Abstract
When conducting scientific and technical expertise, it is necessary to analyze the texts of reports on scientific research work. The analysis is carried out in order to determine whether the research being conducted belongs to the class of scientific research and development work in the field of IT. The main purpose of this study is to improve algorithms for analyzing text documents during scientific and technical expertise. To achieve this goal, the tasks of binary classification of documents provided by companies using machine learning technologies are considered. As a result of the study, a comparative analysis was carried out and the most effective machine learning algorithms were identified. The proposed algorithms will be used in a system that automates the process of checking documents submitted to taxpayers by the tax office.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
