文章基本信息

标题：DEEP LEARNING FOR RECOMMENDER SYSTEM BASED ON APPLICATION DOMAIN CLASSIFICATION PERSPECTIVE: A REVIEW
本地全文：下载
作者：HANAFI ; NANNA SURYANA ; ABD SAMAD BIN HASAN BASARI 等
期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2018
卷号：96
期号：14
出版社：Journal of Theoretical and Applied
摘要：Recommender system is critical equipment for establishing an effective communication between consumers and retailers in ecommerce business. Effective and enjoyable communication to find the fit product is considered to have a massive implication to increase of sales achievement. Recommender system established in the middle 90s. Based on technical approach, there are four of recommender system model namely Collaborative filtering, Contents Based, Knowledge Based and Demographic filtering. Collaborative filtering is considered to be more superior than another tree methods. It offers obviously advantages in terms of serendipity, novelty and accuracy. Although it has several benefits in recommendation result, in an effort to improve the weakness of the recommender system, many involving machine learning, machine learning with shallow layers was popular in the 90's for instance neural network, SVM. In the era of big data like now, where the amount of data is abundant, and the data variations are very diverse, this will become an increasingly interesting challenge in generating a recommender system results more appropriate in the present era of big data. in this literature review, researchers are trying to find answers to the weaknesses, challenges and opportunities forwards that exist in the method of deep learning for ecommerce recommender system.
关键词：Ecommerce; Recommender System; Recommendation System; Deep Learning; Deep Network