top of page

AI Case Study

Amazon provides customers with product suggestions according to its recommendation algorithm which improves upon machine learning techniques to scale with its large product catalogue

Amazon's recommendation algorithm was developed as an improvement over existing techniques to address their shortcomings and scale to Amazon's large datasets. The product recommendations are used as a marketing tool to encourage repeat customers and increase customer order size.


Consumer Goods And Services

Retail General

Project Overview

Amazon developed its own algorithm in-house, called item-to-item collaborative filtering, to overcome the limitations of existing recommendation algorithms: "Because existing recommendation algorithms cannot scale to’s tens of millions of customers and products, we developed our own. Our algorithm, item-to-item collaborative filtering, scales to massive data sets and produces high-quality recommendations in real time... In the future, we expect the retail industry to more broadly apply recommendation algorithms for targeted marketing, both online and offline. While e-commerce businesses have the easiest vehicles for personalization, the technology’s increased conversion rates as compared with traditional broad-scale approaches will also make it compelling to offline retailers for use in postal mailings, coupons, and other forms of customer communication."

Reported Results

While not disclosing specific results, Amazon claims item-to-item collaborative filtering is fast even for extremely large data sets. Because the algorithm recommends highly correlated similar items, recommendation quality is excellent. Unlike traditional collaborative filtering, the algorithm also performs well with limited user data, producing high-quality recommendations based on as few as two or three items."


"There are three common approaches to solving the recommendation problem: traditional collaborative filtering, cluster models, and search-based methods... Unlike traditional collaborative filtering, our algorithm’s online computation scales independently of the number of customers and number of items in the product catalog. Rather than matching the user to similar customers, item-to-item collaborative filtering matches each of the user’s purchased and rated items to similar items, then combines those similar items into a recommendation list. To determine the most-similar match for a given item, the algorithm builds a similar-items table by finding items that customers tend to purchase together."



Product Marketing


" uses recommendations as a targeted marketing tool in many email campaigns and on most of its Web sites’ pages, including the high traffic homepage. Recommendation algorithms provide an effective form of targeted marketing by creating a personalized shopping experience for each customer. For large retailers like, a good recommendation algorithm is scalable over very large customer bases and product catalogs, requires only subsecond processing time to generate online recommendations, is able to react immediately to changes in a user’s data, and makes compelling
recommendations for all users regardless of the number of purchases and ratings."



Historic customer transaction data, catalogue of product data including customer ratings - " has more than 29 million customers and several million catalog items"

bottom of page