Nice had three patents in regtech during Q2 2024. Nice Ltd has developed computerized methods for identifying fraud transactions in financial systems and generating classification Machine Learning (ML) models in a cloud-based environment. The fraud detection method involves training ML models on fraud-labeled and legit-labeled transactions to mark transactions as ‘similar’ or ‘novel’, while the ML model generation method involves building an ML model using isolated datasets from different environments and continuously training the model before deploying it in a target tenant system for classifying objects. GlobalData’s report on Nice gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Access deeper industry intelligence
Experience unmatched clarity with a single platform that combines unique data, AI, and human expertise.
Nice had no grants in regtech as a theme in Q2 2024.
Recent Patents
Application: Computerized-method and computerized-system for identifying fraud transactions in transactions classified as legit transactions by a classification machine learning model (Patent ID: US20240193608A1)
The patent filed by Nice Ltd. describes a computerized method for identifying fraud transactions within a financial system that have been classified as legitimate by a Machine Learning (ML) model. The method involves training ML models on datasets of fraud-labeled and legit-labeled transactions to mark transactions as 'similar' or 'novel'. These trained models are then deployed in a computerized environment along with a classification ML model to identify fraud transactions that were classified as legitimate. The trained classification ML model is based on preconfigured transactions from the data store.
Furthermore, the method includes sending transactions classified as 'legit' by the ML model to a trained ML legit model for processing, and those marked as 'novel' are then sent to a trained ML fraud model. Transactions marked as 'novel' by the fraud model are identified as potential unknown fraud, while those marked as 'similar' are identified as potential missed fraud. Additionally, the method involves calculating novelty and similarity scores for transactions marked as 'novel' and 'similar' respectively, with the highest scoring transactions being transmitted to a user for investigation. The legit and fraud models are trained using an unsupervised algorithm, and the retrieved transactions are from preconfigured times or randomly sampled from the data store.
To know more about GlobalData’s detailed insights on Nice, 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.
