TRANSACTION DATA-BASED CUSTOMER CLASSIFICATION METHOD, AND SYSTEM THEREOF

摘要

A transaction data-based customer classification method, and system thereof, relating to the technical field of data mining, wherein said method comprises: gathering transaction data from a transaction database of a retail business; pre-processing the gathered transaction data, and respectively encoding the pre-processed transaction data in layers; establishing a customer purchasing tree for each customer according to layered information following encoding; clustering all established customer purchasing trees until a clustering center undergoes no further changes, or any changes that do occur are below a preset threshold value, thereby acquiring a customer classification result. The present scheme is capable of processing large amounts of data quickly and efficiently, and solves the problem of conventional methods being unable to process current big data on account of the excessively high computational complexity.