Machine learning engine for fraud detection during cross-location online transaction processing

A system, comprising:

• a processor;
• and
• a non-transitory computer-readable medium having stored thereon instructions that are executable to cause the system to perform operations comprising:
• based on a processing request for a transaction for an entity located at a first location, determining a first vertical categorization for the transaction;
• determining a second location associated with an online account corresponding to the transaction;
• identifying a vertical cluster associated with the online account based on the first location and the second location, wherein the vertical cluster includes a second vertical categorization corresponding to a previous transaction conducted by the online account;
• determining a probability, using a machine learning engine, of a user of the online account to participate in the transaction within the first vertical categorization based on the second vertical categorization;
• using one or more transaction risk assessment rules and the probability of the user to participate in the transaction, assigning a risk score to the transaction;
• and
• reporting the assigned risk score.

A method, comprising:

• receiving an indication, at a computer system, that a first user device has made a processing request for a transaction for an entity located at a first location;
• determining, by the computer system, a first vertical categorization for the transaction;
• determining, by the computer system, a second location associated with an online account corresponding to the transaction;
• identifying, by the computer system, a vertical cluster associated with the online account based on the first location and the second location, wherein the vertical cluster includes a second vertical categorization corresponding to a previous transaction conducted by the online account;
• determining a probability, using a machine learning engine, of a user of the online account to participate in the transaction within the first vertical categorization based on the second vertical categorization;
• and
• the computer system using one or more transaction risk assessment rules and the probability of the user to participate in the transaction, assigning a risk score to the transaction.

A non-transitory computer-readable medium having stored thereon instructions executable by a computer system to cause the computer system to perform operations comprising:

• based on a processing request for a transaction for an entity located at a first location, determining a first vertical categorization for the transaction;
• determining a second location associated with an online account corresponding to the transaction;
• identifying a vertical cluster associated with the online account based on the first location and the second location, wherein the vertical cluster includes a second vertical categorization corresponding to a previous transaction conducted by the online account;
• determining a probability, using a machine learning engine, of a user of the online account to participate in the transaction within the first vertical categorization based on the second vertical categorization;
• using one or more transaction risk assessment rules and the probability of the user to participate in the transaction, assigning a risk score to the transaction;
• and
• reporting the assigned risk score.