电子商务推荐系统中服装推荐问题研究  

Researeh on apparel recommendation in e-commerce recommender systems

作　　者：单毓馥[1] 李丙洋 

机构地区：[1]天津工业大学纺织学院,天津300387

出　　处：《毛纺科技》2016年第5期66-69,共4页Wool Textile Journal

摘　　要：推荐系统在解决信息超载和个性化需求方面展现出巨大的潜力。结合服装这一特定的推荐对象对推荐系统及服装推荐问题进行研究,明确了服装推荐系统的定义,通过分析服装推荐的现状和难点问题,提出一种基于AHP层次分析法的服装推荐方法。该方法可以量化影响顾客选择主要因素的权重,通过相似顾客群对某一服装的评分预测另一顾客对该服装的喜好程度,从而选择更符合顾客喜好的服装进行推荐。同现在主流的协同过滤方法比较,该推荐方法算法简单,计算量更小。In dealing with information overload and individualized demands, recommendation system shows great potential. Combined with clothing, the specific object, it discussed the problems of recommender systems and apparel recommendation, gave the definition of clothing recommender system, then analyzed its present situation and difficulties, put forward a clothing recommendation method based on analytic hierarchy process （AHP）. This method can quantify the weight of the main factors that influence customers to make a choice, and predict how much the customer like the clothing by the scores which were given by similar customer groups. Compared with the main stream method, collaborative Key words：

关 键 词：服装 推荐系统 服装推荐 AHP层次分析法 

分 类 号：F724.6[经济管理—产业经济] F426.86