A prediction method for the cellphone replacement: Rough set-based analysis

Owing to the communication customers' data are large scale, inconsistent and incomplete, it is hard to predict who will replace their cellphones in the near future. In order to solve this problem, a prediction method based on dominance-based rough set approach (DRSA) is proposed in this paper. Firstly, the customers' features are extracted based on experts' knowledge. So, we get the customer decision table. After that, the maximum certainty of each class union is used as the corresponding variable threshold value to control the decision rule extraction program. Therefore, the extracted decision rules can reflect the data characteristics effectively. In this process, it can learn knowledge automatically without setting the threshold values of consistency level depending on prior domain knowledge or by a complex tail-and-error procedure. Additionally, it strengthens the performance for dealing with inconsistent information systems. The efficiency of this method is illustrated by simulation experiments.