Abstract: The subject of the research is assessing the risks of performing government contracts. The object of the study is the process of analysis and evaluation of the implementation of government contracts. The study is aimed at developing a methodology that determines the importance and significance of signs that influence the risk of non-fulfillment of government contracts. Research methods were used: data analysis to detect connections and dependencies between various characteristics and the risk of non-fulfillment of government contracts; statistical analysis to obtain an assessment of the impact of each characteristic on the risk of non-fulfillment of contracts and ranking them in order of importance; machine learning to predict the risk of non-fulfillment of government contracts; expert assessments to take into account contextual factors and features, their impact on the importance of features. The main conclusions of the study are the presented methods for assessing the importance of features when analyzing the implementation of government contracts, by using data from various sources, including the register of public procurement of the unified information system (UIS), the register of unscrupulous suppliers (RNP) of the EIS and the SPARK information system. The authors managed to achieve high prediction accuracy (more than 97%) and analyze the most important and significant features. The scientific novelty lies in the fact that the results obtained make it possible to identify and analyze factors from three information systems that influence the risks of non-fulfillment of government contracts. Thus, this study is valuable and important in its field, which contributes to the development of more effective risk management methods and increased efficiency in the implementation of government contracts. The results obtained allow us to identify the factors that have the greatest impact on the risks of non-fulfillment of contracts, which makes the study valuable and important in this area.

Abstract: The research is aimed at solving the problem of the execution of government contracts, the importance of using unstructured information and possible methods of analysis to improve the control and management of this process. The execution of government contracts has a direct impact on the security of the country, its interests, economy and political stability. Proper execution of these contracts contributes to the protection of national interests and ensures the security of the country in every sense. The object of research is algorithms used to extract information from texts. These algorithms include machine learning technologies and natural language processing. They are able to automatically find and structure various entities and data from government contracts. The scientific novelty of this study is the accounting of unstructured information in the analysis of the execution of government contracts. The authors drew attention to the problem-oriented texts in the contract documentation and suggested analyzing them with numerical indicators to assess the current state of the contract. Thus, a contribution was made to the development of methods for analyzing government contracts by taking into account unstructured information. The proposed methods for analyzing problem-oriented texts using machine learning. This approach can significantly improve the evaluation and management of the execution of government contracts. The results of the interpretation of problem-oriented texts can be used to optimize the risk assessment model for the execution of a government contract, as well as to increase its accuracy and efficiency.