Abstract: In some examples, a financial system receives, from a plurality of computing devices associated with a plurality of users, respectively, transaction data of transactions performed by the plurality of users. The financial system may provide, based at least on the transaction data, financing to an account of a first user, the financing including repayment terms for repayment of the financing. The financial system may receive, from one or more services, one or more signals related to a business of the first user. Further, the financial system may determine, based on the received one or more signals related to the business of the first user, updated repayment terms for repayment of the financing from the first user. In addition, the financial system may apply the updated repayment terms for repayment of the financing.

Abstract: Using a machine learning model(s) for fraud reduction is described. A payment service computing platform may receive, from an electronic device, user data associated with a user, and dynamically determine an incentive(s) associated with the user based on the user data. The incentive(s) may be determined using a trained machine learning model(s) that is trained based on previously collected user data. The payment service computing platform can then cause a user interface to be displayed via a payment application executing on the electronic device, wherein the user interface presents an interactive element(s) for receiving the incentive(s) in exchange for the user referring at least one other user to a payment service.

Abstract: A payment processing system receives, from a plurality of merchant computing devices associated with respective merchants, transaction information of transactions performed between the respective merchants and customers. Further, the system may receive, from a first computing device, a request to finance a purchase to be made by a customer from a first merchant. The system may determine, based at least partially on analysis of previous transactions of the customer determined from the received transaction information, financing terms for the purchase, the financing terms including a financed amount and repayment terms for the customer for the financed amount. The system may transmit the financing terms to the first computing device, and may receive an acceptance by the customer of the financing terms. Additionally, the system may send, based on the approved financed amount, a communication indicating an amount to provide to an account associated with the first merchant.

Abstract: In some examples, a payment processing system receives transaction information of transactions performed by a plurality of merchants. The payment processing system may generate, using one or more trained machine learning classifiers and based on transaction information of a current transaction of a first merchant, a request to a plurality of financial systems. Further, the payment processing system may expose an application programming interface (API) to at least one financial system of the plurality of financial systems for electronic communication of financial information at least one of to or from the at least one financial system. Additionally, the payment processing system may generate, using the one or more trained machine learning classifiers and based at least on information obtained from the at least one financial system, via the API, one or more payment actions for the first merchant to perform using the payment processing system.

Abstract: A payment processing system for mobile point-of-sale transactions from a mobile point-of-sale (POS) terminal including a payment card reader having a card interface configured to read data from a payment card, the payment processing system configured to process a request from a merchant to provide financing for a purchase by a buyer (e.g., a second merchant). The payment processing system is further configured to calculate financing terms including an approved purchase amount and repayment terms for the approved purchase amount, to transmit the financing terms to the merchant for presentation to the buyer via the mobile POS terminal, to receive an acceptance of the financing terms from the buyer, to transmit the approved purchase amount to the merchant, and to receive payment from the buyer according to the repayment terms.

Abstract: In some examples, a payment processing system may send, based on transaction information received from a plurality of merchant devices, an incentive for a first merchant to whom financing has been provided, to achieve a performance target during a specified time period. For instance, the incentive may include a proposed modification to repayment terms for the financing to be implemented if the merchant achieves the performance target during the specified time period. The system may track transactions processed for the first merchant during the specified time period. Based on the tracking, the system may determine that the merchant has achieved the performance target during the specified time period for receiving the incentive, and may implement the modification of the repayment terms for the financing for the first merchant.

Abstract: In some examples, a payment processing system may receive, from a plurality of merchant computing devices associated with a plurality of merchants, respectively, transaction data of transactions performed between the plurality of merchants and a plurality of customers. Based at least on the transaction data, the payment processing system may provide financing to an account of a first merchant, the financing including repayment terms for repayment of the financing. In addition, the payment processing system may determine that the first merchant is predicted to have a change in sales during an upcoming time period. Based on the predicted change in sales, the payment processing system may determine updated repayment terms for repayment of the financing from the first merchant, and may apply the updated repayment terms for repayment of the financing.

Abstract: A payment processing system is configured to expose an API to provide financing terms to a financial institution. The payment processing system receives, via the API, a request from the financial institution to calculate financing terms for providing capital to a merchant based on the merchant's financial history with the payment processing system and/or the financial institution. The payment processing system calculates the financing terms including an approved financing amount and repayment terms, which may include a portion of the transaction processed by the payment processing system or the financial institution to be withheld for repayment of the approved financing amount. The payment processing system transmits the financing terms to the financial institution via the API.

Abstract: A payment processing system receives, from merchant computing devices, transaction information of transactions performed between a plurality of merchants and customers. The merchant computing devices may each execute a merchant application that configures the merchant computing devices as point-of-sale (POS) terminals. The payment processing system receives, from a first POS terminal, a request to finance a purchase between a customer and a first merchant. The payment processing system determines financing terms for the purchase from the transaction information received from the merchant computing devices. The payment processing system sends the financing terms, including an approved financed amount and repayment terms for the approved financed amount, to the first POS terminal for presentation to the customer. In response to receiving an indication of acceptance by the customer of the financing terms, the payment processing system transfers the approved financed amount to an account of the first merchant.

Abstract: In some examples, a payment processing system may receive, from merchant devices of a plurality of merchants, transaction data of transactions performed between the merchants and customers. The system may provide financing to an account of a first merchant with repayment terms based on one or more attributes of the first merchant determined from the received transaction data. The system may receive service information from at least one service performed for a business of the first merchant and may determine a state of the business of the first merchant. Based on the received transaction data and the state of the business of the first merchant, the system may determine that the first merchant is expected to have a decrease in sales. The system may determine a deferral period based on the expected decrease in sales and may refrain from taking repayment of the financing for the deferral period.

Abstract: A payment processing system is configured to provide financing to a merchant, the merchant having an account with a payment provider who operates the payment processing system to process a plurality of financial transactions between the merchant and buyers via a mobile point-of-sale (POS) terminal. The payment processing system receives repayment of the financing from the merchant by withholding a portion of funds from the plurality of financial transactions processed for the merchant by the payment processing system. The payment processing system evaluates financial transactions conducted by the merchant through the payment processing system and, based on the evaluation, provides the merchant with one or more offers defining an incentive of financing or modification of current financing arrangements in order to induce activity by the merchant. The payment processing system identifies that the merchant has performed the activity identified in the offer and implements the incentive in the offer.

Abstract: An automated purchase transaction analyzes a purchase transaction using a probability model to determine a probability that the transaction is fraudulent. If the probability exceeds a threshold, the transaction may be manually reviewed to determine whether to freeze the account associated with the transaction. When introducing the model, the threshold may be set to a relatively high value so that a small number of transactions are submitted for manual review. After a period of time, the observed freeze rate resulting from manual reviews is compared to a target freeze rate. The threshold is then adjusted upwardly or downwardly to decrease the difference between the observed and target freeze rates.

Abstract: An automated purchase transaction service implements a two-phase analysis to identify suspect transactions and to freeze merchant accounts associated with certain of the suspect transactions. In a first analysis phase, a transaction is analyzed using a first predictive model to determine a probability that the transaction is fraudulent. If the probability exceeds a first threshold, the transaction is further analyzed in a second phase. In the second analysis phase, the transaction is analyzed using a second predictive model to determine a probability that manual review by a human analyst will result in freezing the associated account. If the probability exceeds a second threshold, the transaction is automatically frozen. If the probability does not exceed the second threshold, the transaction is submitted to a human analyst for manual review.

Abstract: A payment processing system for processing mobile point-of-sale transactions and extending cash advances to merchants is disclosed. The payment processing system receives repayment of the cash advance from the merchant by withholding a portion of funds from financial transactions processed for the merchant, the portion of funds determined according to repayment terms for the cash advance. The payment processing system receives signals from other products provided to the merchant by the payment processing service provider to determine payment deferral eligibility for the merchant where the payment processing system refrains from taking repayment from the financial transactions processed for the merchant by the payment processing system. The payment deferral eligibility may be determined in response to a merchant request for a payment deferral or automatically by the payment processing system.

Abstract: A payment processing system for mobile point-of-sale transactions from a mobile point-of-sale (POS) terminal including a payment card reader having a card interface configured to read data from a payment card, the payment processing system configured to process a request from a merchant to provide financing for a purchase by a buyer (e.g., a second merchant). The payment processing system is further configured to calculate financing terms including an approved purchase amount and repayment terms for the approved purchase amount, to transmit the financing terms to the merchant for presentation to the buyer via the mobile POS terminal, to receive an acceptance of the financing terms from the buyer, to transmit the approved purchase amount to the merchant, and to receive payment from the buyer according to the repayment terms.

Abstract: A system and method for calculating crowdfunding terms based on a financial history of a merchant is described. The crowdfunding terms include an approved funding amount and repayment terms including a portion of transactions processed for the merchant by the payment processing system to withhold for repayment of the approved funding amount plus earnings to investors. The a payment processing system may withhold the portion of the transactions processed for the merchant by the payment processing system for repayment of the approved funding amount plus earnings to the investors, apportion the portion of the transactions processed for the merchant by the payment processing system amongst the investors, and transmit, by the payment processor system, the apportioned amount to each investor.