Starbucks has filed a patent for a system that generates personalized recommendations for users based on their propensity for purchasing sustainable items. The system uses machine learning to analyze user account data and generate a sustainability score, which is then used to generate recommendations for both sustainable and non-sustainable items. The recommendations are displayed on the user’s device. GlobalData’s report on Starbucks gives a 360-degree view of the company including its patenting strategy. Buy the report here.

According to GlobalData’s company profile on Starbucks, Intelligent beverage dispenser was a key innovation area identified from patents. Starbucks's grant share as of June 2023 was 1%. Grant share is based on the ratio of number of grants to total number of patents.

A system for generating recommendations for sustainable items

Source: United States Patent and Trademark Office (USPTO). Credit: Starbucks Corp

How well do you really know your competitors?

Access the most comprehensive Company Profiles on the market, powered by GlobalData. Save hours of research. Gain competitive edge.

Company Profile – free sample

Thank you!

Your download email will arrive shortly

Not ready to buy yet? Download a free sample

We are confident about the unique quality of our Company Profiles. However, we want you to make the most beneficial decision for your business, so we offer a free sample that you can download by submitting the below form

By GlobalData

A recently filed patent (Publication Number: US20230196439A1) describes a system for generating personalized recommendations for users based on their sustainability preferences. The system includes a data store and a processor that executes computer-executable instructions.

The system first identifies account data associated with the user, which includes characteristics that define the user's preferences. It then accesses a machine learning model that generates a sustainability score for the user. This score indicates the user's likelihood of purchasing sustainable items. The machine learning model analyzes the user's account data to determine their characteristics and generates the sustainability score based on these characteristics.

Based on the sustainability score, the system generates a set of recommendations for the user. These recommendations include both non-sustainable items and at least one sustainable item. The recommendations are displayed on the user's computing device.

The system can also take into account the user's previous purchases. If the user has previously purchased a non-sustainable item, the recommendations may be influenced by this information.

Additionally, the system can consider metadata associated with the user, such as clusters of users with similar characteristics. This metadata is used to generate a second sustainability score for the user, which further influences the recommendations.

The system allows for dynamic adjustment of the sustainability score based on user responses to the recommendations. If the user responds positively or negatively to the recommendations, the sustainability score can be adjusted accordingly.

The system also includes features such as monitoring a dynamic threshold for the sustainability score, performing reinforcement learning to adjust the score, and updating the user's account data based on the sustainability score.

Overall, this patent describes a system that uses machine learning and user data to generate personalized recommendations that balance non-sustainable and sustainable items based on the user's sustainability preferences.

To know more about GlobalData’s detailed insights on Starbucks, buy the report here.


GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.

GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.