Nice had five patents in regtech during Q1 2024. Nice Ltd has developed computerized methods for predicting fraudulent financial-account access and generating high-quality synthetic fraud data. The first method involves building a Machine Learning sequence model, implementing a forward-propagation routine, and integrating it with a Fraud Management System to predict fraud probability scores. The second method includes handling missing values in financial transaction data, generating synthetic fraud data using deep learning, and training a ML model to differentiate between original and synthetic fraud transactions for fraud detection. 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 grant share with regtech as a theme is 60% in Q1 2024. Grant share is based on the ratio of number of grants to total number of patents.
Recent Patents
Application: Computerized-method and system for predicting a probability of fraudulent financial-account access (Patent ID: US20240070673A1)
The patent filed by Nice Ltd. describes a computerized method for predicting the probability of fraudulent financial account access using a Machine Learning (ML) sequence model. The method involves building the ML model by retrieving and labeling chronical sequences of non-financial activities associated with financial accounts, training the model, implementing a forward propagation routine to generate fraud probability scores, and integrating the routine with a Fraud Management System for real-time prediction. The system also includes a memory to store data and processors to execute the method, with the ability to re-tune the ML model for improved accuracy and prevent fraudulent activities based on a predefined threshold.
The computerized system and method outlined in the patent focus on leveraging ML techniques to analyze sequences of non-financial activities preceding financial transactions to predict fraudulent access to accounts. By encoding activities into vectors, training the ML model, and utilizing a forward propagation routine, the system can generate fraud probability scores in real-time. The integration with a Fraud Management System allows for early fraud detection and decision-making based on the calculated scores, ultimately enhancing security measures and preventing unauthorized financial activities. Additionally, the system's ability to re-tune the ML model, set threshold values for fraud probability, and restrict user actions based on these scores demonstrates a comprehensive approach to fraud prevention in financial transactions.
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.
