Toronto-Dominion Bank had 25 patents in artificial intelligence during Q2 2024. The Toronto-Dominion Bank filed patents for methods, systems, and techniques for multivariate time series forecasting using machine learning, a computerized portfolio optimization and management tool with a graphical user interface, automatically generating and storing business entity summaries in a uniform format, and analyzing interactions between entities using electronic communication channels with automated messages. GlobalData’s report on Toronto-Dominion Bank gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Toronto-Dominion Bank had no grants in artificial intelligence as a theme in Q2 2024.
Recent Patents
Application: Multivariate time series forecaster using deep learning (Patent ID: US20240211732A1)
The patent filed by The Toronto-Dominion Bank describes methods, systems, and techniques for multivariate time series forecasting using deep learning models. The approach involves utilizing an autoencoder and autoregressor within a machine learning model to analyze seasonality, covariance, and trend information of the multivariate input dataset. The autoencoder generates layers to analyze seasonality and covariance, while the autoregressor generates layers to analyze trend information. These layers are then merged to form a set of merged layers that represent a multivariate time series forecast in a future time frame. The method also includes stationarizing the input data, applying a sliding window to designate training and forecasted sets, and using a bottleneck layer in the autoencoder for encoding.
The patent further details the use of a dilated convolutional neural network in the autoencoder for multivariate time series forecasting, as well as the application of granger causality feature selection to assess the efficacy of utilizing specific variables for forecasting separate multivariate time series data. The system described in the patent includes a processor and storage configured to execute instructions for receiving, processing, and forecasting multivariate time series data using deep learning models. The system also involves stationarizing the input data, utilizing an autoencoder and autoregressor, and merging the generated layers to produce a multivariate time series forecast. Additionally, the system can perform granger causality feature selection to evaluate the impact of specific variables on forecasting different time series data.
To know more about GlobalData’s detailed insights on Toronto-Dominion Bank, 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.
