Northern Trust has been granted a patent for a system utilizing a k-Nearest Neighbor algorithm to address the cold start problem in recommender engines. The system clusters profiles based on attributes, prioritizes benchmarks, and presents them in a user interface. The system includes an analytics environment and an API environment for efficient operation. GlobalData’s report on Northern Trust gives a 360-degree view of the company including its patenting strategy. Buy the report here.

According to GlobalData’s company profile on Northern Trust, was a key innovation area identified from patents. Northern Trust's grant share as of February 2024 was 73%. Grant share is based on the ratio of number of grants to total number of patents.

Benchmarking system using k-nearest neighbor algorithm for recommender engine

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

A recently granted patent (Publication Number: US11869015B1) outlines a system that includes a computing instance with a server, database, and network storage. The system utilizes a k-Nearest Neighbor (kNN) algorithm to identify subsets of profiles based on similarity across numerical, categorical, and Boolean attributes. These subsets are associated with profile identifiers and used to present a user interface for selecting profiles. Upon user selection, the system accesses quantitative benchmarks related to content, ranks them based on relevance and profile deviation, and presents them in a parent-child structure on the user interface. The system also includes separate analytics and API environments for data processing and user interaction, respectively.

Furthermore, the patent describes a method where a computing instance accesses profiles with attributes, uses a kNN algorithm to identify similar profiles, associates them with identifiers, and presents a user interface for profile selection. Upon selection, the system accesses quantitative benchmarks, ranks them based on relevance and deviation, and presents them in a structured format on the user interface. The method also involves handling missing attributes by prompting user input and adjusting profile subsets accordingly. The user interface features tiles for each benchmark, expandable to show detailed information. The system's design includes separate analytics and API environments for efficient data processing and user interaction, enhancing the overall functionality of the system.

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

Premium Insights

From

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

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.