Associative Model of Support for Judicial Decision-Making
DOI:
https://doi.org/10.35774/10.35774/app2023.03.056Keywords:
decision-making, criminal justice, computational criminology, criminal offenses, security, criminal recidivism, suspended convictions, early dismissals, predictive justice, data science, associative modelAbstract
Despite numerous efforts aimed at ensuring the protection of the accused, and despite the understanding of the effectiveness of preventive measures in contrast to punitive sanctions, modern industrialized society in most cases decides to apply imprisonment to persons convicted of crimes. Convicted persons face increasing legal and social prejudice, alienation, and marginalization, including the loss of voting privileges. In addition, keeping a significant number of prisoners in penitentiary institutions causes an additional significant burden on the economies of the countries of the world. In addition, keeping a significant number of prisoners in penitentiary institutions causes an additional significant burden on the economies of the countries of the world. Today, effective solutions are needed in the criminal justice system, which will not be excessive in relation to the convicts and will be sufficient to ensure social order. Scientific methods and modern information technologies are increasingly used in predictive justice to support judicial decision-making.
The search for effective decision-making strategies that can help reduce the number of prisoners and state costs for their maintenance in penitentiary institutions and at the same time ensure the personal safety of citizens and the safety of society in general are becoming more and more relevant. The application of data science to support effective judicial decision-making is a prerequisite.
The work uses the analysis of associative rules to identify non-obvious relationships between data on previous criminal offenses of convicts. A model of associative rules was built to identify non-obvious interesting connections between individual statistical and dynamic characteristics of convicts and the fact of their criminal recidivism. Associative rules (regularities) were revealed, which are a combination of individual characteristics of convicts who commit repeated criminal offenses. The obtained results give grounds for asserting that convictions are the main conditions (antecedents), that cause the risk of recidivism (consequent).
References
Ilyushin, M. & Ebel, F. (2022). Using conscripts and prison inmates, Russia doubled its forces in Ukraine. Retrieved from https://www.washingtonpost.com/world/2022/12/23/russia-troops-wagner-convicts-ukraine [in English]
Walsh, N. P., Markina, D., Shukla, S., Ochman, O. & Tarasova, D. (2022). Russia dangles freedom to prisoners if they fight in Ukraine. Many are taking the deadly gamble. Retrieved from https://edition.cnn.com/2022/08/09/ europe/russia-recruits-prisoners-ukraine-war-cmd-intl/index.html [in English]
Kovalchuk, O. & Banakh, S. (2023). Lohika prava: stratehiia kryminalnoho profiliuvannia [Logic of Law: Criminal Profiling Strategy]. Aktualni problemy pravoznavstva ‒ Actual problems of law, 3, 169-175 [in Ukrainian]
Jabeen, N. & Agarwal, P. (2021). Data Mining in Crime Analysis. Proceedings of Second International Conference on Smart Energy and Communication, 97–103. Retrieved from https://10.1007/978-981-15-6707-0_10 [in English]
Ogochukwu, O. & Forster, O. (2021). An Overview of Crime Analysis, Prevention and Prediction Using Data Mining Based on Real Time and Location Data. International Journal of Engineering Applied Sciences and Technology, 5 (10), 99-103. Retrieved from https://www.ijeast.com/papers/99-103,Tesma510,IJEAST.pdf [in English].
Sangani, A., Sampat, C. & Pinjarkar, V. (2019). Crime prediction and analysis. SSRN Electronic Journal, 1-5. Retrieved from https://doi.org/10.2139/ssrn.3367712 [in English]
Saravanan, P., Selvaprabu, J., Raj, L. A., Khan, A. & Sathick, K. (2021). Survey on crime analysis and prediction using data mining and machine learning techniques. Lecture Notes in Electrical Engineering, 688, 435-448. URL: https://doi.org/10.1007/978-981-15-7241-8_31 [in English].
Idder, A. & Coulaux, S. (2021). Artificial intelligence in criminal justice: invasion or revolution? International Bar Association. Retrieved from https://www.ibanet.org/dec-21-ai-criminal-justice [in English]
Berezka, K. M, Kovalchuk, O. Ya., Banakh, S. V., Zlyvko, S. V. & Hrechaniuk, R. (2022). A Binary Logistic Regression Model for Support Decision Making in Criminal Justice. Folia Oeconomica Stetinensia, 22 (1), 1-17. Retrieved from https://doi.org/10.2478/foli-2022-0001 [in English]
Kovalchuk, O., Banakh, S., Masonkova, M., Burdin, V., Zaverukha, O. & Ivanytskyy, R. (2022). A Scoring Model for Support Decision Making in Criminal Justice. Advanced Computer Information Technology: Proceedings of the 12th International Conference (Slovakia), 116-120. Retrieved from https://doi.org/10.1109/ACIT54803.2022.9913182 [in English]
Baker, D. J. & Robinson, P. H. (Eds.). (2020). Artificial Intelligence and the Law. Cybercrime and Criminal Liability. Retrieved from https://doi.org/10.4324/9780429344015 [in English]
Dakalbab, F., Talib, M., Waraga, O., Nassif, A., Abbas, S. & Nasir, Q. (2022). Artificial intelligence & crime prediction: A systematic literature review. Social Sciences & Humanities Open, 6 (1), 1-23 [in English]
Wyner, A., Mochales-Palau, R., Moens, M.-F. & Milward, D. (2018). Approaches to Text Mining Arguments from Legal Cases. Semantic Processing of Legal Texts: Proceedings of the Conference (Germany), 60-79 [in English] https://doi.org/10.1007/978-3-642-12837-0_4
Xu, Ju. (2021). Research on Judicial Big Data Text Mining and Sentencing Prediction Model. Journal of Physics: Conference Series 1883, 1-6 [in English]. https://doi.org/10.1088/1742-6596/1883/1/012158
Jantan, H. & Jamil, A. (2019). Association Rule Mining Based Crime Analysis using Apriori Algorithm. International Journal of Advanced Trends in Computer Science and Engineering, 8 (1.5), 18-24 [in English] https://doi.org/10.30534/ijatcse/2019/0581.52019
Kovalchuk, O., Banakh, S., Masonkova, M., Berezka, K., Mokhun, S. & Fedchyshyn, O. (2022). Text Mining for the Analysis of Legal Texts. Advanced Computer Information Technology: Proceedings of the 12th International Conference (Slovakia), 502-505 [in English] https://doi.org/10.1109/ACIT54803.2022.9913169
Kovalchuk, O., Banakh, S., Masonkova, M., Moskaliuk, N., Rohatynska, N. & Pustovyi, O. (2023). Survival Analysis Models for Estimating and Predicting the Risks of Confession of Criminal Defendants. Advanced Computer Information Technology: Proceedings of the 13 th International Conference (Poland), 46-51 [in English]. https://doi.org/10.1109/ACIT58437.2023.10275450
Kovalchuk, O., Kasianchuk, M., Karpinski, M. & Shevchuk, R. (2023). Decision-Making Supporting Models Concerning the Internal Security of the State. International Journal of Electronics and Telecommunications, 69 (2), 301-307 [in English].
Kovalchuk, O., Shevchuk, R., Shangytbayeva, G. & Kasianchuk, M. (2022). Decision Support Model Based on the Analysis of International Security Risks and Threats. Chapter in monograph: Przetwarzanie, transmisja i bezpieczeństwo informacji. Akademia Techniczno-Humanistycznej, Bielsku-Białej, 57-70 [in English]
Kovalchuk, O., Karpinski, M., Banakh, S., Kasianchuk, M., Shevchuk, R. & Zagorodna, N. (2023). Prediction Machine Learning Models on Propensity Convicts to Criminal. Information, 14 (3), 161 [in English] https://doi.org/10.3390/info14030161
Mathur, V. (2022). Association Rule Mining: Importance and Steps. Analytics Steps. Retrieved from https://www.analyticssteps.com/blogs/association-rule-mining-importance-and-steps [in English]