Using risk metrics to facilitate transactions

1 . A computer-implemented method comprising:

receiving, by one or more processors, a search query from a payment application associated with a payment service and executing on a device of a user;

determining, by the one or more processors, a user risk metric associated with the user, the user risk metric indicating that the user is classified as a risk class of multiple risk classes;

determining, by the one or more processors, and based at least in part on transaction data associated with merchants, merchant risk metrics associated with the merchants;

filtering, by the one or more processors, the merchants based at least in part on the user risk metric and the merchant risk metrics to generate a list of merchants;

causing, by the one or more processors, a user interface of the payment application to present at least a portion of the list of merchants as a search result to the search query;

receiving, by the one or more processors, a first indication of a selected merchant from the list of merchants;

receiving, by the one or more processors, a second indication of one or more items to be purchased from the selected merchant;

using, by the one or more processors, a single-use payment instrument to complete a transaction for the one or more items; and

generating, by the one or more processors, a loan associated with the transaction, wherein at least a first payment associated with the loan is made using the single-use payment instrument at a time of the transaction and one or more additional payments associated with the loan are to be made at a later time.

2 . The computer-implemented method of claim 1 , wherein the multiple risk classes comprise a low risk class and a high risk class.

3 . The computer-implemented method of claim 1 , wherein the multiple risk classes comprise a low risk class, a medium risk class, and a high risk class.

4 . The computer-implemented method of claim 3 , wherein:

the risk class as which the user is classified is the high risk class; and

the filtering comprises:

excluding, from the list of merchants, a first subset of the merchants classified as the high risk class, as indicated by the merchant risk metrics;

excluding, from the list of merchants, a second subset of the merchants classified as the medium risk class, as indicated by the merchant risk metrics; and

including, in the list of merchants, a third subset of the merchants classified as the low risk class, as indicated by the merchant risk metrics.

5 . The computer-implemented method of claim 1 , wherein the user interface is a first user interface, the computer-implemented method further comprising:

causing, by the one or more processors, a second user interface of the payment application to present a subset of a full set of payment options for purchasing the one or more items from the selected merchant, wherein the subset includes at least the single-use payment instrument; and

receiving, by the one or more processors, a third indication to use the single-use payment instrument to complete the transaction,

wherein the using of the single-use payment instrument to complete the transaction is based at least in part on the receiving of the third indication.

6 . The computer-implemented method of claim 1 , wherein the user risk metric is determined using a machine-trained model.

7 . The computer-implemented method of claim 6 , further comprising determining, by the one or more processors, an occurrence of an event, wherein the machine-trained model is executed to determine the user risk metric in response to the occurrence of the event.

8 . A system comprising:

one or more processors; and

memory storing computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:

receiving a search query from a payment application associated with a payment service and executing on a device of a user;

determining a user risk metric associated with the user, the user risk metric indicating that the user is classified as a risk class of multiple risk classes;

determining, based at least in part on transaction data associated with merchants, merchant risk metrics associated with the merchants;

filtering the merchants based at least in part on the user risk metric and the merchant risk metrics to generate a list of merchants;

causing a user interface of the payment application to present at least a portion of the list of merchants as a search result to the search query;

receiving a first indication of a selected merchant from the list of merchants;

receiving a second indication of one or more items to be purchased from the selected merchant;

using a single-use payment instrument to complete a transaction for the one or more items; and

generating a loan associated with the transaction, wherein at least a first payment associated with the loan is made using the single-use payment instrument at a time of the transaction and one or more additional payments associated with the loan are to be made at a later time.

9 . The system of claim 8 , wherein the multiple risk classes comprise a low risk class and a high risk class.

10 . The system of claim 8 , wherein the multiple risk classes comprise a low risk class, a medium risk class, and a high risk class.

11 . The system of claim 10 , wherein:

the risk class as which the user is classified is the high risk class; and

the filtering comprises:

excluding, from the list of merchants, a first subset of the merchants classified as the high risk class, as indicated by the merchant risk metrics;

including, in the list of merchants, a second subset of the merchants classified as the medium risk class, as indicated by the merchant risk metrics; and

including, in the list of merchants, a third subset of the merchants classified as the low risk class, as indicated by the merchant risk metrics.

12 . The system of claim 8 , wherein the merchant risk metrics are determined using a machine-trained model.

13 . The system of claim 12 , wherein the machine-trained model is executed offline to determine the merchant risk metrics prior to the receiving of the search query.

14 . The system of claim 8 , wherein terms of the loan are restricted to a particular payment amount at a particular payment frequency.

15 . One or more non-transitory computer-readable media storing computer-executable instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

receiving a search query from a payment application associated with a payment service and executing on a device of a user;

determining a user risk metric associated with the user, the user risk metric indicating that the user is classified as a risk class of multiple risk classes;

determining, based at least in part on transaction data associated with merchants, merchant risk metrics associated with the merchants;

filtering the merchants based at least in part on the user risk metric and the merchant risk metrics to generate a list of merchants;

causing a user interface of the payment application to present at least a portion of the list of merchants as a search result to the search query;

receiving a first indication of a selected merchant from the list of merchants;

receiving a second indication of one or more items to be purchased from the selected merchant;

using a single-use payment instrument to complete a transaction for the one or more items; and

generating a loan associated with the transaction, wherein at least a first payment associated with the loan is made using the single-use payment instrument at a time of the transaction and one or more additional payments associated with the loan are to be made at a later time.

16 . The one or more non-transitory computer-readable media of claim 15 , wherein the multiple risk classes comprise a low risk class and a high risk class.

17 . The one or more non-transitory computer-readable media of claim 15 , wherein the multiple risk classes comprise a low risk class, a medium risk class, and a high risk class.

18 . The one or more non-transitory computer-readable media of claim 17 , wherein:

the risk class as which the user is classified is the medium risk class; and

the filtering comprises:

excluding, from the list of merchants, a first subset of the merchants classified as the high risk class, as indicated by the merchant risk metrics;

including, in the list of merchants, a second subset of the merchants classified as the medium risk class, as indicated by the merchant risk metrics; and

including, in the list of merchants, a third subset of the merchants classified as the low risk class, as indicated by the merchant risk metrics.

19 . The one or more non-transitory computer-readable media of claim 15 , wherein the user interface is a first user interface, the operations further comprising:

causing a second user interface of the payment application to present a subset of a full set of payment options for purchasing the one or more items from the selected merchant, wherein the subset includes at least the single-use payment instrument; and

receiving a third indication to use the single-use payment instrument to complete the transaction,

wherein the using of the single-use payment instrument to complete the transaction is based at least in part on the receiving of the third indication.

20 . The one or more non-transitory computer-readable media of claim 15 , wherein the user risk metric is determined using a machine-trained model.