Spam detection using Catboost integration algorithm
TianLin Zhang, Youfeng Niu, Rong Ma, MengYuan Zhao, DuoYang Song, Hengbin Liu · 2023
This paper introduces the background and significance of building a CatBoost-based spam detection model and proposes a new research approach on the classical research model. Besides, a large number of network resources are occupied which makes 85% of the system resources of the mail server are used for the identification of spam. It is not only a waste of resources, but may even lead to network congestion and paralysis, affecting the normal business email communication of enterprises. In this study, we use the Enron-Spam dataset, which is currently the most publicly available dataset used in email-related research. First, we use word bagging processing and TF-IDF processing for feature extraction, and then CatBoost integration algorithm is used for training. The final accuracy of the model is more than 98%. Compared with the conventional model, the model has better performance, which can effectively improve the accuracy of spam detection and identification.