摘要
为解决团购网站无法针对用户进行个性化推荐,结合传统的基于项目和基于用户的协同过滤算法,提出组合的协同过滤算法模型,同时采用商品推荐和好友推荐的双重推荐模式,满足团购个性化推荐的需要.通过离线测试的方法对推荐系统的性能进行仿真实验.结果表明:改进后的算法在推荐效果上是有效的,对协同过滤算法起到了改进作用.
In order to slove the issue that group purchase web site can not target to users personalized recommendation, this paper proposed a combination of collaborative filtering algorithm model by combining with the traditional item-based and user-based collaborative filtering algorithm. Moreover, dual recommendation model that product recommendations and friends' recommended is used to meet the needs of personalized recommendations to buy. The performance of the recommendation system simulation experiment was carried out by off-line testing method. The experimental results show that the improved algorithm is obviously better than the traditional algorithm in the recommended effect and improved the collaborative filtering algorithm.
出处
《辽宁工程技术大学学报(自然科学版)》
CAS
北大核心
2017年第7期761-766,共6页
Journal of Liaoning Technical University (Natural Science)
关键词
推荐系统
协同过滤
团购
信息过载
个性化
recommendation system
recommendation
similar cloud
cold-start
sparsity