Abstract: In order to deeply analyze the demand of the railway freight market and assist in the dynamic adjustment of operational strategies and precise allocation of marketing resources, this paper proposed a maximal clique correlation analysis algorithm improved by combining K-means clustering, based on the annual customer waybill data and phased demand data of Zhengzhou Railway Group Co., Ltd. from the China Railway 95306 Freight E-commerce Platform. Specifically, through data preprocessing, the paper identified the key factors affecting the market-oriented operation of railway freight transportation and drew a key data map of railway freight transportation. Furthermore, the paper constructed the hierarchical relationship between key factors to simplify the map branches. The improved algorithm was used to explore the maximal cliques with strong correlations affecting railway freight transportation, and comparisons with common correlation analysis algorithms verified the advantages of the proposed algorithm in solving speed. The research results visualized and analyzed the maximal cliques taking the transportation volume and distance as the core elements, effectively identifying the demand characteristics of the freight market and providing support for enhancing the core competitiveness of railway freight.