Customer recommendation system based on data digging and method thereof

Abstract

The invention discloses a data mining based customer recommendation system and a method of the same, wherein the system comprises a data preparation part and a real-time recommendation part. The data preparation part comprises a source data extracting module, an order data extracting module, a calculation model module, a similar customer calculation model module. The real-time recommendation part comprises a recommendation result generating and displaying module. The method comprises the following steps of: preparing the source data and extracting the corresponding data items, building a customer-commodity calculation model, calculating the similar customer sets of each customer, recommending the commodities the similar customers purchased to the customer. Thus, the customers are catered for, an intelligent online purchasing guide function is provided, the online purchasing feelings of users are improved, and the profits of commercial websites therefore are maximized.

Description

technical field [0001] The invention relates to the field of database information retrieval, in particular to the field of information retrieval for mining data information and recommending to customers. Background technique [0002] Today's era is the era of information technology, the Internet occupies a considerable proportion in people's lives, and online shopping is one of them. For this reason, e-commerce websites all aim to obtain the maximum benefit, and use technical and non-technical methods to increase registered customers, increase order volume, and provide high-quality services. Under these circumstances, the personalized recommendation technology of e-commerce website emerges as the times require. [0003] At present, some domestic recommendation technologies mostly use relatively primitive methods: [0004] The most primitive method is "database query", which uses sql statements to find products with the same author, same category, etc. in the database, and ...

AI Technical Summary

Problems solved by technology

Association rule extraction is difficult and time-consuming; product names are synonymous Sexual issues; low personalization

Images