Toronto-Dominion Bank had no grants in blockchain as a theme in Q2 2024.

Recent Patents

Application: Decision tree model training process (Patent ID: US20240161185A1)

The patent filed by The Toronto-Dominion Bank describes a method and apparatus for optimizing decision tree models by assigning criteria to nodes, executing the model on training data, identifying nodes with high purity, generating rules based on these nodes, and embedding the rules back into the model for storage. The apparatus includes a processor and storage for executing and storing the decision tree model, while the method involves assigning criteria, executing the model, identifying interconnected nodes with high purity, generating rules, and embedding them back into the model. The system dynamically determines purity thresholds based on historical data and can record outputs via a blockchain ledger for transparency and security.

The invention aims to improve decision tree models by focusing on nodes with high purity, which are determined based on the percentage of approved historical loan applications. By generating rules based on these high-purity nodes, the model can make more accurate decisions. The system can also adapt the purity threshold dynamically based on the model's performance and record outputs on a blockchain ledger for added security. Additionally, the method involves encoding training data for efficient execution of the decision tree model. Overall, the patent outlines a comprehensive approach to enhancing decision tree models for more effective decision-making processes.

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.

Be better informed