Computerized-methods and systems for identifying duplicate entries in a database of merchant data

A system for use in identifying duplicate merchant locations in payment network transaction data, the system comprising:

• a payment network including at least one processor coupled to a memory, the memory having a transaction data structure including transaction data for a plurality of transactions involving a plurality of merchants and at least one location identifier for each of the plurality of merchants, the at least one processor of the payment network configured to:
• provide one or more services to users registered with the payment network, wherein the one or more services are network-accessible to each of the users;
• and
• for each of the plurality of transactions in the transaction data structure:
• receive an authorization request for the transaction from a merchant via an acquirer, the authorization request including a merchant location identifier for the merchant;
• and
• store the merchant location identifier for the merchant in the transaction data structure as part of the transaction data for the transaction;
• and
• a verification engine including at least one processor coupled to a memory, the memory of the verification engine including a merchant data structure comprising a master location for each of the plurality of merchants involved in the plurality of transactions in the transaction data structure, the at least one processor of the verification engine configured to:
• identify a merchant of the plurality of merchants for audit;
• determine, from the merchant data structure, the master location for the identified merchant for audit;
• identify, from the plurality of merchants involved in the plurality of transactions in the transaction data structure, a plurality of close-match merchants for the identified merchant for audit, based on a similarity of the merchant location identifiers in the transaction data in the transaction data structure for each of the plurality of close-match merchants to the determined master location for the identified merchant for audit;
• identify a plurality of the users registered with the payment network for crowd sourcing, based on at least one of:
• a location associated with the user being within a predefined distance from at least one of the merchant location identifiers for the identified plurality of close-match merchants, a location associated with the user being within a predefined distance from the determined master location for the identified merchant for audit, and/or the user having performed one or more purchase transactions at the identified merchant for audit;
• query at least some of the identified plurality of users, in connection with a Completely Automated Public Turing test to tell Computers and Humans Apart (CAPTCHA), as to which of the merchant location identifiers for the identified plurality of close-match merchants is associated with the master location of the identified merchant for audit, thereby enabling the crowd sourcing in connection with verifying, by the CAPTCHA, that responses to the queries are not provided by automated computers;
• receive responses from the queried users selecting ones of the merchant location identifiers for the identified plurality of close-match merchants as associated with the master location of the identified merchant for audit;
• calculate a score indicative of a probability that at least one of the merchant location identifiers, for the identified plurality of close-match merchants, corresponds accurately to the determined master location of the identified merchant for audit, based on the responses from the queried users;
• compare the calculated score to a threshold value,
• when the calculated score satisfies the threshold value, update a location designation value for the identified merchant for audit in the merchant data structure;
• when the calculated score does not satisfy the threshold value, query additional ones of the identified plurality of users, in connection with the CAPTCHA, as to which of the merchant location identifiers for the identified plurality of close-match merchants is associated with the master location of the identified merchant for audit;
• receive responses from the queried additional users selecting ones of the merchant location identifiers for the identified plurality of close-match merchants as associated with the master location of the identified merchant for audit;
• and
• update the score based on the responses from the queried additional users and, when the updated score satisfies the threshold value, update the location designation value for the identified merchant for audit in the merchant data structure.