Recommendations AI
Google Cloud Recommendations AI is a managed service that helps ecommerce websites personalize product recommendations for shoppers. It uses AI and machine learning to analyze shopper behavior, then recommends items that are most likely to be relevant.
Types of Models
Google Cloud's Retail API includes several pre-built AI models. Some models will require ingesting user event data for 60 to 90 days before they can be trained. Each model should be placed on its intended page type for best results.
Serving Configurations
Recommendations AI models can be attached to one serving configuration.
Recently Viewed Items
The built-in, default model that shows products shoppers recently viewed. This model helps shoppers return to items they were considering without searching for them again.
Product Pages Ready Immediately!
Recommended for you
Predicts products that shoppers will most likely engage with or purchase based on their shopping or viewing history. Recommended products highlight options that fit shopper needs and preferences, simplifying the decision-making process.
Home Page
Others you may like
Predicts products that shoppers will most likely engage with or purchase based on their shopping or viewing history and relevance to specific products. These recommendations can introduce complementary or unexpected items that shoppers might not find through normal browsing.
Product Pages
Frequently bought together
Predicts products that are frequently bought together based on product pages visited during the same shopping session. Showing commonly purchased items alongside the product being viewed reduces the need to search for accessories or complementary items separately.
Product Pages Cart Pages
Similar items
Predicts products with attributes similar to the products on the page. Similar items show alternative options when the current product is close but not quite right for the shopper.
Product Pages Quick to Train!
Buy it again
Predicts products for shoppers to purchase again based on purchase history. This is useful for repeat purchases and replenishment experiences.
Any Page
On sale
Recommends products that are on sale based on their current and original prices. "On Sale" sections help shoppers find discounted products.
Any Page
Advanced Model
The Page-level Optimization AI model can be applied to many page types and automatically optimizes the entire page with multiple recommendation panels.
Model Training Frequency
Training a model unnecessarily can create additional Google Cloud costs. Use the default settings for each model and pause model training if storefront traffic becomes stagnant.
Business Objectives
Some AI model types allow merchants to select different business objectives and have different training data requirements. The business objectives are typically one of:
Click-Through Rate
The model will recommend products that optimize for the highest number of clicks on the recommended products.
Conversion Rate
The model will recommend products that are most likely to complete a purchase on the storefront.
Revenue per Session
The model will recommend products that are most likely to increase the amount of revenue generated from each purchase.