Bank of New York Mellon. has filed a patent for a system using multiple machine learning models to detect anomalies in historical data values. The system can reduce false positives and negatives by training models to detect different behaviors of the same metric, providing robust multi-metric anomaly detection. GlobalData’s report on Bank of New York Mellon gives a 360-degree view of the company including its patenting strategy. Buy the report here.

According to GlobalData’s company profile on Bank of New York Mellon, Corrosion resistant battery packaging was a key innovation area identified from patents. Bank of New York Mellon's grant share as of January 2024 was 90%. Grant share is based on the ratio of number of grants to total number of patents.

Anomaly detection system using multiple machine learning models

Source: United States Patent and Trademark Office (USPTO). Credit: The Bank of New York Mellon Corp

A newly filed patent (Publication Number: US20240036963A1) describes a system that utilizes multiple machine learning models to detect anomalies in historical data values of a metric. The system includes a processor programmed to access data values, provide them to the machine learning models, generate anomaly scores based on different behaviors of the historical data values, and aggregate these scores to predict anomalies. Additionally, the system can identify mitigative actions and sources of data values based on stored associations. The processor can also determine the duration of anomalies and generate duration scores positively correlated with the duration.

Furthermore, the system allows for the pluggability of machine learning models, enabling the addition or removal of models to adapt to different anomaly detection requirements. By adding or removing models, the system can update the plurality of machine learning models to improve anomaly detection accuracy. The system's capabilities include normalizing anomaly scores, generating aggregate scores, and providing indications for investigative, warning, or escalation actions based on the anomaly predictions. Overall, the system offers a comprehensive approach to anomaly detection in historical data values, enhancing the accuracy and efficiency of anomaly prediction processes.

To know more about GlobalData’s detailed insights on Bank of New York Mellon, 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.