Kolpakova T. Methods, models and information technology of supporting the process of competing agents selecting

The object of study - the process of competing agents selecting. The purpose of this study is supporting of the competing agents selection process based on models and methods for obtaining and formalization of individual and group peer reviews, and creating of the appropriate information technology. Methods of research are methods of decision support theory for obtaining expert evaluations, methods of pattern recognition theory for the selection and evaluation of agents, multi-objective optimization methods for determining of the optimal distribution of the order, methods of object-oriented programming and service-oriented approach for the information system development. The result of the study is creating an information technology which allows to automate the process of competing agents selecting. Scientific novelty: the model of the process of competing agents selecting, which represents decomposition of the process into a set of defined stages is proposed; the method of determining group ratings based on individual expert ratings for each decision is improved; the method of competing agents evaluating by a set of criteria that allows to rank the agents is improved; the method of optimizing the distribution of the order among competing agents which takes into account the relative importance of criteria is improved. Scope of use: problems that require expert evaluation.