Developement of an Decision Making System for Analysys of Judicial Pronouncement

Graduation qualification work consists of 37 pages, contains 14 drawings, 1 table and 2 appendixes. Key words: legal tech; machine learning; data mining; predictive models; natural language processing. The object of development in this work is the decision-making system on court cases. The purpose of the project is to develop an automated system for processing text materials on court decisions, able to analyze them and predict the probability of satisfaction of the case at the hearing. During the work, a marked-up data set for predictive model training was obtained, which can be used in the future by other developers, and software for the analysis of decisions of court cases was created. A review and comparative analysis of the existing technical solutions in the field of legal proceedings with the analysis of relevant statistics was carried out, software tools were selected based on a comparative analysis of methods and tools for developing the system. The results of the work can be used for further research in the field of jurisprudence, consultations of both parties to the dispute, as well as to improve the quality of legal proceedings.