In view of the unclear classification boundary of the traditional manufacturing enterprise warehouse classification method and the difficulty of adapting to the development trend of modern enterprise informatization, the ABC inventory classification algorithm based on the clustering algorithm is proposed to improve the classification accuracy and efficiency of the traditional inventory classification model. Taking the inventory product data of an electric power manufacturing company as the research object, combining the clustering algorithm and the ABC classification method, an evaluation function suitable for actual research scenarios is proposed, and a new ABC classification method based on the k-means algorithm is given. This classification model is used to classify the inventory ring network cabinet products, and based on the product data stored in the ERP system, the inventory ring network cabinet products are divided into three categories: A, B, and C. According to the classification results, different categories of ring network cabinet products are taken Different inventory control strategies. The research results show that the application of data mining algorithms to inventory management has realized the scientific and intelligent decision-making of enterprise inventory management.