METHOD FOR SELECTING RECOMMENDATION TYPE IN PRODUCT RECOMMEDING SYSTEM

• Main Authors: MOON, HYUN SIL, KIM, JAE KYEONG
• Format: Patent
• Language: English; Korean
• Published: 08.10.2015
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The present invention relates to a method for recommending a product based on cooperation filtering. More specifically, the present invention relates to a method for selecting the most suitable recommendation technique by configuring a product purchasing database to a plurality of sample networks based on a data property of the product purchasing databases, and determining a recommendation outcome of the whole product purchasing data using a property having a significance in each sample network. 본 발명은 협업 필터링 기반의 상품 추천 방법에 관한 것으로, 보다 구체적으로 상품 구매 데이터베이스의 데이터 특성에 기초하여 상품 구매 데이터베이스를 다수의 샘플 네트워크로 구성하고 각 샘플 네트워크에서 유의성을 가지는 특성으로 전체 상품 구매 데이터의 추천 성과를 판단하여 상품 구매 데이터베이스에 가장 적합한 추천 기법을 선택하는 방법에 관한 것이다.