Recommendations AIbeta

Deliver highly personalized product recommendations at scale.

Recommendations Hero Image

Give customers more of what they love

Earn your customers’ trust and loyalty by proving how well you understand them. Google has spent years delivering recommended content across flagship properties such as Google Ads, Google Search, and YouTube. Recommendations AI draws on that experience to deliver personalized recommendations that suit each customer’s tastes and preferences across all your touchpoints. Ask your Google Account Manager about this limited beta opportunity.

Dramatic improvements to meaningful metrics

Dramatic improvements to meaningful metrics

Recommendations AI uses Google’s latest machine learning architectures, which dynamically adapt to real-time customer behavior and changes in variables like assortment, pricing, and special offers. Early results from retailers around the world have shown dramatic improvements on previous recommendation systems, with some achieving up to the following results.

+90%

click-thru rate

driven by recommendations

+40%

conversions

driven by recommendations

+50%

revenue

driven by recommendations

+5%

total revenue per visit

* Source: Google LLC. Actual results will vary by retailer.

Benefits

Fully managed service

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 up and running fast

Get up and running fast

Integrate your data, configure and launch recommendations, and monitor system performance, all from an easy-to-use graphical interface. Quickly connect data by using existing integrations with Google Tag Manager, Google Shopping, Google Cloud Storage, and BigQuery.

Maximize your data’s value

Maximize your data’s value

Put all your data to work producing great predictions by incorporating unstructured metadata like product name, description, category, images, product longevity, and more.

Choose your strategy

Choose your strategy

Customize recommendations to deliver your desired outcome: engagement, revenue, or conversions. Easily apply business rules to fine-tune what shoppers see, diversify what products are shown, filter by product availability, custom tags, etc.

Deliver at any touchpoint

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 more.

Data Models

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.

Simple pricing

Simple pricing

Pay only for the predictions you consume. Google covers all underlying infrastructure costs.

Automatic global scale

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.

GDPR compliant

GDPR compliant

Recommendations AI is compliant with the General Data Protection Regulation (GDPR). See terms for more information.

Product catalog data

  • Name
  • Description
  • Image
  • Categories
  • Price
  • Discount price + timing
  • Availability
  • Unique identifier
  • Custom features (e.g., brand, franchise)
  • more...

Customer data

  • History of user events
  • User event time, time deltas, sequence order
  • Context: device, domain/URL, month/week/day, etc.
  • Custom features (e.g., retailer-provided demographics)
  • more...

Multiple ways to integrate your data

  • API
  • JavaScript snippet
  • Google Shopping
  • Google Tag Manager
  • Google Cloud Storage
  • BigQuery

Select your recommendation type

  • Recommended for you
  • Other items you may like
  • Frequently bought together
  • Add to your cart/list/registry

Select your objective

  • Click-thru rate
  • Conversion rate
  • Revenue per session

Set business rules

  • Filter out-of-stock items
  • Filter duplicate items
  • Filter by custom tag
  • Result diversification on/off
  • Personalization on/off

Show recommendations anywhere in the customer journey

How It Works

Recommendations AISelect your recommendation type+Select your objective+Set business rules+Multiple ways to integrate your data+Show recommendations at customer touchpoints+Product catalog data+Customer data+Prediction APICUSTOMIZE YOUR RECOMMENDATIONS2DELIVER RECOMMENDATIONS ANYWHERE IN THE CUSTOMER JOURNEY3INGEST YOUR DATA1

How It Works

Product catalog data

  • Name
  • Description
  • Image
  • Categories
  • Price
  • Discount price + timing
  • Availability
  • Unique identifier
  • Custom features (e.g., brand, franchise)
  • more...

Customer data

  • History of user events
  • User event time, time deltas, sequence order
  • Context: device, domain/URL, month/week/day, etc.
  • Custom features (e.g., retailer-provided demographics)
  • more...

Multiple ways to integrate your data

  • API
  • JavaScript snippet
  • Google Shopping
  • Google Tag Manager
  • Google Cloud Storage
  • BigQuery

Select your recommendation type

  • Recommended for you
  • Other items you may like
  • Frequently bought together
  • Add to your cart/list/registry

Select your objective

  • Click-thru rate
  • Conversion rate
  • Revenue per session

Set business rules

  • Filter out-of-stock items
  • Filter duplicate items
  • Filter by custom tag
  • Result diversification on/off
  • Personalization on/off

Show recommendations anywhere in the customer journey

Recommendations AISelect your recommendation type+Select your objective+Set business rules+Multiple ways tointegrate your data+Show recommendations at customer touchpoints+Product catalog data+Customer data+Prediction APICUSTOMIZE YOUR RECOMMENDATIONS2DELIVER RECOMMENDATIONS ANYWHERE IN THE CUSTOMER JOURNEY3INGEST YOUR DATA1

Pricing

Pay only for the predictions you consume. Recommendations AI costs $0.35 per thousand prediction API calls. There is no charge for the first 20K predictions each month. Google covers all underlying infrastructure costs. A small additional fee for surfacing error logs in Stackdriver applies. See pricing details.

Highlights from Google Cloud Next '19

Learn how leading retailers are using Recommendations AI to drive measurable results.

Reinventing Retail with AI
video_youtube
Delivering Highly-Personalized Shopping Experiences on GCP
video_youtube

Resources

This product is in beta. For more information on our product launch stages, see here.

Cloud AI products comply with the SLA policies listed here. They may offer different latency or availability guarantees from other Google Cloud services.

إرسال تعليقات حول...

Cloud Identity for Customers and Partners