Methods of machine learning as a tool for increasing the efficiency of the work of state budgetary institutions authorized to perform state cadaster assessment

The article discusses the tasks that, when conducting a state cadastral valuation, can be solved using machine learning methods, including the problem of automatically determining the topic of requests for correcting errors made in determining the cadastral value. The main attention is paid to the problem of classifying real estate objects in mass appraisal. The results of applying the described methods in the state budgetary institution of the Moscow region, authorized to conduct a state cadastral valuation, are presented. Directions for further development of the proposed algorithms are proposed.