Bottomline Technologies. has been granted a patent for a machine learning application that suggests user actions in payments or banking. The method utilizes algorithms like DensiCube and random forest to analyze user behavior and filter possible actions based on input parameters, enhancing user decision-making. GlobalData’s report on Bottomline Technologies gives a 360-degree view of the company including its patenting strategy. Buy the report here.

According to GlobalData’s company profile on Bottomline Technologies, Dynamic storage rebalancing was a key innovation area identified from patents. Bottomline Technologies's grant share as of June 2024 was 53%. Grant share is based on the ratio of number of grants to total number of patents.

Machine learning for suggesting user actions in banking

Source: United States Patent and Trademark Office (USPTO). Credit: Bottomline Technologies Inc

The patent US11995563B2 outlines methods and systems for automatically suggesting actions to users within a user interface. The primary method involves receiving a set of input parameters and accessing a list of possible actions. The process includes filtering this list to eliminate actions unavailable to the user, followed by looping through the filtered actions. A machine learning model is then executed on each action using the input parameters to generate a machine learning score, which is stored alongside the action. The list of possible actions is subsequently sorted based on these scores. Notably, the machine learning model is developed by iterating through various rule sets using a dataset that encompasses previous user behaviors, which includes data from multiple users. This dataset is utilized up to a certain threshold for individual users before transitioning to data exclusively from the specific user.

Additionally, the patent describes a system that supports this method, comprising a special purpose server connected to a data storage device that retains user behavior history, possible actions, and user behavior models. The server interacts with a computing device via the internet, allowing users to log into an application that sends input parameters to the server. The server then processes the actions similarly to the method described, filtering, scoring, and sorting them based on the machine learning model. The model's development also follows the same principles of utilizing a combination of data from multiple users and specific user data, ensuring a tailored suggestion process that adapts to individual user behavior over time.

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

Data 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.