Amazon Web Services streamlines personalized recommendations

Amazon is leveraging machine learning (ML) to help retailers include completely new products and fresh content in their usual recommendations.

Amazon’s Amazon Web Services (AWS) cloud platform is enhancing its Amazon Personalize solution to ease personalized recommendations for fast-changing catalogs of both physical products and digital content. According to AWS, the new changes to Amazon Personalize improve recommendations by up to 50%, measured by click-through rate.

AWS is aiming the enhancements to Amazon Personalize at retailers which continuously add new products and/or content. Rather than showcase all new products in a fast-moving catalog to every customer, Amazon Personalize employs ML capabilities to automatically match new products to specific consumers, based on their interests and preferences. The solution does this by recommending new products to users who have positively engaged (clicked, purchased, etc.) with similar items in the past.

If users positively engage with the recommended new products, Amazon Personalize further recommends them to more users with similar interests. At Amazon, this capability has been in use for many years for creating product recommendations. According to the e-tailer, it has resulted in 21% higher conversions compared to recommendations that do not include new products. 

This capability is now available in Amazon Personalize at no additional cost as part of its existing deep learning-based algorithms. According to AWS, retailers can utilize the new personalization feature with a few click and without needing to change any application code.