Bank Customer Classification Algorithm Based on Improved Decision Tree
Ruitao Zhou, Cui Li, Xiaohui Wang · 2022
The traditional decision tree algorithm has an over-fitting phenomenon and its pruning step is time-consuming. It is difficult to meet the actual needs in classifying bank customers. In response to this situation, an improved decision tree classification method is proposed. The algorithm is based on rough set theory to reduce the size of the decision tree to avoid overfitting. The simulation results show that the improved algorithm reduces the scale of attributes and the consumption of prediction time, and the prediction accuracy rate reaches more than 95%.