Customer Segment Application of Machine Learning in Business Operation of China Mobile.

The purpose of this paper is to use machine learning technology to build more user profiles in the process of customer segmentation to assist marketing decision-making. Specifically, by introducing cross features into the construction of Feature Engineering, the accuracy of target group prediction can be further improved and the user subgroup after feature crossing can be mined. In addition, this paper also proposes an improved decision tree model, which can build more comprehensive user profiles, and then assist in intelligent marketing. Firstly, both methods need to preprocess the data. In addition, for the subsequent feature crossing, it is necessary to discretize the continuous features and implement one-hot encoding for all data. In the process of discretization, the paper realizes the automatic selection of better discrete granularity value. A specific example is given and a comparative experiment is carried out to verify the effectiveness of the method.