Tools in the management of tourism business resources

The purpose of the work is to develop an application for automated construction of a decision tree of multilevel predictive models. The object of the study is the time series of the number of tourists arriving in the Dombay ski village for the period from 2015-2017. The subject of the research is methodological and methodological issues of assessment, analysis and forecasting of socio-economic indicators in the field of tourism. The theoretical aspects of managing a complex process consist of the following components: the pursuit of the goal of obtaining maximum profit from the sale of tourist vouchers in conditions of uncertainty; the availability of an information base for the future behavior of the system (in this case, information on the forecasts of the tourist flow); the construction of scenarios of possible outcomes of the system based on the “decision tree” model. Electron was used to design the author’s Decision Tree tool, which is a framework for developing desktop applications using HTML, CSS and JavaScript, using libraries - D3.js. When choosing a graphical means of representing the decision tree model, two drawing technologies were used with objects stored in memory - SVG and CANVAS. Such applications can run on various platforms. Among them are Windows, Mac and Linux. The formed decision tree of possible outcomes clearly shows the complexity of the decision-making process on the choice of ticket sales channels for making effective economic decisions in the sanctions restrictions that have been created at the moment.