Decision support systems for predicting innovation activity at the macro level are not yet widely used, and the authors have not been able to find direct analogues of such a system. The relevance of creating the system is due to the need to take into account heterogeneous structured and unstructured information, including in natural language, when predicting innovation activity. The article describes the process of designing a decision support system for predicting innovation activity, based on the system for integrating macroeconomic and statistical data (described by the authors in previous articles) by adding a module of decision-making methods. The UML diagram of use cases and the UML diagram of the components of this module, the general architecture of the prototype of the decision support system, are presented. It also describes an algorithm for predicting innovation activity and its impact on the potential for economic growth using DSS.