Recommendation system is the basis of
statistical speculation or statistical inference, or more generated-machine
learning. This field is now developing rapidly, attracting many CS students to
do research in. However, if we really want to get the consumers satisfied, apart
from the aspect of SVM and neural network algorithms, this matter is heavily
dependent on the following areas.
Satisfaction is a very vague concept. Maybe
we can define it in this way-the a consumer can have an experience of excited feeling
on upon catching sight of what’s just in
his subconsciousness. But this requirement is too high. It is possible for him
to choose from the scope of which there is simply not the commodity that
satisfies him. Such as Douban Radio, if he does not like to listen to classical
music, whatever strong the recommendation algorithm is, he still can not be satisfied.
In this case, no matter how well the recommender knows of him, it is difficult
to give an answer.
Fortunately, there is recently a new trend
among start-ups in Silicon Valley. They combine human recommendation and
machine recommendation, which is also one key factor for Facebook and Twitter
to be so charming. With the help of the deep developed API of Facebook and
Twitter, those start-ups are reading our friend posts to enhance their training
model for recommendation. This can have bad impacts also. If one have too many
friends on Facebook or too many followers on Twitter, there can be some noise
if a recommendation system has referred to it. This combination can be
beneficial but can not solve all the problems.
The amount of data is growing fast this
decade which can be a decade of fast user accumulation in the circumstance of
Web 2.0. Statistics speculated that the most critical user data, which basically
can not make bricks without straw in web 2.0. With the rapid development of the
mass storage and concurrent systems, we can have a lot of data to be excavated.
To sum up, the recommendation system is indeed much more practical than pure
algorithms thus requiring a good mixture of the real demand and algorithm
optimization.
What a profound essay! Along with the growing amount of data, we meet more challenges in technology. We are to gain more and more knowledge to solve problems.
回复删除Hello, Tianyu. With the development of the Internet, its structure becomes more and more complex. It’s hard for people to find useful information. So how to improve directions of recommendation system is so important!
回复删除You mentioned recommender system, and explain it with the help of amazon, I think it is a very good article I have ever read, and you make me learn more things about the recommender system, thanks a lot.
回复删除Hi, Tianyu. I find your blog really useful for me, especially your description of satisfaction. I agree with you on satisfaction is a really vague notion.Meanwhile, you mentioned a new method to recommend which is the combination of human recommendation and machine recommendation. I think it very good.
回复删除此评论已被作者删除。
回复删除Hi Tianyu~ I'm totally attracted by your blog! It's really useful and you're very nice to share the wonderful idea with us. If the recommendation system can't satisfy our real demand, I think we will gradually be tired of so much useless recommended information. Also API will be optimized and deep developed. Hope to share more ideas about this course with you:) I will trace your blog and also you are welcome to come to my blog to have some discussion about this course.
回复删除Thanks for your share ,which is a really useful paper,you mentioned a new method to recommend which is the combination of human recommendation and machine recommendation.that is a really worthy point.
回复删除Recommendation system is very important in this internet era. Social media websites have much data, good recommendation algorithm can handle information overload but it may be difficult to deal with long tail problem. You mentioned combining human recommendation and machine recommendation, I think it's a great idea to improve recommendation System.
回复删除The combinatiion of human recommendation and machine recommendation method which you mentioned in your blog is really new to me.Thanks for your sharing!
回复删除Recommender systemsare a subclass of information filtering system that seek to predict the rating or preference that user would give to an item,which is so popular nowadays, the method you mentioned about combination is great and I learn a lot from your blog.thanks~
回复删除In nowadays internet Web2.0 . People like to interact with each other on the Internet. Lots of information came up to the web, that's why people want to use more efficient way to collect about it.
回复删除It is an interesting topic for me. Recommendation system contains algorithms about how to catch individual person's emotion and preferances. It needs more complex methods to deal with it.
回复删除Very creative idea. Made me think about my methods to evaluate the services I use. For people in the real world choose products using the comparison criteria, ie, seek to know the quality of both their prices and thus to draw their own conclusions. The traditional means as cited in the text is flawed, because people may make different decisions depending on your emotional state.
回复删除