In this paper, according to the information classification algorithm in data mining, data in the network payment system of e-commerce is mined, forming an effective evaluation of the security of the network payment system. Firstly, the method of network security risk prediction is discussed. Secondly, according to the characteristics of network payment system, the system security index system is analyzed in detail, and the specific application process of the C4.5 Classification Algorithm in security evaluation is discussed. Finally, the data mining process is designed in detail and the corresponding code established. In this paper, data mining theory is applied to the network payment security evaluation system, and an algorithm system is constructed to evaluate the network payment security. The algorithm system realizes the effective evaluation and judgment of the network payment system security as well as warning of potential network security problems, effectively changing the previous way of network security management, and ensures the security and stability of the network payment system is maximized. © 2020 CRL Publishing. All rights reserved.