Toast. has been granted a patent for a computer-implemented method that predicts interchange codes for credit card transactions. The method involves analyzing historical transaction data, transforming bank identification numbers into features, and training a random forest model to generate predictions for new transactions. GlobalData’s report on Toast gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on Toast, Transaction splitting was a key innovation area identified from patents. Toast's grant share as of June 2024 was 68%. Grant share is based on the ratio of number of grants to total number of patents.
Predicting interchange codes for credit card transactions
The granted patent US12002022B2 outlines a computer-implemented method for predicting interchange codes related to credit card transactions. The method begins by retrieving a historical dataset of completed transactions from a database, which includes transaction features, bank identification numbers (BINs), and their corresponding true interchange codes. The BINs are transformed into a set of BIN features that represent the probabilities of each BIN falling into various categories. A first training set is created, incorporating all transaction features, BIN features, and true interchange codes. A random forest model is then trained using this dataset, which involves rounding the BIN features and non-discrete transaction features to generate a second training set. This trained model is subsequently used to predict interchange codes for new transactions.
The patent further details the specific transaction features that may be included, such as total transaction amount, tip percentage, time between transaction authorization and capture, transaction type, and address verification system responses. Additionally, it specifies that the BIN features may include categories like regulated debit, debit, rewards, and high rewards. The predicted interchange codes are described as a weighted sum of interchange rates and fees, with weights indicating the likelihood of a transaction being assigned to a particular interchange code. The patent also encompasses a non-transitory computer-readable medium and a computer program product that facilitate the execution of this predictive method, ensuring that the process can be implemented effectively in various computing environments.
To know more about GlobalData’s detailed insights on Toast, 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.
