Users complete payment transactions with various merchants using a wallet application or similar payment application maintained by an account management computing system. The account management computing system creates a predictive model or trains a machine learnt regression function or classifier model to predict the merchant review score based on the payment information received from the user device. A merchant is identified to derive a merchant review score and the account management computing system identifies the business type of the identified merchant. Payment data that corresponds to completed payment transaction between various users and the identified merchant are identified. Each part of the payment data that can be used by the predictive model to infer a merchant review score is a signal that is identified from the payment data. During its analysis of the first signal, the account management computing system determines the number of times the user has visited the identified merchant. The number of repeat visits to the identified merchant can be normalized based on a similar merchant type. During its analysis of the second signal, the account management computing system determines the difference between the preauthorized payment amount and the final payment amount for the user’s payment transaction with the identified merchant. This analysis will yield a calculated gratuity amount. The gratuity amount can be normalized based on a user’s typical gratuity amount for a similar merchant type or based on geographic locations. The predictive model is applied to the identified signals to infer a merchant review score. The account management computing system outputs the merchant review score for the identified merchant.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Sharifi, Matthew and Roblek, Dominik, "INFERRING MERCHANT REVIEW SCORES FROM PAYMENT DATA", Technical Disclosure Commons, (August 15, 2016)