Sift Science. has been granted a patent for a machine learning method that detects automated online fraud and abuse. The method involves identifying digital events, creating activity signatures, and using an autoencoder model to classify these signatures, enabling targeted threat mitigation actions. GlobalData’s report on Sift Science gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
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 July 2024 was 79%. Grant share is based on the ratio of number of grants to total number of patents.
Automated detection of online fraud and abuse attacks
The granted patent US12047401B2 outlines a computer-implemented method for detecting automated online fraud and abuse within an online computing environment. The method begins by sourcing digital event data related to user activities and extracting a set of features from this data. An autoencoder model is then employed to convert these features into an encoded graphical representation of the activity sequence. This representation is classified into one of several distinct categories of automated online fraud or abuse, utilizing a search query that navigates an n-dimensional space containing clusters of encoded graphs, each corresponding to specific types of fraud or abuse.
Further details of the method include the generation of vector embeddings from the extracted features, which are used to compute the encoded representation. The classification process involves mapping the encoded representation to clusters of encoded graphs, with the potential to identify and return relevant encoded graphs based on proximity measures such as cosine or Euclidean distance. The patent also describes the construction of an automated fraud or abuse signature registry, which categorizes distinct activity sequences and associates them with specific fraud or abuse labels. Ultimately, the method allows for the implementation of automated threat mitigation actions, enabling web-enabled services to either process or block digital event data based on the identified threat level.
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, 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.
