Nice had two patents in mobile during Q1 2024. Nice Ltd has developed a computerized method for generating high-quality synthetic fraud data based on tabular financial transaction data. This method involves handling missing values, generating synthetic fraud data using deep learning, evaluating ML model performance, storing misclassified data in a database, and creating a balanced training dataset 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 mobile as a theme is 50% in Q1 2024. Grant share is based on the ratio of number of grants to total number of patents.
Recent Patents
Application: Computerized-method for synthetic fraud generation based on tabular data of financial transactions (Patent ID: US20240013223A1)
The patent filed by Nice Ltd. describes a computerized method for generating high-quality synthetic fraud data based on tabular data of financial transactions to train a fraud-detection machine learning model in a multitenant environment. The method involves receiving tabular data, handling missing values, generating synthetic fraud data using deep learning, combining fraud transactions with synthetic data for training, evaluating model performance, storing misclassified data in a database, creating a balanced training dataset, and providing it to the ML model for training. The process aims to improve the precision and accuracy of fraud predictions in real-time data processing, especially in cases of extreme class imbalance where fraud transactions are less than 0.01% of total transactions.
The patent also includes specific claims related to the fixing module for handling missing values, the use of Conditional Generative Adversarial Networks (CTGAN) for synthetic data generation, and the calculation of median and mode statistics for data cleaning. It emphasizes the importance of misclassified data as an indicator of high-quality results and provides criteria for measuring the increased precision and accuracy of fraud predictions, such as Receiver Characteristic Operator (ROC) Area under Curve (AUC), precision, recall, and F1 score. Additionally, the method is designed to be applicable in a multitenant environment, allowing for the generation of high-quality synthetic fraud data for different tenants to enhance fraud detection capabilities.
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.
