Updating a machine learning fraud model based on third party transaction information

A device, comprising:

• one or more memories;
• and
• one or more processors communicatively coupled to the one or more memories, configured to:
• receive first transaction information associated with a first transaction based on a first transaction account being utilized to conduct the first transaction associated with a first financial institution;
• deny, based on a fraud model, the first transaction due to a potential fraud associated with the first transaction account;
• receive second transaction information associated with a second transaction based on a user device or a second transaction account being utilized to conduct the second transaction associated with a second financial institution;
• process the first transaction information and the second transaction information, with a matching model that is based on a machine learning model, to determine whether the first transaction information matches the second transaction information;
• determine that the first transaction was incorrectly denied, due to potential fraud associated with the first transaction account, when the first transaction information matches the second transaction information within a predetermined threshold;
• remove, based on determining that the first transaction was incorrectly denied, a lock on the first transaction account to allow the first transaction account to be utilized;
• update, based on parameters of the fraud model that caused the first transaction to be incorrectly denied, training data for the fraud model, to generate updated training data;
• and
• retrain the fraud model with the updated training data.

A non-transitory computer-readable medium storing instructions, the instructions comprising:

• one or more instructions that, when executed by one or more processors, cause the one or more processors to:
• receive first transaction information associated with a first transaction based on a first transaction account being utilized to conduct the first transaction associated with a first financial institution;
• determine, based on a fraud model, that the first transaction is to be denied due to a potential fraud associated with the first transaction account;
• receive second transaction information associated with a second transaction based on a user device or a second transaction account being utilized to conduct the second transaction associated with a second financial institution;
• process the first transaction information and the second transaction information, with a matching model that is based on a machine learning model, to determine whether the first transaction information matches the second transaction information;
• determine that the first transaction was incorrectly denied, due to potential fraud associated with the first transaction account, when the first transaction information matches the second transaction information within a predetermined threshold;
• remove, based on determining that the first transaction was incorrectly denied, a lock on the first transaction account to allow the first transaction account to be utilized;
• update, based on parameters of the fraud model that caused the first transaction to be incorrectly denied, training data for the fraud model, to generate updated training data;
• and
• retrain the fraud model with the updated training data.