Amazon Personalize Enables Developers to Build Applications with the Same Machine Learning Technology Used by Amazon.Com for Real-Time Personalized Recommendations with No Machine Learning Expertise Required
Amazon Web Services, Inc. (AWS), an Amazon.com company , announced the general availability of Amazon Personalize, bringing the same machine learning technology used by Amazon.com to AWS customers for use in their applications with no machine learning experience required. Amazon Personalize makes it easy to develop applications with a wide array of personalization use cases, including specific product recommendations, individualized search results, and customized direct marketing. Amazon Personalize is a fully managed service that trains, tunes, and deploys custom, private machine learning models. Amazon Personalize provisions the necessary infrastructure and manages the entire machine learning pipeline, including processing the data, identifying features, selecting algorithms, and training, optimizing, and hosting the results. Customers receive results via an Application Programming Interface (API) and only pay for what they use, with no minimum fees or upfront commitments.
Now available: Amazon Personalize, enabling developers to build applications with the same machine learning technology used by Amazon.com for real-time personalized recommendations – with no machine learning expertise required
Amazon has pioneered the use of machine learning for recommendation and personalization for more than 20 years. During that time, customers have asked for access to these capabilities so they could enjoy similar benefits when running their businesses. However, the technology can be challenging to deliver effectively across a variety of use cases because there isn’t a single, master personalization algorithm. Each use case – videos, music, products, or news articles – has its own specificities, which requires a unique mix of data, algorithms, and optimizations to create a result. Today’s general availability of Amazon Personalize provides a major step toward putting the power of Amazon’s experience in machine learning into the hands of everyday application developers and data scientists at businesses of all sizes across all industries. Amazon Personalize reduces the time to build a custom model from months to days. When using Amazon Personalize, customers provide the service an activity stream from an application (e.g. page views, signups, or purchases) along with an inventory of the items to recommend (e.g. music, videos, products, or news articles), and receive recommendations via an API. Amazon Personalize does this by processing and examining the data, identifying what is meaningful, selecting from multiple advanced algorithms built and refined over years for Amazon’s retail business, and training and optimizing a personalization model customized to the data. During the whole time, all of the data is kept completely private, owned entirely by the customer.
“We are excited to share with AWS customers the expertise we’ve developed during two decades of using machine learning to deliver great experiences on Amazon.com,” said Swami Sivasubramanian, Vice President of Machine Learning, Amazon Web Services, Inc. “Customers have been asking for Amazon Personalize, and we are eager to see how they implement these services to delight their own end users. And the best part is that these artificial intelligence services, like Amazon Personalize, do not require any machine learning experience to immediately train, tune, and deploy models to meet their business demands.”
Amazon Personalize is available today in US East (Ohio), US East (N. Virginia), US West (Oregon), Asia Pacific (Tokyo), Asia Pacific (Singapore) and EU (Ireland) with additional regions coming soon.
Yamaha Corporation of America (YCA) offers a large assortment of high-quality musical instruments and audio products to U.S. customers. Their products include Keyboard, Guitar, Winds and Strings, Percussion, Professional Audio and Consumer Audio. “Amazon Personalize saves us up to 60% of the time needed to set up and tune the infrastructure and algorithms for our machine learning models when compared to building and configuring the environment on our own. It is ideal for both small developer teams who are trying to build the case for ML and large teams who are trying to iterate rapidly at reasonable cost. Even better, we expect Amazon Personalize to be more accurate than other recommender systems, allowing us to delight our customers with highly personalized product suggestions during their shopping experience, which we believe will increase our average order value and the total number of orders,” said Ishwar Bharbhari, Director of Information Technology, Yamaha Corporation of America.
The Subway restaurant chain offers guests in over 100 countries quality ingredients and flavor combinations with nearly 7 million made-to-order sandwiches created daily. “At Subway, guest experience matters,” said Neville Hamilton, Interim Chief Information Officer at Subway. “Using Amazon Personalize, we can quickly deliver personalized recommendations for our endless varieties of ingredients and flavors to fit the unique lifestyles of our busy guests. Amazon Personalize lets our team use simple API calls to curate recommendations without requiring machine learning expertise. We are looking forward to continuing to work with Amazon Personalize to provide the best experience to our guests who want to eat fresh. We have already successfully tested using Amazon Personalize to provide recommendations to guests making orders from our app, and are excited to expand into personalized app notifications in the near future.”
Zola is the fastest-growing wedding company in the country using design and technology to create the easiest wedding planning and registry experience for couples. “At Zola, we develop innovative wedding planning tools. We want to be there along the entire wedding journey and provide the best possible recommendations to our customers based on their style, interests, or preferences. Until now, those recommendations have been implemented via rule-based ranking, popularity, or more recently, via a similarity model calculated internally. These methods were difficult to maintain and scale. Amazon Personalize provides us with state-of-the-art algorithms and an end-to-end personalization solution that enables us to provide recommendations and personalized content in real time. Being a small team, using Amazon Personalize will allow us to quickly deliver capabilities that would have otherwise taken a much larger team and several months development time,” said Stephane Bailliez, Vice President of Engineering at Zola.
Segment provides customer data infrastructure allowing companies to collect, unify, and connect their first-party customer data to over 200 marketing, analytics, and data warehousing tools with just a flip of a switch. “Today’s consumers expect real-time personalization and recommendations, yet the reality for most companies is that the amount of engineering required makes that experience very hard to create, let alone deliver,” said Tom Pinckney, Head of Partnerships at Segment. “Amazon Personalize brings Amazon’s world-class machine learning technology to every company. By combining it with Segment’s Customer Data Infrastructure, our customers can deliver these highly individualized recommendations at scale and in real time. We have been impressed and plan to extend its functionality for Segment with further integration in the future.”