With terrorism aggravating, anti-terrorism has been a main task for national military security departments around the world. The current study utilized categorical data visualization, Parallel Sets, to analyze the relations among the multi-categories in Global Terrorism Database, aimed to uncover the implicit information within the data set. To alleviate the deficiency of excessive edge crossing brought by random layout of categorical values, the research proposed a heuristic layout algorithm based on average heuristic with cardinality reduction, which optimized the layout order of categories and the visual clutter is eased so that the cardinality reduction strategies can reduce the numbers of categories involved in computation. The experimental results demonstrate that the improved parallel sets can clearly express the association among the multi-categories in Global Terrorism Database, thereby assist users in analyzing the information of various terrorist organizations, such as the behavior characteristics. Furthermore, the average-based heuristic with cardinality reduction is simple and highly efficient, which is suitable for large data sets with many categorical attributes.