After the class we learn last week, I have a new idea about how we make decisions with the help of recommend system. We usually rely on some suggestions and recommendations when we make decisions, and we face many information that we can not breath well. With the information overload, how can we make a good decision and what we can we make to filter information, and identify items which are relevant to us.
There are three ways that we can use, respectively they are recommender systems, recommendation systems and recommenders. First of all, I want to talk about the recommendation systems. There is an extensive class of Web applications that involve predicting user responses to options. Such a facility is called a recommendation system. The goal of a Recommender System is to generate meaningful recommendations to a collection of users for items or products that might interest them. Suggestions for books on Amazon, or movies on Netflix, are real world examples of the operation of industrystrength recommender systems. The design of such recommendation engines depends on the domain and the particular characteristics of the data available.
There are also three types of recommender systems. They are contentbased recommendation, collaborative filtering recommendation and hybrid approaches.
Contentbased recommending: These approaches recommend items that are similar in content to items the user has liked in the past, or matched to attributes of the user.
Collaborative Filtering (CF): In CF systems a user is recommended items based on the past ratings of all users collectively.
Hybrid approaches: Thesemethods combine both collaborative and contentbased approaches.
As we continue to integrate more information into recommender systems, and as we expect them to adapt to greater contextual challenges, the problems of algorithmic and system scalability only grow. A key challenge to the field of recommender systems as a whole is the integration of contentbased approaches, collaborative approaches and contextual approaches into comprehensive, practicalrecommender systems. We are already seeing indications of strong interest in this direction. One longrunning challenge is to recommend the next item in a sequence of items to be explored. Such a recommender requires not only ratings of the individual lessons, but also information on sequence and dependency. Similar challenges exist with other forms of context and with recommenders that hope to tap the wide range of implicit behavior that can today be recorded through web browsing behavior.

Wow!You already finished this assignment.The picture you use is so cute.I'd like to talk about recommendation systems as well, so you kind of inspired me.Wish i know what to write.......
回复删除Hi,xiaoxiao!After reading your essay,I found that you have a really brilliant idea on recommendation systems.Meanwhile I agree with you on that filtering information really matters in this system.You mentioned three ways to recommend information in a social media, recommender systems, recommendation systems and recommenders respectively.I am really interested in what you referred.May be we can have a brief communication on that!Many thanks.
回复删除The measures mentioned of recommend system are useful for me. The picture you cited is so lovely, and I love Mario very much. We have so much to study in coming days.
回复删除Hi, Xiaoxiao. Having read your blog, I have to say you really have a profound understanding about recommendation system. And the three ways mentioned by you are clear and useful. Could you please tell me when you are free and we can have further discussion. Thanks!
回复删除Hi, The recommend system is indeed very important and this post is very helpful to me, I have learned skyline as a recommend system, and it's sounds very awesome, if you are interested in this field, try and see:)
回复删除Very good blog about recommendation system. It is not hard to find out that you really took a lot of time on it and did a very good job in this course. I agree with you that everything happen with challenge including recommendation system. Similar challenges exist with other forms of context and with recommenders that hope to tap the wide range of implicit behavior that can today be recorded through web browsing behavior.
回复删除Hi, fanghanxiao. After reading your blog, I have to say you really have a profound understanding about recommendation system.Thank you for sharing.
回复删除Hi, hanxiao, I think your understanding of recommending system is really nice, which is of use to me. and I also appreciate the way in which you organize the content of your blog. I can get the core point about your article in the shortest time.
回复删除