HCRS: A hybrid clothes recommender system based on user ratings and product
features
Xiaosong Hu, Wen Zhu, Qing Li
Sch. of Economic Inf. Eng.
Southwestern Univ. of Finance & Econ.
Chengdu, China
Abstract-Nowadays, online clothes-selling business has become
popular and extremely attractive because of its convenience
and cheap-and-fine price. Good examples of these successful
Web sites include Yintai.com, Vancl.com and
Shop.vipshop.com which provide thousands of clothes for
online shoppers. The challenge for online shoppers lies on how
to find a good product from lots of options. In this article, we
propose a collaborative clothes recommender for easy
shopping. One of the unique features of this system is the
ability to recommend clothes in terms of both user ratings and
clothing attributes. Experiments in our simulation
environment show that the proposed recommender can better
satisfy the needs of users.
Keywords-Collaborative filtering; Clothes recommender
system; Probabilistic model; Information filtering
I. INTRODUCTION
The concept of a recommender system was first put
forward in the mid–1990s [1]. The basic function of a
recommender system is to suggest interesting products to
end users in terms of users’ behavior. With the fast growth
of e-commerce, recommenders have been playing a vital
role in e-commerce and have attracted great attention from
chief-officers in the big e-business companies including
Amazon.com, Tmail.com. In factuality, many companies
find out that recommenders can not only recommend goods
which fit customers, but also take enormous effect in
converting browsers into buyers, increasing cross-sell and
building loyalty [2]. The adoption of recommender system
in business is widespread.
In general, the recommender can be categorized into
three categories, i.e., the content-based recommender, the
collaborative recommender, and the hybrid recommender.
The content-based recommender recommends
products that are most similar to what the user like
most in terms of the inner attributes of the products.
It derived from information retrieval with a specific
focus on long-term information filtering. A good
example is the PicSOM which recommends similar
images based on the color, texture, and shape of
images [3].
For the collaborative recommender system [5], it
usually recommends products considering the
opinions of others. It is a sort of word-of-mouth
advertisement. Specifically, it first finds friends of a
target user who share similar interest on the same
products based on the historical information. And
then, it predicts the preference of the target user on a
certain product based on the opinions of his/her
friends [4]. It can be further categorized into
memory-based recommender and model-based
recommender [6].
The hybrid system takes both forms of the content-
based system and the collaborative system [6]. It
recommends products based on both the product
attributes and user ratings. A good example of such
hybrid recommender is the music recommender
system developed by Li et al. [7], which suggests
music in terms of user ratings and audio features.
In this article, we propose a hybrid recommender system
for easy clothes shopping. One of the unique features of this
system is the ability to recommend clothes in terms of both
user ratings and clothing attributes. Experiments in our
simulation environment show that the proposed
recommender can better satisfy the needs of users.
II. SYSTEM DESIGN
Figure 1 is the outline of our proposed hybrid clothes
recommendation system, dubbed HCRS, which takes the
utilization of both user ratings and product features. In
particular, it first applies the human detection techniques to
detect the clothes area in an image. Second, it analyzes the
clothes area and calculates the percentage of each color in
this area. Third, it extends the item-rating matrix with group-
rating matrix to accommodate product features for
recommendation. Fourth, similar products of the target
product to be recommended are selected based on such
extended rating matrix. At last, the recommended products
are determined by the ratings earned by the similar products.
下载后可阅读完整内容，剩余4页未读，立即下载
weixin_38513794
- 粉丝: 1
- 资源: 946
我的内容管理
展开
最新资源
- 多传感器数据融合手册：国外原版技术指南
- MyEclipse快捷键大全，提升编程效率
- 从零开始的编程学习：Linux汇编语言入门
- EJB3.0实例教程：从入门到精通
- 深入理解jQuery源码：解析与分析
- MMC-1电机控制ASSP芯片用户手册
- HS1101相对湿度传感器技术规格与应用
- Shell基础入门：权限管理与常用命令详解
- 2003年全国大学生电子设计竞赛：电压控制LC振荡器与宽带放大器
- Android手机用户代理(User Agent)详解与示例
- Java代码规范：提升软件质量和团队协作的关键
- 浙江电信移动业务接入与ISAG接口实战指南
- 电子密码锁设计：安全便捷的新型锁具
- NavTech SDAL格式规范1.7版：车辆导航数据标准
- Surfer8中文入门手册：绘制等高线与克服语言障碍
- 排序算法全解析：冒泡、选择、插入、Shell、快速排序
资源上传下载、课程学习等过程中有任何疑问或建议，欢迎提出宝贵意见哦~我们会及时处理！
点击此处反馈
