Sift Science has patented a system and method for accelerating the resolution of digital dispute events using machine learning-based models. The technology routes disputes to specific models based on historical data, computes preliminary dispute inferences, generates response artifacts, and updates inferences based on evidence data. GlobalData’s report on Sift Science gives a 360-degree view of the company including its patenting strategy. Buy the report here.

According to GlobalData’s company profile on Sift Science, AI-assisted threat classification was a key innovation area identified from patents. Sift Science's grant share as of April 2024 was 83%. Grant share is based on the ratio of number of grants to total number of patents.

Machine learning-based system for accelerating digital dispute resolution

Source: United States Patent and Trademark Office (USPTO). Credit: Sift Science Inc

A recently granted patent (Publication Number: US11916927B2) outlines a machine learning-based method designed to expedite the resolution of digital dispute events. The method involves identifying a digital dispute event and routing it to either a subscriber-specific machine learning-based dispute scoring model or a subscriber-agnostic model based on historical data. The system computes a preliminary dispute inference based on extracted features, generates a dispute response artifact, and updates the inference based on evidence data included in the artifact before transmitting it to the relevant entity. The method aims to enhance the subscriber's chances of prevailing against the digital dispute event by leveraging machine learning algorithms and historical data.

Furthermore, the patent details additional features such as displaying the dispute response artifact on a web-based interface, highlighting missing probative evidence data, and providing insights on improving the response. The method also involves evaluating evidence data against a proposed corpus, generating an evidence feature dataset, and utilizing subscriber-specific or subscriber-agnostic models based on the available evidence. By automating the extraction of event attributes, executing API calls, and generating evidence data corpora, the system streamlines the dispute resolution process. Overall, the method combines machine learning techniques with historical data analysis to optimize the handling of digital dispute events and enhance the subscriber's chances of success.

To know more about GlobalData’s detailed insights on Sift Science, 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.