Abstract-In recent years, the analysis of social networks has received considerable attention in the literature because they have a global reach and the large number of data available. For organizations, there are the social networks attractive from the perspective of the promotion of their products and services. And the successful implementation of these activities must take into account a number of factors, existing dependencies in the system and laws for its development. This article is dedicated to study of marketing activities in the social network. The main factors that can influence the result of economic activities are identified. For the study, the authors used data from the groups in the social network VKontakte in the city of Tomsk. For this purpose, the authors calculated network analysis metrics (a clustering factor, a degree, a number of second-level elements) and specific indicators of social groups (activity, popularity). A Java-based program was implemented to collect data and perform group metric calculations. Two regression models have been developed. Also different types of dependencies were studied: linear, hyperbolic, progressive. The first regression model describes the change dependency on the number of members of the group as a result of the competition, based on the number of subscribers and the popularity of the group. The second regression model describes how the value of the advertisement in the group is dependent on the number of subscribers and the indicator of whether the group is the "leader". Both regressions are significant at 99% confidence level. The models can be used in planning and evaluating the results of marketing activities.