FMR had six patents in artificial intelligence during Q1 2024. FMR LLC filed patents in Q1 2024 for methods and apparatuses using machine learning for predictive analysis of transaction data, intelligent imputation of missing data in ML datasets, and disambiguating unrecognized abbreviations in search queries. These technologies involve training machine learning models, selecting imputation algorithms based on dataset characteristics, and using trained models to generate replacement words for unrecognized abbreviations in search queries. GlobalData’s report on FMR gives a 360-degree view of the company including its patenting strategy. Buy the report here.

FMR grant share with artificial intelligence 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: Methods and systems for predictive analysis of transaction data using machine learning (Patent ID: US20240095549A1)

The patent filed by FMR LLC describes methods and apparatuses for predictive analysis of transaction data using machine learning. The system involves training multiple machine learning models with historical transaction data for entities to predict future transaction activity likelihood. Each model is trained on a different target transaction variable, generating predicted likelihood values for future transactions associated with each entity and target variable. These values are then transmitted to a remote computing device for display. The system utilizes tree-based machine learning models and a feature selection process to optimize model performance, with periodic validation of model accuracy using newly received historical transaction data.

The system's method involves creating an initial feature set based on historical transaction data, determining target transaction variables, generating variable-specific feature sets, and training machine learning models for each variable. The trained models are then executed to predict future transaction likelihood for each entity and target variable, with the results transmitted to a remote device for display. The process includes a feature selection pipeline, correlative feature selector, and merging of screening attributes with predicted values for display. The system ensures model performance and accuracy through periodic validation using updated historical transaction data, enhancing the predictive capabilities of the machine learning models for transaction analysis.

To know more about GlobalData’s detailed insights on FMR, buy the report here.

Premium 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.