Amazon A9 algorithm: Everything you should know- Signalytics (2023)

Amazon A9 algorithm: Everything you should know- Signalytics (1)

Secrets of the A9 Explained

The science behind Amazon’s A9 algorithm disambiguated

In 2016 the paperAmazon Search: The Joy of Ranking Productswas published by Daria Sorokina and Erick Cantu-Paz. It has since served as the ultimate resource by which the layman can understand how Amazon’s relevance engine, and by proxy the ranking algorithm, works.

We hold that this resource still accurately describes the functions and mechanisms of Amazon’s ranking technology, despite its age. The reason is because since then, only two other relevant papers have been published (Multi-Objective Relevance RankingandMulti-Objective Ranking with Constrained Optimization).

Both of those papers merely build off of the work from the Joy of Ranking by optimizing the algorithm’s performance under multi-objective constraints (basically, some categories and some buyer behaviors must be treated differently as their objectives will be different). This involves optimizing gradient-boosted trees in the relevance algorithms, which is a topic for machine learning scientists, and not Amazon sellers.

Amazon A9 algorithm: Everything you should know- Signalytics (2)
Amazon A9 algorithm: Everything you should know- Signalytics (3)

Get Our Internal Amazon Listing Optimization Operating System HERE 👇

Download the Guide!

As such, we wish to disambiguate the topic as presented by Sorokina’s paper, as well as discuss implications from the perspective of sellers with decades of combined experience.

(Video) Amazon A9 Algorithm | What's Working Now in 2021 for Ranking

Part 1: How the Algorithm is “Programmed”

Amazon A9 algorithm: Everything you should know- Signalytics (4)

There are actually a number of different algorithms that work in-tandem with one another to create the rich complexity that is relevance and ranking on Amazon.

These algorithms are “programmed,” or rather “trained” using customer behavior as well as internal metrics. Essentially, these are machine learning algorithms that are given mountains of historical data from which they are able to make predictions of future action.

Ranking Models

Ranking models are the thing that presents the sorted information when a shopper enters a query on Amazon. There is one model per category per marketplace on Amazon. There are over 100 machine learned models, each optimized with “gradient boosted trees.” Each model has 200 trees.

The mechanism that facilitates ranking is the gradient boosted trees, but for rank problems a pairwise objective is used. This essentially takes the relevance score of a pair of listings and compares them.

All of that to illustrate that the relevance engine is robust and complex, accounting for as many variables and behaviors as possible.

Ranking models are trained using behavioral features, which are customer actions. These features largely impact exactly how rank sort is presented on a browse page.

Aside from customer behavior, another factor in training the ranking models is internal metrics such as conversion rate, basket size, revenue, etc. These are more the hard numbers that prove what worked (or didn’t) as well as steers action toward what will benefit Amazon’s bottom line.

It has been often wondered whether price or revenue had any impact on rank, but after this paper it is not only clear but explicitly stated. Amazon absolutely tailors their customer experience to also benefit revenue (to no one’s surprise).

Behavioral Features

One of the most fascinating aspects of how Amazon determines relevance is its use of behavioral cues. Being the largest online retailer in the US, pushing record sales by inventing a shopping holiday (Prime Day) and innovating the most seamless checkout experience in existence, Amazon has the most robust data set on customer behavior there is.

It would be foolish to not use that data to optimize the shopping experience, and therefore optimize the number of checkouts the marketplace gets.

(Video) SIGCE001 - Amazon Product Research in 2022 with Kevin King

As such, the ranking models are trained with features such as query specificity (the specific searched query and any notes as to shopper intent) as well as “customer status” (seemingly a reference to customer trust score).

The reason behavioral features weight relevance so much on Amazon, much more so than on web search, is because several listings on the platform could have similar descriptions that would fit the same query. Yet, still some listings will be more popular than others. The logic is that those more popular items “should be ranked higher.” It’s only by analyzing behavioral actions can the rank sort deliver the most appropriate rankings for both the shopper and Amazon.

Other Mechanisms

Other mechanisms of the “relevance engine,” as we like to call it, are:

  • Click through rates capture both position bias (accounting for higher position gathering higher clicks by default) as well as typical relevance at that position. Bias correction is also adapted day to day.
  • In an effort to separate product type from modifiers in queries, each query is treated as a noun phrase, with the head of the phrase being treated as the product type and all other words treated as modifiers. This is largely done through detected product types in the queries and in product descriptions (i.e. listing optimization is critical for this reason primarily).
  • Behavioral features can also shift the models from category to category (as fashion shoppers react differently to the search experience than kitchen shoppers, for example).

*A quick note on general search:

Ranking models provide search order within categories. Amazon recognizes, however, that most customers use the “search all” feature on the homepage. So Amazon has created a blended scoring mechanism in an effort to offer search results from multiple categories that may be relevant. Results are offered based on the probability of that relevant search being intended for that category. 90 day click data is used to help determine these probabilities.

Part 2: Features and Labels

Amazon A9 algorithm: Everything you should know- Signalytics (5)

Seemingly counterintuitive, the most purchased product for a query isn’t necessarily the most relevant for that query. The example of this given in the paper is someone searching for the term “diamond earrings.”

The number one seller is often the cheap, cubic zirconium version of the earrings, however it would not be acceptable to present these as the top option in a search for diamond earrings. To combat this, relevance algorithms are given features and labels to tease out a customer’s intention for using a query.


The ranking models start with 150 possible features, which are whittled down to just 50 based on scoring above random. From there the most applicable 20 are used to create the final rank sort for a query.

An example of a feature given in the paper is “days_since_release” which is only applicable to movies. Undoubtedly this feature is used to help determine whether a query refers to an older or newer version, or whether the movie exists yet at all.

Another example is “is_prime_benefit” which helps determine whether a video is available as a benefit for a Prime user (and thus would be relevant to certain searches and show higher in search queries as it enhances the user experience).

(Video) SIGC003 - SEO and Copywriting for Amazon

Other features include behavioral actions such as clicks, purchases, add-to-carts, etc. These are all weighted, but differently based on the model (category, known user intent, etc). The reason is because some category shoppers act differently than others.

A good example of this is a search for the query “iPhone.” The number one clicked result is the latest iPhone, yet that is often not the most purchased. Why? Because it is at its highest price and many shoppers will wait for a price reduction. Actually, the most purchased product for that query is the lightning cable. This is why not every model can be trained to prioritize purchases.


To assist with feature selection data logs of customer actions are used and “labels” are applied to listings. These are binary in nature, providing only positive or negative labels. Positive labels are based on action, whereas negative labels are based on inaction.

For example, someone submits a query and clicks on a listing. That listing got a positive label for the click. However, the other listings that received a page impression (the customer visibly could see it from the search page) but did NOT get a click, those got a negative label.

Listings that were added to cart also got positive labels, whereas listings that were clicked but not added to the cart would receive a negative label. This is how behavior is sorted and tracked so that the proper features are selected and used to ensure each category of customer receives the expected search experience.

Part 3: Match Sets and Cold Start

Amazon A9 algorithm: Everything you should know- Signalytics (6)

Query results are delivered by presenting two types of products; standard and behavioral. Standard matches are textual matches. Behavioral matches are based on products shoppers interacted with in past queries.

The example given in Sorokina’s paper was a search for a movie DVD before it is released. Obviously that DVD cannot be presented since it doesn’t exist yet. When the shopper clicks other movie titles within the same session, those are used to build behavioral models for future query results.

In the above example, the different types of products shown for a query are the “match sets.” The behavioral model results built specifically for queries with little to no relevant product matches, in this example, are what’s called the “cold start.”

Cold start is what has become commonly known in the Amazon industry as the “honeymoon period.” This is a period of time where Amazon’s relevance engine must draw solely on listing information and customer clicks to determine relevance before it has the data it needs.

Every new listing has a cold start, but the amount of time necessary to build relevance for specific keywords will vary based on existing behavioral models. The literature does suggest, however, that seven days is typically the timeframe the algorithms need to fully assess data and determine relevance for most keywords.

(Video) Demo of using a PFR Report for Doing Product Research

Part 4: Implications for Sellers

Amazon A9 algorithm: Everything you should know- Signalytics (7)

To recap, listing sort order, otherwise known as keyword ranking, on Amazon is determined by relevance. Relevance is determined by ranking models. Ranking models are determined per category per marketplace by behavioral features, customer status, and listing data. Features are determined by behavior and labels.

That details exactlyhowthe ranking algorithm works, but how can that information be used?

Well, first it is important to recognize what won’t work. Due to the bias-control it is much harder to manipulate rank position with automated clicks. Due to the behavioral analysis it would also be difficult to manipulate rank with automated actions such as add-to-cart.

The reason for this is because every click, a2c, purchase, or other action is modeled and an expectation is set for every category (and even some sub-categories). And finally, because customer status is a feature, fake orders and poor customer pools will be ineffective as well.

However, note that the paper outlines specifically that the ranking models detect product types from listing information. This means that what WILL work is stellar listing optimization. To further that point, positive labels will be attributed to listings that get clicks and other actions, which will increase with optimized imagery.

Essentially, all of the positive features needed for relevance can be increased with imagery and SEO focused copy.

Aside from optimization, reading between the lines we can also conclude that being direct and unambiguous with keyword selection is advantageous. Basically, the more clearly your product is represented within a category by a keyword the easier it is to gain relevance for that keyword.

Lastly, it is good to know the types of expected behavior for your product’s category. For example, you should be aware, if you sell an expensive product, of whether or not there are keywords people use just for research, versus purchase intent keywords.

And of course, always keep in mind that the more products you can get customers to add to their baskets and the more revenue you can earn for Amazon, the more likely you are to win favor with the algorithms, all other things being equal.

If you need help with crafting the most optimized listing for both Amazon’s relevance engine and your prospective customers, reach out to us. Signalytics accesses the most robust data tools to ensure greater conversions and profits with incredible optimizations.

(Video) Listing SEO’s affect on Amazon Ranking | Top Consultants Debate


How to does Amazon A9 algorithm commonly work in SEO? ›

The A9 search algorithm, as a result, is built on two core tenets: performance and relevance. A product with strong sales performance history will rank higher in Amazon's search results, as will a product that uses the proper keywords to effectively match a customer's search queries.

What is Amazon's A9 stand for? ›

The Amazon A9 Algorithm is the system that powers the Amazon search engine and determines which products to rank within the search results. Amazon's algorithm works similarly to other search engines where it displays results based on keyword search — plus a couple of other factors.

What is A9 and A10 algorithm? ›

Amazon A9 is an old amazon algorithm that helps the sellers on amazon to get a better ranking with search keywords, pay–per–click (PPC), and Amazon's paid adverts. Whereas the Amazon A10 algorithm helps the seller's product rank higher in the search results by the clicking process.

How does the Amazon ranking algorithm work? ›

Amazon's algorithm determines your product ranking by analyzing your product listings, matching them with online shoppers' search queries, and then placing the most relevant ones on the first page of the search results.

How can I become number 1 in SEO? ›

Typically you get to number 1 by having a good online reputation. Well-known brands have good reputations. These brands rank at the top of Google, too. Reputation is increased by the number of quality web pages that link to any page on your site.

Is A9 owned by Amazon? ›

A9, a subsidiary of, was founded in 2003 with an exclusive focus on producing technology for search and advertising.

What is the highest rank in Amazon? ›

Amazon Sales Rank or BSR is ideally ranked from 1 to 1 million. A good Amazon Sales Rank is from #1-3, meaning that you are on the top three results. Now, this means that a potential buyer is more likely to buy yours. In short, the lower your number, the higher your rank is.

What is A10 Amazon? ›

The Amazon A10 algorithm is Amazon's search engine organic ranking algorithm. It takes into account several factors to determine the order in which search results are displayed. These factors include keywords, customer reviews, price, shipping time, etc.

What is A9 and A10 algorithm of Amazon? ›

An outdated Amazon algorithm called Amazon A9 helps Amazon sellers in improving their position through the use of pay-per-click (PPC) and Amazon sponsored ads. The Amazon A10 algorithm, on the other hand, uses the clicking process to assist the seller's goods rank better in the search results.

How do I improve my organic ranking on Amazon? ›

Use Amazon PPC to rank higher for organic results

If you are a new seller or trying to rank for your competitor keywords, using Amazon PPC to rank organically is one of the best strategies. You can target the keywords in your PPC campaigns and this enables you to build organic traffic for the same set of keywords.

What is the most powerful algorithm? ›

Random Forest is one of the most popular and most powerful machine learning algorithms. It is a type of ensemble machine learning algorithm called Bootstrap Aggregation or bagging. The bootstrap is a powerful statistical method for estimating a quantity from a data sample.

Does Amazon pay for 5 star reviews? ›

Amazon's seller guidelines specifically ban offering a financial reward for reviews. It's supposedly a zero-tolerance policy. "I know a lot of sellers who are legitimate who follow the rules who are kind of angry," said Stark.

Is Amazon Listing Optimization Worth It? ›

Amazon product listing optimization is important for sellers because it is the best way to boost product visibility and, in turn, product sales.

How do you become #1 on Amazon? ›

The way to get an Amazon Best Seller badge is by selling the most products within your category over time. The Amazon Best Seller badge is precisely that: an icon displayed in the search results and on the product detail pages for items that are the best sellers in a category.

Can you learn SEO in 3 months? ›

Experts say it usually takes one to three months to learn the foundations of SEO and a year or more to master the practice fully. The length of time it takes to learn the basics of SEO depends upon several factors.

Who is king of SEO? ›

But in the end, the golden rule of SEO is that Content is the King. It is not because of a search engine, but it is for your site visitors. A page that is read by people is better than a page that is read by bots.

Is SEO a high paying job? ›

Highest salary that a SEO can earn is ₹8.0 Lakhs per year (₹66.7k per month). How does SEO Salary in India change with experience? An Entry Level SEO with less than three years of experience earns an average salary of ₹2.9 Lakhs per year.

What are the 3 C's of SEO? ›

Simply put, the fundamentals of SEO can be boiled down to The 3 Cs: content, code and credibility.

What are the 3 pillars of SEO? ›

The Three Pillars Of SEO: Authority, Relevance, And Experience.

Who maintains the A9? ›

Bear Scotland, which maintains the A9, has now moved to quash fears the trunk road had not been sufficiently gritted.

How old is the A9? ›

The road's origins lie in the military roads building programme of the 18th century, further supplemented by the building of several bridges in later years. The A9 route was formally designated in 1923, and originally ran from Edinburgh to Inverness. The route was soon extended north from Inverness up to John O'Groats.

Does China own Amazon? ›

Amazon China (Chinese: 亚马逊中国), formerly known as (Chinese: 卓越网), is an online shopping website. was founded in early 2000 by the Chinese entrepreneur Lei Jun in Beijing, China.
Amazon China.
Type of siteOnline shopping
Available inChinese
OwnerAmazon (2004–present)
3 more rows

How do I increase my rank on Amazon? ›

Now that you understand how Amazon ranks their products, it's time to start optimizing your product listings.
  1. Earn customer reviews. ...
  2. Integrate keywords for Amazon SEO. ...
  3. Upload high-quality images for your Amazon listing optimization. ...
  4. Use the parent-child feature. ...
  5. Optimize the price.

What is an Amazon Tier 1 position? ›

Entry level positions at Amazon warehouses are usually referred to as Tier 1 (T1) or Level 1 (L1) depending on the position and the type of facility.

What is Amazon SERP? ›

What is the Amazon SERP? SERP stands for “search engine results page.” The Amazon SERP shows results to shoppers after they complete a product search on To help boost product rankings on the SERP, optimize your Amazon product listings.

What sorting algorithm does Amazon use? ›

The A9 Algorithm is the system which Amazon uses to decide how products are ranked in search results. It is similar to the algorithm which Google uses for its search results, in that it considers keywords in deciding which results are most relevant to the search and therefore which it will display first.

When did the A10 algorithm start? ›

Amazon's Search Algorithm

Amazon uses a proprietary algorithm for search results. The current version is called the A10 algorithm and was implemented in 2021.

What is Amazon A-to-Z for? ›

The Amazon A-to-z Guarantee provides buyers with an opportunity to obtain a full reimbursement for their purchase or cancel their authorized payment if they are not satisfied with a purchase made on a third-party site using Amazon Payments.

What does the A and Z in Amazon mean? ›

The A-to-z Guarantee protects you when you buy items sold and fulfilled by a third-party seller. It covers both the timely delivery and condition of your items.

How do I create an Amazon action plan? ›

Important Things to Keep In Mind While Writing Amazon POA
  1. Make it short and straight to the point. ...
  2. Divide it into sections. ...
  3. Step-by-step instructions. ...
  4. Don't get bogged down in details. ...
  5. Make use of bullet points. ...
  6. While writing an Amazon action plan, bear in mind that each issue has its own set of considerations.
22 Nov 2021

How do you rank high organically? ›

  1. How to Improve Your Organic Search Engine Optimization Efforts‍ ...
  2. Target Keywords That Match Intent. ...
  3. Don't Be Afraid of Low or Zero-Volume Keywords. ...
  4. Build Topical Authority with a Hub-and-Spoke Content Strategy. ...
  5. Consolidate Pages with Similar Content. ...
  6. Refresh Old Content for a Boost.
2 Sept 2022

How long does it take to rank organically? ›

According to, it can take anywhere from three to six months to rank on the first page of Google, assuming that you're writing good content and optimizing your website for search engines. If there's high competition or you haven't optimized your website, it may take six to 12 months to see results.

What are the 4 types of algorithm? ›

Introduction To Types of Algorithms

Brute Force algorithm. Greedy algorithm. Recursive algorithm. Backtracking algorithm.

Which algorithm is unbreakable? ›

The Advanced Encryption Standard (AES) is a type of symmetric encryption that is considered both the most unbreakable algorithm and the global standard of security.

What is the most advanced AI algorithm? ›

The most advanced AI technology to date is deep learning, a technique where scientists train machines by feeding them different kinds of data. Over time, the machine makes decisions, solves problems, and performs other kinds of tasks on their own based on the data set given to them.

How much do Tier 5 Amazon employees make? ›

The estimated total pay for a Area Manager Level V at Amazon is $121,267 per year. This number represents the median, which is the midpoint of the ranges from our proprietary Total Pay Estimate model and based on salaries collected from our users.

Can Amazon ban you for reviews? ›

We take the integrity of our reviews platform very seriously. If we determine that you have attempted to manipulate reviews or violated our guidelines in any other manner, we may immediately suspend or terminate your Amazon privileges, remove reviews, and delist related products.

Does Amazon negotiate salary? ›

Amazon Initial Equity Package

Equity compensation is a central part of Amazon's total comp philosophy, and it's fully negotiable. It's actually where our clients have made some of the largest improvements in their compensation when we guided them through their salary negotiation with Amazon.

How many keywords should I use for Amazon listing? ›

Put your most important keyword in the header. Your second and third most important keywords will go in your descriptions. If you use the same keyword more than once, it has no effect on your Amazon ranking. If anything, you're wasting space where you could use a different keyword and rank for it.

How do I optimize a+ content on Amazon? ›

What is Amazon A+ content?
  1. Enhanced Product Description.
  2. Brand Story Content.
  3. Ensure customers know what they are getting.
  4. Elaborate on your product's features.
  5. Show customers how the product fits in their lives.
  6. Compare different products in your brand.
  7. Tell your brand's story.
  8. Introduce your other products.
15 Aug 2022

Is promoting listing worth it? ›

Yes. Promoted Listings are a great tool for boosting your items in the search results, and can have a really positive impact on sales. Depending on how competitive your product category is, Promoted Listings may not secure as many additional sales as you hope, but it should still have an effect.

How many followers do you need to make money on Amazon? ›

There isn't a specific follower count needed to earn money from influencer marketing. It still depends on the brand. Some brands look into your number of followers, while others look into your engagement rate. It can be anywhere between 1,000 to 1,000,000 followers to get paid.

What people buy most on Amazon? ›

Best Selling Categories on Amazon
  • Gift Cards. ...
  • Electronics. ...
  • Camera and Photography. ...
  • Video Games. ...
  • Books. ...
  • Clothing, Shoes, and Jewelry. ...
  • Beauty and Personal Care Products. ...
  • Home and Kitchen.
15 Nov 2022

What is 1-Click ordering on Amazon? ›

1-Click ordering places Amazon customers' orders automatically so they can skip the shopping cart, simplifying their shopping experience.

Does Amazon A+ content help with SEO? ›

Amazon A+ content is one of the best ways to elevate Amazon SEO by optimizing the product content by using high-quality images and visuals. The Amazon A+ content templates guide you and offer several modules that use meaningful and informative content to highlight your product and the brand.

What SEO does Amazon use? ›

Amazon SEO is the practice of optimizing your product listings for Amazon's ranking algorithm, A9. These optimizations include using keywords (or search terms) in a product listing's title, uploading high-quality photos, setting competitive prices, and more.

Which algorithm is used in SEO? ›

What is a Google algorithm for SEO? As mentioned previously, the Google algorithm partially uses keywords to determine page rankings. The best way to rank for specific keywords is by doing SEO. SEO essentially is a way to tell Google that a website or web page is about a particular topic.

How does Amazon A10 algorithm work? ›

The Amazon A10 algorithm is Amazon's search engine organic ranking algorithm. It takes into account several factors to determine the order in which search results are displayed. These factors include keywords, customer reviews, price, shipping time, etc.

Does Google index Amazon A+ content? ›

So make sure to include keywords in other parts of your listing. However, the information and images included in your Amazon A+ Content are indexed by Google. This means it can appear in Google search results, so it's still worth optimising your content for search.

Is Amazon A+ content worth it? ›

Amazon A+ content is one of the most effective and important ways to increase customer trust, boost conversion rates, and acquire a higher ranking on Amazon SERPs (Search Engine Results Pages).

How long does it take to review a+ content? ›

How long does it take for A+ Content to be approved? It varies. A+ Content approval can take up to seven days, but we have also seen content approved within a matter of hours. Keep an eye on the status of your content within Seller Central.

What are the 3 algorithms? ›

An algorithm is made up of three basic building blocks: sequencing, selection, and iteration.

How many clicks does Amazon get per day? ›

Just like it sounds, daily clicks are the total volume of clicks on your ads per day. The average daily clicks on Amazon is around 382 per user. Impressions naturally lead to clicks.

How do I avoid A to Z guarantee on Amazon? ›

You can also protect your account health by using Amazon Buy Shipping Services. If you ship on time with Buy Shipping, you'll be protected against A-to-z Guarantee claims related to delivery issues. If a claim is granted for this reason, it won't impact your account health.


1. This Secret Amazon KDP Keyword Tool Helps You Double Or Triple Your Profitable Keywords
(Hurricane Liz)
2. Amazon FBA Ranking Service Assists Sellers to Boost Listing Position
(Super Buzz Daily)
3. Ranking Techniques for Private Label Sellers in 2021 | Anthony Lee | Ep. 182
(Norman Farrar)
4. Howard Thai at the Seller World Conference 2019 - Bangkok Thailand
(Howard Thai)
5. The Ultimate Product Launch that Nobody Dares To Talk About - Howard Thai
(Sellers World Conference)
6. Amazon to eBay Dropshipping Automation Software | Find & List products in BULK [Beginners Guide]
(ZIK Analytics)
Top Articles
Latest Posts
Article information

Author: Frankie Dare

Last Updated: 27/06/2023

Views: 5579

Rating: 4.2 / 5 (53 voted)

Reviews: 92% of readers found this page helpful

Author information

Name: Frankie Dare

Birthday: 2000-01-27

Address: Suite 313 45115 Caridad Freeway, Port Barabaraville, MS 66713

Phone: +3769542039359

Job: Sales Manager

Hobby: Baton twirling, Stand-up comedy, Leather crafting, Rugby, tabletop games, Jigsaw puzzles, Air sports

Introduction: My name is Frankie Dare, I am a funny, beautiful, proud, fair, pleasant, cheerful, enthusiastic person who loves writing and wants to share my knowledge and understanding with you.