USING ARIMA MODELS FOR FORECASTING OF OVERALL CRIME RATE IN UKRAINE

2024;
: 49–56
https://doi.org/10.23939/ujit2024.02.049
Received: October 15, 2024
Accepted: November 19, 2024
1
Vinnytsia National Technical University, Vinnytsia, Ukraine
2
Vinnytsia National Technical University, Vinnytsia, Ukraine
3
Vinnytsia National Technical University, Vinnytsia, Ukraine
4
Vinnytsia National Technical University, Vinnytsia, Ukraine
5
Vinnytsia National Technical University, Vinnytsia, Ukraine

Crime rate forecasting is a critical element in the development of strategies for sustainable socio-economic growth in a rule-of-law state. Accurate forecasting becomes particularly important in times of economic instability and geopolitical crises, as is the case in Ukraine. This article explores the problem of constructing and applying autoregressive integrated moving average (ARIMA) models to predict the total number of crimes committed in Ukraine. The statistical analysis of the crime time series was conducted using the Python programming language, utilizing specialized libraries such as numpy, pandas, matplotlib, statsmodels, pmdarima, and scikit-learn. The calculations indicate that the crime time series (1990-2023) demonstrates a declining trend, is non-stationary, and contains anomalous values in crime rates in 2003, 2013, and 2020, correlating with socio-political crises in Ukraine. Specifically, the anomalous increases in crime rates (in 2003 and 2013) align with heightened public unrest preceding the Orange Revolution (2004-2005) and the Revolution of Dignity (2013-2014). In contrast, the unusually low crime rates observed in 2020 are attributed to restrictive quarantine measures implemented due to the COVID-19 pandemic. The use of data integration by taking the first differences between observations resulted in the loss of autocorrelation structure inherent in the overall crime series. Consequently, the initial ARIMA (1, 0, 0) model was built based on the untransformed input data. The accuracy of this model was higher compared (MAPE = 8,61%) to the model obtained using the exponential smoothing method (MAPE = 9,38%). Logarithmic transformation of the crime time series and smoothing of anomalous levels enhanced the predictive validity, allowing the ARIMA model to account for additional autocorrelation while avoiding the need for a moving average component. As a result, the ARIMA (2, 0, 0) model demonstrated the highest accuracy (MAPE = 7,04%) with minimal complexity, as confirmed by information criteria results. Furthermore, the model successfully passed robustness testing using the cross-validation method with the exclusion of a single observation. The forecasted estimates, derived from all the examined ARIMA models, indicate a continued increase in the overall crime rate in Ukraine, which began in 2021 following a prolonged period of decline.

1. Box, G. E. P., Jenkins, G. M., Reinsel, G. C., & Ljung, G. M. (2015). Time series analysis: Forecasting and control (5th ed.). Hoboken, NJ, USA: John Wiley & Sons Inc. https://doi.org/10.1111/jtsa.12194
https://doi.org/10.1111/jtsa.12194
2. Dzendzeliuk, O., Kostiv, L., & Rabyk, V. (2013). Building ARIMA models of time series for weather data forecasting in R programming language. Electronics and Information Technologies, 3, 211-219. http://nbuv.gov.ua/UJRN/Telt_2013_3_24
3. Strilets, V. Ye., & Doroshenko, M. I. (2022). Analysis and forecasting of computer network characteristics. Bulletin of V. N. Karazin Kharkiv National University. Mathematical Modeling. Information Technologies. Automated Control Systems, 55, 49-57. https://doi.org/10.26565/2304-6201-2022-55-05
4. Marchuk, D. K., Kravchenko, S. M., Levchenko, A. Yu., & Lezhnov, I. Ya. (2023). Using time series for forecasting the monetary value of cars. Scientific Notes of the V. I. Vernadsky Taurida National University. Series: Technical Sciences, 34(73), 119-125.
https://doi.org/10.32782/2663-5941/2023.1/18
5. Masliy, V. V., & Berezka, K. M. (2017). Selection and evaluation of ARIMA models for forecasting foreign direct investment. Scientific Bulletin of the International Humanitarian University. Series: Economics and Management, 24(2), 115-119. http://nbuv.gov.ua/UJRN/Nvmgu_eim_2017_24(2)__26
6. Dziubanovska, N. V., & Liashenko, O. M. (2018). Application of ARIMA models for forecasting the dynamics of Ukraine's foreign trade. Black Sea Economic Studies, 35(1), 142-147.
7. Islam, K., & Raza, A. (2020). Forecasting crime using ARIMA model. arXiv. http://arxiv.org/abs/2003.08006
8. Chen, P., Yuan, H., & Shu, X. (2008). Forecasting crime using the ARIMA model. In Proceedings of the 5th International Conference on Fuzzy Systems and Knowledge Discovery (pp. 627-630). https://doi.org/10.1109/FSKD.2008.222
https://doi.org/10.1109/FSKD.2008.222
9. Salati, L., & Majige, S. (2022). Forecasting criminal offenses against persons using time series models: A case study of Mwanza Region. Asian Journal of Multidisciplinary Research & Review, 3(2), 61-77. https://doi.org/10.55662/AJMRR.2022.3202
https://doi.org/10.55662/AJMRR.2022.3202
10. Lu, Y. (2023). Crime prediction utilizing ARIMA model. BCP Business & Management, 38, 410-418. https://doi.org/10.54691/bcpbm.v38i.3721
https://doi.org/10.54691/bcpbm.v38i.3721
11. Vijayarani, S., Suganya, E., & Navya, C. (2021). Crime analysis and prediction using enhanced ARIMA model. International Journal of Research Publication and Reviews, 2, 257-266. https://www.ijrpr.com/uploads/V2ISSUE1/IJRPR153.pdf
12. Jain, H., & Patel, R. (2024). Analysis & forecasting of juvenile crime using variance threshold and time series algorithm. Multimedia Tools and Applications. https://doi.org/10.1007/s11042-024-19780-x
https://doi.org/10.1007/s11042-024-19780-x
13. Triana, Y. S., & Retnowardhani, A. (2019). Enhance interval width of crime forecasting with ARIMA model-fuzzy alpha cut. TELKOMNIKA (Telecommunication, Computing, Electronics and Control), 17(3), 1193-1201. https://doi.org/10.12928/TELKOMNIKA.v17i3.12233
https://doi.org/10.12928/telkomnika.v17i3.12233
14. State Statistics Service of Ukraine. (2024). Demographic and social statistics. Retrieved from https://www.ukrstat.gov.ua (accessed on 01.09.2024).
15. National Police of Ukraine. (2024). Annual reports. Retrieved from https://www.npu.gov.ua/diyalnist/zvitnist/richni-zviti (accessed on 01.09.2024).
16. Said, S. E., & Dickey, D. A. (1984). Testing for unit roots in autoregressive-moving average models of unknown order. Biometrika, 71, 599-607. https://doi.org/10.1093/biomet/71.3.599
https://doi.org/10.1093/biomet/71.3.599
17. Mann, H. B. (1945). Non-parametric tests against trend. Econometrica, 13(3), 245-259. http://dx.doi.org/10.2307/1907187
https://doi.org/10.2307/1907187
18. Irwin, J. O. (1925). On a criterion for the rejection of outlying observations. Biometrika, 17(3-4), 238-250. https://doi.org/10.2307/2332079
https://doi.org/10.2307/2332079
19. Shevchuk, O. F. (2023). Statistical analysis of the dynamics of crimes committed in Ukraine in 1990-2020. Current Issues in Modern Science, 2(8), 268-279. https://doi.org/10.52058/2786-6300-2023-2(8)-268-27