Zeta Global has filed a patent for a computer-implemented method that generates content recommendations for customers. The method involves receiving a content request, retrieving request parameters and user data, routing the request to ranking and optimization components, generating content recommendations based on recommendation scores, and evaluating and optimizing the efficacy of the components. The patent claim has been canceled. GlobalData’s report on Zeta Global gives a 360-degree view of the company including its patenting strategy. Buy the report here.

According to GlobalData’s company profile on Zeta Global, Dynamic premium pricing was a key innovation area identified from patents. Zeta Global's grant share as of September 2023 was 63%. Grant share is based on the ratio of number of grants to total number of patents.

The patent filed is for a computer-implemented method for generating content recommendations

Source: United States Patent and Trademark Office (USPTO). Credit: Zeta Global Holdings Corp

A recently filed patent (Publication Number: US20230319165A1) describes a computer-implemented, network-connected content recommender system. The system is designed to generate content recommendations for multiple content servers associated with one or more customers. The system includes one or more processors and a memory that stores instructions for performing various operations.

When a content request is received from a content server, the system retrieves a set of recommendable resources for the associated customers from the resource data. It then selects multiple recommendation strategies, each including an ensemble model used to generate a recommendation score for each recommendable resource. The system retrieves multiple parameters for each selected recommendation strategy, including learned weights calculated using user data, resource data, and event data for the customers.

Using the selected recommendation strategies, the system determines a recommendation score for each recommendable resource and generates content recommendations based on these scores. The recommendations are then returned to the requesting content server.

The system also includes features such as training a machine learning module using customer data, optimizing weights applied to individual models within each ensemble model, and determining recommendation scores using the optimized weights. The learned weights can be calculated based on previously learned model weightings for an industry segment that includes the customers.

The ensemble models used in the recommendation strategies can include behavioral similarity models that predict user behavior based on the behavior of related users, as well as collab models that predict user interests based on behavioral sequences, user similarities, resource similarities, user-item interactions, and time series data.

The system can also record subsequent interactions with recommended resources, store them as recommendation events, and evaluate the relative efficacy of the recommendation strategies based on these events. The multiple parameters for each recommendation strategy can be updated based on this evaluation to optimize recommendation strategy efficacy.

Additionally, the system can scrape a resources stream associated with the customers to collect information on new resources and store this information in the resource data.

Overall, this patent describes a comprehensive content recommender system that utilizes ensemble models and machine learning techniques to generate personalized content recommendations for multiple content servers.

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

Premium Insights


The gold standard of business intelligence.

Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.


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.