TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Ask HN: Where can I learn how to build a recommender system?

48 pointsby xkyabout 9 years ago
I&#x27;m trying to build a recommender system for news articles. I&#x27;ve read about basic collaborative systems but I&#x27;m looking for something more.<p>Do you know of any good intros to building recommender systems?<p>Thanks HN!

10 comments

vaibkvabout 9 years ago
Why don&#x27;t you try and read some research papers on this topic and then decide how you would want to build your algorithm? Some links -<p><a href="http:&#x2F;&#x2F;static.googleusercontent.com&#x2F;media&#x2F;research.google.com&#x2F;en&#x2F;&#x2F;pubs&#x2F;archive&#x2F;35599.pdf" rel="nofollow">http:&#x2F;&#x2F;static.googleusercontent.com&#x2F;media&#x2F;research.google.co...</a><p><a href="http:&#x2F;&#x2F;insight-centre.org&#x2F;sites&#x2F;default&#x2F;files&#x2F;publications&#x2F;14.095_analysis-recommender-algorithms_15.pdf" rel="nofollow">http:&#x2F;&#x2F;insight-centre.org&#x2F;sites&#x2F;default&#x2F;files&#x2F;publications&#x2F;1...</a><p><a href="http:&#x2F;&#x2F;users.cis.fiu.edu&#x2F;~taoli&#x2F;pub&#x2F;p125-li-sigir2011.pdf" rel="nofollow">http:&#x2F;&#x2F;users.cis.fiu.edu&#x2F;~taoli&#x2F;pub&#x2F;p125-li-sigir2011.pdf</a><p><a href="http:&#x2F;&#x2F;arxiv.org&#x2F;pdf&#x2F;1303.0665v2.pdf" rel="nofollow">http:&#x2F;&#x2F;arxiv.org&#x2F;pdf&#x2F;1303.0665v2.pdf</a><p><a href="http:&#x2F;&#x2F;scholarworks.sjsu.edu&#x2F;cgi&#x2F;viewcontent.cgi?article=1297&amp;context=etd_projects" rel="nofollow">http:&#x2F;&#x2F;scholarworks.sjsu.edu&#x2F;cgi&#x2F;viewcontent.cgi?article=129...</a><p><a href="https:&#x2F;&#x2F;www.ntnu.no&#x2F;wiki&#x2F;download&#x2F;attachments&#x2F;71733389&#x2F;WEBIST_2014_Ozgobek%20Final.pdf?version=1&amp;modificationDate=1400066559000&amp;api=v2" rel="nofollow">https:&#x2F;&#x2F;www.ntnu.no&#x2F;wiki&#x2F;download&#x2F;attachments&#x2F;71733389&#x2F;WEBIS...</a><p>A chapter dedicated to the subject -<p><a href="http:&#x2F;&#x2F;infolab.stanford.edu&#x2F;~ullman&#x2F;mmds&#x2F;ch9.pdf" rel="nofollow">http:&#x2F;&#x2F;infolab.stanford.edu&#x2F;~ullman&#x2F;mmds&#x2F;ch9.pdf</a>
评论 #11607808 未加载
karolisdabout 9 years ago
The book Programming Collective Intelligence has a step-by-step example of how to build a recommendation system. Highly recommended.
评论 #11607991 未加载
评论 #11624274 未加载
siquickabout 9 years ago
Heres an outstanding answer on Stack Overflow on how to implement Collaborative Filtering in MySQL<p>edit: link included<p><a href="http:&#x2F;&#x2F;stackoverflow.com&#x2F;questions&#x2F;2440826&#x2F;collaborative-filtering-in-mysql" rel="nofollow">http:&#x2F;&#x2F;stackoverflow.com&#x2F;questions&#x2F;2440826&#x2F;collaborative-fil...</a>
评论 #11608576 未加载
dserbanabout 9 years ago
One of the Spark-focused EdX courses[0] has a very good module on Alternating Least Squares, that will help you understand how to build recommender systems in a scalable way with Spark.<p>[0] <a href="https:&#x2F;&#x2F;www.edx.org&#x2F;course&#x2F;big-data-analysis-spark-uc-berkeleyx-cs110x" rel="nofollow">https:&#x2F;&#x2F;www.edx.org&#x2F;course&#x2F;big-data-analysis-spark-uc-berkel...</a>
评论 #11606135 未加载
lazyantabout 9 years ago
<a href="http:&#x2F;&#x2F;www.amazon.com&#x2F;Programming-Collective-Intelligence-Building-Applications&#x2F;dp&#x2F;0596529325&#x2F;" rel="nofollow">http:&#x2F;&#x2F;www.amazon.com&#x2F;Programming-Collective-Intelligence-Bu...</a> has a chapter on recommendation systems
vojta1about 9 years ago
I found myself in a similar situation about year and a half ago wanting to learn recommender systems. What worked best for me was the already mentioned coursera recommender system course. Then if you can, go to RecSys conference (this year happening in fall in Boston). Then the absolute go to book for recommender systems is &quot;Recommender systems handbook&quot; - it has second edition that came out last year and this book covers everything from math, practical issues&#x2F;architecture, to industry use cases etc.<p>Good luck!
评论 #11618428 未加载
aaron695about 9 years ago
What you are wanting to do is very hard.<p>Netflix offered a million prize for a movies recommender and then proceed to not use the winning solution.<p>Don&#x27;t underestimate it. It&#x27;s a large investment, don&#x27;t think of it as a side part of a project. It&#x27;s the project.<p>I did the coursea course mentioned in the other comments and it was ok.<p>If I was you I&#x27;d look at some sort of hack. Using mods or something. If it was possible with software on something common like news it&#x27;d be open sourced already.
评论 #11636605 未加载
mystiqueabout 9 years ago
There is a good course on coursera just for recommendation systems. Evaluation of different models is something many algorithm oriented posts don&#x27;t talk about but is covered well in this course.
评论 #11606277 未加载
xkyabout 9 years ago
HN delivers. Thanks for the recommendations. I decided to start with Coursera to get a lay of the land then dig deeper from there.
rajacombinatorabout 9 years ago
Pretty trivial really. If you can&#x27;t deduce the principles, building one from scratch may be inadvisable.