Fully managed service
No need to preprocess data, train or hypertune machine learning models, load balance or manually provision your infrastructure to handle unpredictable traffic spikes. We do it all for you automatically.
Get your project started quickly
Integrate data, manage models, serve recommendations, monitor performance, all from an intuitive graphical user interface. Quickly connect data with your existing tools like Google Analytics 360, Tag Manager, Merchant Center, Cloud Storage, BigQuery.
Take advantage of Google's expertise in recommendations, powered by state-of-the-art machine learning models. They can correct for bias and seasonality and excel in scenarios with long-tail products and cold-start users and items.
Maximize value of your data
Put all your data to work producing great predictions by incorporating unstructured metadata like product name, description, category, images, product longevity, and more.
Deliver at any touchpoint
Offer first-time users and loyal customers alike high-quality recommendations via web, mobile, email, and more, anywhere in their journey from homepage to shopping cart to order confirmation and beyond.
Choose your strategy
Customize recommendations to deliver your desired outcome: engagement, revenue, or conversions. Apply business rules to fine-tune what customers see, diversify product displays, and filter by product availability, custom tags, etc.
Automatic global scale
With one click, you can seamlessly deliver curated recommendations with low latency to customers anywhere in the world. It supports international product catalogs and multiple geographies.
Your data, your models.
Your data and models are yours and yours alone. They’ll never be used for any other Google product nor shown to any other Google customer. You’re never locked in, and can delete your data and models anytime. Learn more.
How it works
IKEA Retail (Ingka Group) increases Global Average Order Value for ecommerce by 2% with Recommendations AI.
1-800-FLOWERS.COM, Inc. uses Google Recommendations AI to deliver personalized recommendations to their shoppers.
Recommendations AI was easy to integrate with our existing recommendations framework, and enabled us to deliver next-gen recommendations without a ton of work. We are steadily investing in data science and it is very helpful for us to be able to integrate and test different algorithms. Recommendations AI performs really well on our product detail pages and increased conversions and revenue significantly.Oliver Herren, CIO, Galaxus
Integrate Recommendations AI into your systems with our trusted partners.
Implementing Recommendations AIFollow this step-by-step guidance for setting up your recommendations solution.
Features and capabilitiesLearn what information Recommendations AI requires and the capabilities of its API.
Recommendation model typesSee what recommendation models are provided by Recommendations AI, their default placements and optimization objectives, available customizations, and supported event types.
Pricing for Recommendations AI is based on operations such as training and tuning (per node per hour) and requesting predictions (per 1000 predictions). Prediction cost is tiered by number of monthly prediction requests.
You can try Recommendations AI with a $600 free credit. This free credit is typically sufficient to train a model and test its performance in production through a two-week A/B test.