| 摘要 |
A system and method a method for providing for providing personalized transaction learning and tagging. The method may include tagging transactions associated with one or more financial accounts belonging to an account holder, whether the account holder be the primary, secondary, or a related account holder, such as a spouse, parent, guardian, and the like. The method may include linking all accounts belong to and/or associated with an account holder and receiving transaction data from each linked account, including, for example, transaction date, transaction time, transaction amount, merchant name, merchant location, merchant identifier, account number used in transaction, SKU-level transaction information, and/or other purchase identifiers (e.g., merchant-provided product/service name, account holder-provided product/service name, and the like). Once the system receives the transaction data, the system may query the account holder for input regarding the transaction data. The input may include tagging the transaction as belonging to a particular spending category and/or affirming or denying that the transaction belongs to a particular category. The system may receive and create categories based on account holder data, demographic data, credit data, and account holder profile data. |
| 主权项 |
1. A system, comprising:
data storage that maintains historical transaction data received from a plurality of financial institutions through a financial institution application programming interface (API); a categorization system connected to the data storage, wherein the categorization system:
receives, via a network from an account holder device, at least one category associated with at least one transaction in the historical transaction data;receives, via a network, account holder profile data and demographic data;receives, via a financial institution API, current transaction data;determines, using a categorization subsystem, whether the current transaction data has a threshold number of similarities with a transaction in the historical transaction data by comparing the current transaction data with the historical transaction data;determines, using machine learning techniques implemented by the categorization subsystem, a most-likely spend category based on the threshold number of similarities;receives, via a network from the account holder device; a confirmation that the most-likely spend category is correct;tags, using the categorization subsystem, the current transaction data with most-likely spend category;stores, in the data storage, the current transaction data along with the tagged spend category; andprepares a visualization report to include all transaction data tagged with the most-likely spend category. |
