Jan 9, 2013

Product Recommendation by Amazon

Amazon is quite secretive about its technology. While researchers from other companies publish many papers on their approaches, we seldom see papers from Amazon. However, we can still infer about its technology by looking at their products in action. In this blog, we take a look at how Amazon makes recommendation to it users.

Users who purchase on Amazon typically get the following two "recommendations" at the bottom of product page: (1)"Frequently bought together" and (2) "Customers who bought this item also bought".

Strictly speaking, showing what are frequent bought together does not require complex recommender systems. This is a simple counting of frequent itemsets, a very fundamental technique taught on the first day of data mining class. This technique is also called Frequent Pattern Mining. The key challenge here is getting all of those "bought together" sets quickly from billions of transactions.

However, Amazon does provide more personalized recommendation, similar to what Netflix does. After you log in, there is a"recommended for you" page where Amazon's recommendation engine is in full action.

How does it Amazon make this recommendation? Based on a 2003 article published on IEEE Internet Computing (Jan/Feb issue), the company uses item-item similarity methods from collaborative filtering. At that time, this was state-of-the-art method, and Amazon was pioneering the field of recommender system.

It seems this same implementation has been in use in Amazon until today. As we can see from the picture to the left. The snapshot was taken in January 2013.  The first product (Girl’s 7-16 Jacket) is recommended because the user purchased a somewhat similar item (Girls 2-6x Princess Jacket). Similar thing is true for the second recommended product. In other words, item-item similarity is a major technology used by Amazon's recommendation engine.  

The field of recommender systems have seen great advance since 2006's Netflix Prize contest. From 2006 until 2009 when the prize was awarded,  many methods have been invented to tackle recommendation problem. Among them, the most widely adopted method today is Matrix Factorization (with SVD as a special implementation). It was shown that this method generated better results than item-item similarity approach. Netflix adopted matrix factorization method after 2007, and has been using it in its production system until today. 

Both item-item similarity and matrix factorization approach have been eclipsed by other approaches in the last 2 years. Netflix itself has moved into a machine-learning based ranking model, and others (such as getJar, see an early blog) have explored neighborhood-based methods.

Would Amazon adopt more sophisticated methods to make its recommendation? Given its business is doing so well with simple methods, this probably will not happen soon.


  1. This comment has been removed by the author.

  2. This article has covered the topic quite well. Very informational and interesting. Thanks for sharing this knowledge with us.

    new year, new year images, new year wallpapers, new year quotes, new year wishes, new year sms, new year greetings, whatsapp status

  3. This comment has been removed by the author.

  4. We more likely than not read it about how to keep safe, utilize this web security and utilize that antivirus, ye her is example of this article about it be that as it may, once you are tainted with something like a rootkit they won't generally benefit any occupation.

  5. good a Raspberry Pi the installation is definitely even more challenging. kodi apk There is definitely another technique to set up nice.

  6. good One of them is definitely the capability to access Kendall Jenner Snapchat the tiny crew of Stanford Collage. This program nice.

  7. Thanks for sharing this amazon products
    download kodi

  8. Can one jailbreak iOS 10 / iOS 10.0.2 / 10.0.1? If not, what is latest on iOS 10 / 10.0.2 jailbreak status for iPhone, iPad and iPod touch devices? you can get answer of this Question as now you can get iOS 10 jailbreak.

  9. good scanned using the rear video camera of your telephone, WhatsApp Online Login that payment features been taken out rendering it totally free of charge for lifestyle. nice.

  10. good Just download and install the shareit.exe file shareitforpcdl we require to share any kind of type of files like records nice.

  11. good complete then established the exact same on your wise device Playstore download There are numerous sites which offer apk documents for nice.

  12. Hey – great blog, just looking around some blogs, seems a really nice platform you are using. I’m currently using WordPress for a few of my blogs but looking to change one of them over to a platform similar to yours as a trial run. Anything in particular you would recommend about it?

  13. Hello there! This article couldn’t be written any better!
    Looking at this post reminds me of my previous roommate!
    He continually kept talking about this. I most
    certainly will forward this post to him. Pretty sure he will have a good read.

    Thank you for sharing! Jaket Parka | Grosir Jaket Parka | Grosir Jaket Parka | Grosir Jaket Parka

  14. This is a great article thanks for sharing this informative information. I will visit your blog regularly for some latest post. I will visit your blog regularly for Some latest post. product ranking service

  15. Packers and movers in thane@
    Packers and movers in varanasi@
    Packers and movers in surat@
    Packers and movers in lucknow@

  16. Thanks on your marvelous posting! I really enjoyed reading it, you’re a great author.Please visit here:
    Packers And Movers Hyderabad

  17. Nice blog…thanks for sharing…its very interesting…
    i’m searching for this information from long time…Packers And Movers Ahmedabad

  18. Really impressive post. I read it whole and going to share it with my social circules. I enjoyed your article and planning to rewrite it on my own blog.
    Packers And Movers Gurgaon