(Yi et al.2014)
explicit feedback: star ratings
implicit feedback : purchase histories, bookmarks, browsing logs, search patterns, mouse activities ...
hybrid models
text (and context), taxonomies, and user demographics (Bao,Fang, and Zhang 2014; Lu et al. 2015; Kanagal et al. 2012; Qiao et al. 2014).cold start issues
due to the sparsity of real-world datasets.
context-aware recommendations (Schein et al. 2002)
text (Bao, Fang, and Zhang 2014), a user's physical location (Qiao et al. 2014), the season or temperature (Brown, Bovey, and Chen 1997),
Visual personalized ranking
没见过样子,不会买衣服。个人对服装外观风格有喜好。deep learning feature extraction + MF + BPR
item-to-item collaborative filtering,returning customers.
what a user has bought in the past,
which items they have in their virtual shopping cart,
items they’ve rated and liked,
and what other customers have viewed and purchased.
Frequently Bought Together
other items customers also bought.
ON-SITE RECOMMENDATIONS
【小数据】
“RECOMMENDED FOR YOU, THOMAS”
依你特点,刚登录,还未浏览,给你综合个性化推荐,第一界面
BROWSING HISTORY
依你浏览历史,记录,方便来回浏览购买操作
YOUR RECENTLY VIEWED ITEMS AND FEATURED RECOMMENDATIONS – INSPIRED BY YOUR BROWSING HISTORY
依你浏览历史,为你找替代品
RELATED TO ITEMS YOU’VE VIEWED
依你浏览历史,为你找搭配
RECOMMENDED FOR YOU BASED ON A PREVIOUS PURCHASE
依你购买历史,为你推荐替代品或搭配
【大数据】
FREQUENTLY BOUGHT TOGETHER
关联规则找到频繁集的两个商品,并给出一定的组合优惠
CUSTOMERS WHO BOUGHT THIS ITEM ALSO BOUGHT
没有那么频繁的关联商品
THERE IS A NEWER VERSION OF THIS ITEM
产品升级
BEST-SELLING IN “CATEGORY” – ‘DISCOVERY’
新流行产品
OFF-SITE RECOMMENDATIONS WITH EMAIL
follow up they received after browsing ‘Point and Shoot’ cameras on Amazon.com.
“THIS WEEK’S BEST SELLING CANON MODELS”
“THIS WEEK’S BEST SELLING KODAK MODELS”
“BUY A CAMERA PACKAGE”
“BEST SELLERS ACROSS THE ENTIRE PRODUCT CATEGORY” – NO SPECIFIC BRAND