Recommender system has become an important application of big data technology. In order to master the complex influencing factors of dynamic feedback of recommendation system on information platform, based on the theory of system dynamics, this paper analyzes the causal relationship of each element of personalized recommendation system of news information, draws the causality diagram, and establishes the system dynamics flow chart of influencing personalized recommendation, the simulation equations are constructed and simulated with Vensim software. The results show that the number of articles, the characteristic tags and the interest factors of articles have important influence on the recommendation effect, which are also the key problems to be solved in the design of the recommendation system. At the same time, it can also solve the key problems of the news information recommendation system, such as cold start, real-time and information cocoon room.