Tips and Tricks - Amazon Recommendations

2012-Jul-25 -> from the free-advice-take-it-or-leave-it department Tags: tipsandtricks writing amazon 

Amazon is the great mystery of our time. They are so secretive about their algorithms and inner workings that it's very difficult to tell why certain books launch to the top while other possibly better books languish in the nether regions of their rankings. I'm here today to shed some light on at least one part of the mystery, but bear with me... this is going to get technical. VERY technical.

What Recommendations?

If you're not sure what I'm talking about, you should stop reading right now, go to Amazon, and look at any page, even their home page. Everywhere you look on Amazon, you'll see "More Items to Consider", "Customers Who Bought This Item, Also Bought...", "Inspired By Your Wishlist", or any number of other recommendation lists that they feed you while browsing. These lists are where you want your book to be.

"Why?" you ask? Because these are going to be some of the best recommendation lists that you will ever encounter. Seriously. The technology that goes into creating these lists is unmatched by any other site in the industry, except maybe Netflix. These lists will sell your books, I guarantee it. You just need to get your book there.

Oh, sure. Is that all?

Thing is, Amazon wants to sell your book. They want to sell everyone's books. They want to sell millions and millions of everyone's books. Know why? Because they make lots and lots of money. How do they make sure they sell the maximum number of books possible? By creating really, really good recommendation lists. Don't believe me? They're not the #1 book seller in the world for no reason.

Item-to-item Collaborative Filtering

Holy crap. I hit you right over the head with those great big words. Here's where the technical stuff starts. Put on your hard hat, and watch for falling math.

Amazon has some of the biggest data stores in the world. They keep track of everything. Every item that you've ever purchased, when it was purchased and for how much. Every item you've ever clicked, what you clicked after that, how often you visit certain pages, how often you purchase an item after visiting the page, and how many times you visited the page before you bought it. Thing is, Amazon is greedy. They don't like to share data, because that's their competitive edge over everyone else.

I don't blame them.

Their recommendation system is based on one thing and one thing only, and it's really very simple when you tear it down to just this: who bought what items. But they don't even care about who bought what, all they really care about is how many people bought the same two items.

Here is the basic algorithm, in all it's glory:

For any Item (Item_X), compute a list of items that have the most in common, according to sales.

This list is computed based on something called a Commonality Index (CI). The CI of any two items (Item_X,Item_Y) is calculated using the following equation:

CI(Item_X,Item_Y) = Ncommon / √(Nx * Ny)

Take 3 items:

  • Item_X = purchased 300 times (Nx)

  • Item_Y = purchased 200 times (Ny)

  • Item_Z = purchased 30000 times (Nz)

Find which item (Y, or Z) has the most in common with Item_X, where:

  • Ncommon(Item_X, Item_Y) = 20

  • Ncommon(Item_X, Item_Z) = 25


  • CI(Item_X,Item_Y) = 20 / √(300 * 200) = 0.08165

  • CI(Item_X,Item_Z) = 25 / √(300 * 30000) = 0.00833


Item_X has MORE in common with Item_Y than Item_Z, even though Item_X and Item_Z have more common purchasers.

This is important. It means that you have no immediate hope of being paired with Item_Z until you have a fair number more purchasers in common. Want to be recommended to people who buy the big guns at the top of the list? You need to get MORE people who buy the top books to also buy your books. In this case, Item_X and Item_Z would have to have almost 250 common purchasers in order to top CI(Item_X, Item_Y), and get recommended over it.

But Wait, There's More!

It's still not as simple as just a single score, and you had to know it wasn't. So what's the catch?

Your sales have an expiry date. That's right. When working out the recommendation list, Amazon only considers the last six months' worth in sales data. By doing this, they keep the recommendations fresh. They don't sell books by recommending what was popular last year. They want to show you what's popular now.

The rest of the recommendation lists are figured out based on what you've looked at recently, what you've bought recently, what's currently in your cart, what's currently in your wishlist, what products you've marked as "liked", and what products you've reviewed. Each of these factors produces a different list of items based on the same equations above.

Lighting the Fire

So how do you take this information and use it to light the Amazon Recommendation fire?

Two Words: Targeted Marketing.

Most people don't know what that means. Do some research, and get started today. I'll do that as well, and will bring you another post later on, all about it.

Good luck!

I hope this helps at least some of you out there. If you're looking for a way to help me out and spread the word, clicking the Tweet and +1 buttons below are quick and simple ways that I would greatly appreciate!

Thanks for reading!

I'm always interested in hearing what you have to say. Contact Me, I'd love to hear from you.

Don't forget to join in on the conversation in the comments section below.

17 Comments(74 Pending Approval):

By Ia Uaro on Thu 26 Jul 2012 01:15:31 am [ Reply ] Thomas. Very informative and helpful for planning the marketing, prompting me to research more. Thanks heaps!

By Jody on Thu 26 Jul 2012 07:39:14 am [ Reply ] Okay, the truth is that I don't COMPLETELY follow this (it's a bit like when I've heard Brian Greene describe string theory -- I only sort of get it). But...I'm not sure it matters as long as you do the follow up article explaining how the heck we can "Target Market."

I'm waiting, eager.

(Thank you -- I retweeted --)

By Cynthia Echterling on Thu 26 Jul 2012 08:47:43 am [ Reply ] Waiting with bit on my breath!

By Cynthia Echterling on Thu 26 Jul 2012 08:48:29 am [ Reply ] bait

By Catherine Kirby on Thu 26 Jul 2012 09:06:38 am [ Reply ] Thanks for this Thomas. I look forward to the Target Market piece. Well done!

By Thomas A. Knight on Thu 26 Jul 2012 10:12:18 am [ Reply ] Thanks for the comments, everyone. And thanks for dropping by. This post has been in the works for a while now, but I wanted to make sure I had all my facts straight, and understood it all myself before I tried to help other people understand it.

Good luck to you all in all your prospects.

By Rodney Walther on Thu 26 Jul 2012 10:31:09 am [ Reply ] This is my understanding of how the algorithms work as well (esp. Item-to-item Collaborative Filtering). It's all good to know, but the key is to facilitate this matching by making sure that the people positively predisposed to your work find out about your work. I still believe that Amazon is "The Most Amazing Salesman Known to Man" and this is why.

By Rodney Walther on Thu 26 Jul 2012 10:35:51 am [ Reply ] By the way, this is one of the most concrete reasons NOT to offer one's book for free. When Amazon looks at the shopping carts of your readers and can't really make heads or tails of them, you'll end up having Amazon recommend your book against a disparate collection of books, many of which haven't sold many copies. Self-pubbed authors should really want their TARGET reader to buy their book, not ANY reader.

By Thomas A. Knight on Thu 26 Jul 2012 10:38:25 am [ Reply ] I couldn't agree with you more, Rodney.

This has to do with targeted marketing. Getting your book into the hands of the people who are most likely to have bought books similar to yours.

There are ways to do free promos and still accomplish targetting, but yeah, you still end up with a bit of a mish-mash in your product's customer list which can damage your chance at getting recommended to the right people.

By Aubrey Hansen on Thu 26 Jul 2012 11:58:22 am [ Reply ] This is amazingly helpful! Thanks so much for putting this together. I always get something out of your book marketing posts. :)

By Rodney Walther on Thu 26 Jul 2012 12:41:32 pm [ Reply ] Let me give you an example of how recommendations pay off. I hope this is illustrative and not spammy.

My book (Broken Laces) has been compared thematically to works by Jodi Picoult and Nicholas Sparks, in that they are emotional family dramas with damaged protagonists. I believe the comparison to Jodi Picoult is more apt based on our writing style. So, the person who enjoys those kinds of books is predisposed to enjoy mine.

For reasons that are known only to Amazon (and Thomas apparently!), I have been fortunate that my book has pretty much been identified by Amazon as a read-alike for Jodi Picoult and other similar writers: Nicholas Sparks, Maria Rachel Hooley, Diane Chamberlain, Jennifer Weiner, If you look at "Customers Who Bought xxx Also Bought yyy" for my book, you'll find that of 95 suggested books, 21 of them are for works by Jodi Picoult and 15 for Nicholas Sparks. This makes sense and is very helpful to my sales.

But you want to know what's over-the-moon awesome and what really drives sales? Look at the flip side for the heavy hitters (Jodi Picoult and Nicholas Sparks books). My book is on THEIR "Customers Who Bought xxx Also Bought yyy" list. In fact, Broken Laces is the #1 suggestion for Picoult’s Plain Truth and #2 for her latest (2012) novel Lone Wolf, ahead of other books by Picoult herself!

Plain Truth
Lone Wolf
Broken Laces

Amazon’s algorithms are also self-fulfilling to some degree. Amazon suggests Broken Laces to a Jodi Picoult reader, which causes a Picoult reader to buy it. So Amazon adds another Picoult->Walther link to its magic database, which reinforces the suggestion again the next time. (“And they tell two friends… and they tell two friends…”). FYI, I had no idea how much readers take Amazon’s suggestions to heart—I’ve actually had reviews from readers who “accidentally” (their words) bought my book based on Amazon’s word.

By Amber Dane on Thu 26 Jul 2012 02:02:42 pm [ Reply ] Good post!

By Uvi Poznansky on Thu 26 Jul 2012 09:08:33 pm [ Reply ] Excellent post.

By Will Belacqua on Fri 27 Jul 2012 10:36:23 am [ Reply ] So... much... math...

Haha, but seriously, this was very informative! For someone who only recently got into self-pubbing and marketing and all that, you're very knowledgeable and helpful. :)

Oh, and Rodney, that's excellent about Broken Laces! It's always nice to hear about a fellow ABNA participant getting some awesomeness :)

By trend wedding on Thu 16 Aug 2012 01:29:44 am [ Reply ] This is exactly what I need:) Awesome collection of wedding blogs..

By L.A. Rikand on Fri 5 Oct 2012 08:16:45 pm [ Reply ] I'm frightened by your math, Thomas. And a little scared that I understand it. If everyone who bought my book would now go out an buy The Fault In Our Stars...and vice versa...I'm very much appreciate it. Thank you.

By L.A. Rikand on Fri 5 Oct 2012 08:17:49 pm [ Reply ] Good God, I need some sleep. Can't. Spell.

Back To Top

Leave a comment:
Name (required)
Email Address (required, will not be shown)
Web Site
What's 10 + 6?
Current WIP: approximate numbers only, working titles
The Spell Breaker:
65% (Writing... 64,860/100,000 words)