BIG DATA BASED RETAIL RECOMMENDER SYSTEM OF NON E-COMMERCE

Recommender system, as a means of achieving precision marketing, has been widely used and brought about significant benefits in modern e-commerce systems. However, there is a lack of study on the applying of recommender system to traditional non e-commerce retailing mode. This paper presents a retail recommender model based on collaborative filtering, and designs the corresponding distributed computing algorithm on MapReduce, so as to implement a big data based retail recommender system. The big data mechanism helps the system do scalable data processing easily. Experimental results show that the system is effective for the estimation of retail sales for each store and product. As a result, non e-commerce enterprises could benefit from this novel way of precision marketing supports.