Thursday, March 22, 2018

How Amazon’s Algorithms Really Work



The German journalist and author Matthias Matting -- faithfully followed in Europe his "Self-Publisher Bibel" site -- has conducted an experiment to see if he could detect what may affect sales rankings on Amazon.

Matting has kindly written up a shortened edition of his report in English -- Test: How Amazon’s algorithms really work – myth and reality -- and comes up with some signal notions.

He starts with four books nominally named "The Self-Publishers Bible: Knowledge for Authors" and "...News for Authors" and "...Tips for Authors" and "Marketing for Authors." Here is one of them on Amazon.de. These are new titles, which he generated from the previous omnibus work, the "Bible" of each title. Two are priced at 0.99 euros, two at 2.99 euros.

He went in with three expectations. Matting thought he would see, as he writes, that:

  • Price influences sales rank
  • Enrolling in KDP Select influences sales rank
  • The dynamics of sales influence sales rank

He came out with five "facts," and I'll leave you to peruse most of the supporting commentary for each at his site. In quoting him:

Fact 1: Price does not influence sales rank.

Fact 2: Enrollment in KDP Select does not influence sales rank.

Fact 3: An organic growth of sales number results in a higher ranking.

Fact 4: Sales of (much) more than 24 hours are important for the sales rank.

Fact 5: Borrows on Kindle Unlimited influence the sales rank immediately.
.
Some of Matting's most interesting notes tie  to "Fact 4." He writes, emphasis his:

One day without sales decreases the sales rank of a title in the same way as halving its sales numbers. That means the Amazon algorithms devalue a sale by half every 24 hours (approximately, the exact amount is impossible to calculate). Add to this that the sales numbers are increasing exponentially with high ranks and it gets clear how hard it is for a new title to climb into the charts.
.
And as for "Fact 5," what Howey calls "the KU effect" in which Matting sees an immediate impact on sales ranking with Kindle Unlimited, emphasis mine this time:

I couldn’t believe this [at] first. Borrows on Kindle Unlimited are only paid when the user reads at least 10 percent. But for the sales rank, all borrows count immediately...You can reach higher visibility on Amazon without having to wait until a borrower actually reads your book. Even if a borrower never reads your book but only returns it later, you still have a higher sales rank (but you won’t get paid, of course).
His advice, in fact, is that Kindle Unlimited may not be so bad for authors, at least in terms of sales rankings, per his test and observations, emphasis mine:

Twenty sales each day for a week [can] get you higher [in sales rankings] than 150 sales one day and none the [next].

Kindle Unlimited is not as bad a deal as one might think – at least, you get an immediate boost if someone borrows your title.

.

No comments:

Post a Comment

Note: Only a member of this blog may post a comment.