Google Cloud for Retailers adds AI-based inventory, e-commerce tools

In a bid to help retailers transform their in-store, inventory-checking processes and enhance their e-commerce sites, Google on Friday said that it is enhancing Google Cloud for Retailers with a new shelf-checking, AI-based capability, and updating its Discovery AI and Recommendation AI services.

Shelf-checking technology for inventory at physical retail stories has been a sought-after capability since low — or no — inventory is a troubling issue for retailers. Empty shelves cost US retailers $82 billion in missed sales in 2021 alone, according to an analysis from NielsenIQ.

The new AI-based tool for shelf-checking, according to the company, can be used to improve on-shelf product availability, provide better visibility into current conditions at the shelves, and identify where restocks are needed.

The tool, which is built on Google’s Vertex AI Vision and powered by two machine learning models — product recognizer and tag organizer — can be used to identify different product types based on visual imaging and text features, the company said, adding that retailers don’t have to spend time and effort into training their own AI models.

Further, the shelf-checking tool can identify products from images taken from a variety of angles and across devices such as a ceiling-mounted camera, a mobile phone or a store robot, Google said in a statement. Images from these devices are fed into Google Cloud for Retailers.

The capability, which is currently in preview and is expected to be generally available to retailers globally in the coming months, will not share any retailer’s imagery and data with Google and can only be used to identify products and tags, the company added.

Improving retail website experience

To help retailers make their online browsing and product discovery experience better, Google Cloud is also introducing a new AI-powered browse feature in its Discovery AI service for retailers.

The capability uses machine learning to select the optimal ordering of products to display on a retailer’s e-commerce site once shoppers choose a category, the company said, adding that the algorithm learns the ideal product ordering for each page over time based on historical data.

As it learns, the algorithm can optimize how and what products are shown for accuracy, relevance, and the likelihood of making a sale, Google said, adding that the capability can be used on different pages within a website.

“This browse technology takes a whole new approach, self-curating, learning from experience, and requiring no manual intervention. In addition to driving significant improvements in revenue per visit, it can also save retailers the time and expense of manually curating multiple ecommerce pages,” the company said in a statement.

The new capability, which has been made generally available, currently supports 72 languages.

Personalized recommendations for customers

In order to help retailers create hyperpersonalization for their online customers, Google Cloud has released a new AI-based capability for its Recommendation AI service for retailers.

The new capability, which is expected to advance Google Cloud’s existing Retail Search service, is underpinned by a product-pattern recognizer machine learning model that can study a customer’s behavior on a retail website, such as clicks and purchases, to understand the person’s preferences.

The AI then moves products that match those preferences up in search and browse rankings for a personalized result, the company said.

“A shopper’s personalized search and browse results are based solely on their interactions on that specific retailer’s ecommerce site, and are not linked to their Google account activity,” Google said, adding that the shopper is identified either through an account they have created with the retailer’s site, or by a first-party cookie on the website.

The capability has been made generally available.