Granted Patent B2

US 12,346,907 · App. 18/388,983 · Granted Jul 1, 2025

Inventors: Jacqueline Reses (Woodside, CA); Audrey Kim (San Francisco, CA); Theodore Kosev (Seattle, WA); Andy Montgomery (San Francisco, CA)

Assignee: Block, Inc.

G06Q20/405G06Q20/108G06Q40/02G06Q40/03G06Q40/12G06Q40/128

Abstract

Claims (65)

1. A system comprising:

at least one memory storing instructions; and

at least one processor that executes the instructions to perform operations comprising:

accessing, by the at least one processor, a data structure including historical account data for a plurality of accounts of a plurality of users over time;

training, by the at least one processor, at least one predictive machine learning model based on training data extracted at least from the data structure to generate at least one trained predictive machine learning model, the training data including the historical account data associated with the plurality of accounts of the plurality of users, the at least one trained predictive machine learning model trained based on the training data to determine account balance thresholds over which funds in user accounts are to be predicted to be surplus;

processing, by the at least one processor, account data associated with a first account using the at least one trained predictive machine learning model to determine an account balance threshold for the first account over which a portion of funds in the first account are predicted to be surplus funds for a period of time, wherein the first account is associated with a user of the plurality of users, wherein the plurality of accounts includes the first account;

causing, by the at least one processor, a user device of the user to present a user interface that indicates predicted expenses and predicted income for a plurality of periods of time including the period of time, wherein the user interface identifies the surplus funds for the period of time, and wherein the user interface includes an interactive element for indicating disposition of the surplus funds; and

in response to receiving an indication of an action to perform with respect to the surplus funds via the interactive element of the user interface, automatically sending, by the at least one processor, at least one instruction for performing the indicated action to improve a yield associated with the surplus funds.

2. The system of claim 1 , wherein the indicated action includes transferring at least a portion of the surplus funds to a second account, and the at least one trained predictive machine learning model is further trained to predict times when respective balances of user accounts are predicted to fall below respective minimum balances, the operations further comprising:

inputting, into the at least one trained predictive machine learning model, at least one of: additional account data related to the first account of the user, or transaction data related to the user; and

based at least on an output of the at least one trained predictive machine learning model indicating that the first account of the user is predicted to fall below a minimum balance for the first account of the user, sending at least one communication for transferring funds from the second account back to the first account.

3. The system of claim 1 , wherein the at least one trained predictive machine learning model is further trained to predict respective timings at which user accounts are predicted to fall below respective minimum balances, the operations further comprising:

inputting, into the at least one trained predictive machine learning model, at least one of: additional account data related to the first account of the user, or transaction data related to the user; and

based at least on an output of the at least one trained predictive machine learning model indicating a time at which the first account of the user is predicted to fall below a minimum balance for the first account of the user, sending, to the user device of the user, a communication to cause the user device to present another user interface including a timing at which the first account of the user is predicted to fall below the minimum balance, and further presenting an offer to extend financing to the user.

4. The system of claim 1 , wherein the indicated action includes moving at least a portion of the surplus funds to a second account, the operations further comprising:

receiving information related to a transaction in which the user is a participant; and

transferring an amount associated with the transaction to the second account, wherein the amount transferred corresponds at least to a difference between a transaction amount for the transaction and a rounded-up amount associated with the transaction.

5. The system of claim 1 , wherein:

the indicated action includes transferring at least a portion of the surplus funds to a second account; and

funds in the second account are pooled from multiple users of the plurality of users for use as loaned funds to one or more other users of the plurality of users.

6. The system of claim 1 , wherein at least a portion of the historical account data for the plurality of accounts of the plurality of users that is included in the data structure, and that is included in the training data used to train the at least one predictive machine learning model, is received from a plurality of point-of-sale devices associated with a plurality of merchants that use a payment service system associated with the at least one processor.

7. The system of claim 1 , the operations further comprising:

aggregating a portion of the historical account data in the data structure associated with users determined to be similar to each other based on at least one similarity characteristic; and

using the aggregated portion of the historical account data for training the at least one predictive machine learning model, wherein the account data related to the first account of the user is inputted into the at least one trained predictive machine learning model based at least on the user being associated with the at least one similarity characteristic.

8. A method comprising:

accessing, by at least one processor, a data structure including historical account data for a plurality of accounts of a plurality of users over time;

training, by the at least one processor, at least one predictive machine learning model based on training data extracted at least from the data structure to generate at least one trained predictive machine learning model, the training data including the historical account data associated with the plurality of accounts of the plurality of users, the at least one trained predictive machine learning model trained based on the training data to determine account balance thresholds over which funds in user accounts are to be predicted to be surplus;

processing, by the at least one processor, account data associated with a first account using the at least one trained predictive machine learning model to determine an account balance threshold for the first account over which a portion of funds in the first account are predicted to be surplus funds for a period of time, wherein the first account is associated with a user of the plurality of users, wherein the plurality of accounts includes the first account;

causing, by the at least one processor, a user device of the user to present a user interface that indicates predicted expenses and predicted income for a plurality of periods of time including the period of time, wherein the user interface identifies the surplus funds for the period of time, and wherein the user interface includes an interactive element for indicating disposition of the surplus funds; and

in response to receiving an indication of an action to perform with respect to the surplus funds via the interactive element of the user interface, automatically sending, by the at least one processor, at least one instruction for performing the indicated action to improve a yield associated with the surplus funds.

9. The method of claim 8 , wherein the indicated action includes transferring at least a portion of the surplus funds to a second account, and the at least one trained predictive machine learning model is further trained to predict times when respective balances of user accounts are predicted to fall below respective minimum balances, the method further comprising:

inputting, into the at least one trained predictive machine learning model, at least one of: additional account data related to the first account of the user, or transaction data related to the user; and

based at least on an output of the at least one trained predictive machine learning model indicating that the first account of the user is predicted to fall below a minimum balance for the first account of the user, sending at least one communication for transferring funds from the second account back to the first account.

10. The method of claim 8 , wherein the at least one trained predictive machine learning model is further trained to predict respective timings at which user accounts are predicted to fall below respective minimum balances, the method further comprising:

inputting, into the at least one trained predictive machine learning model, at least one of: additional account data related to the first account of the user, or transaction data related to the user; and

based at least on an output of the at least one trained predictive machine learning model indicating a time at which the first account of the user is predicted to fall below a minimum balance for the first account of the user, sending, to the user device of the user, a communication to cause the user device to present another user interface including a timing at which the first account of the user is predicted to fall below the minimum balance, and further presenting an offer to extend financing to the user.

11. The method of claim 8 , wherein the indicated action includes moving at least a portion of the surplus funds to a second account, the method further comprising:

receiving information related to a transaction in which the user is a participant; and

transferring an amount associated with the transaction to the second account, wherein the amount transferred corresponds at least to a difference between a transaction amount for the transaction and a rounded-up amount associated with the transaction.

12. The method of claim 8 , wherein:

the indicated action includes transferring at least a portion of the surplus funds to a second account; and

funds in the second account are pooled from multiple users of the plurality of users for use as loaned funds to one or more other users of the plurality of users.

13. The method of claim 8 , wherein at least a portion of the historical account data for the plurality of accounts of the plurality of users that is included in the data structure, and that is included in the training data used to train the at least one predictive machine learning model, is received from a plurality of point-of-sale devices associated with a plurality of merchants that use a payment service system associated with the at least one processor.

14. The method of claim 13 , further comprising:

aggregating a portion of the historical account data in the data structure associated with users determined to be similar to each other based on at least one similarity characteristic; and

using the aggregated portion of the historical account data for training the at least one predictive machine learning model, wherein the account data related to the first account of the user is inputted into the at least one trained predictive machine learning model based at least on the user being associated with the at least one similarity characteristic.

15. One or more non-transitory computer readable media storing instructions executable by at least one processor to configure the at least one processor to perform operations comprising:

accessing a data structure including historical account data for a plurality of accounts of a plurality of users over time;

training at least one predictive machine learning model based on training data extracted at least from the data structure to generate at least one trained predictive machine learning model, the training data including the historical account data associated with the plurality of accounts of the plurality of users, the at least one trained predictive machine learning model trained based on the training data to determine account balance thresholds over which funds in user accounts are to be predicted to be surplus;

processing, account data associated with a first account using the at least one trained predictive machine learning model to determine an account balance threshold for the first account over which a portion of funds in the first account are predicted to be surplus funds for a period of time, wherein the first account is associated with a user of the plurality of users, wherein the plurality of accounts includes the first account;

causing, a user device of the user to present a user interface that indicates predicted expenses and predicted income for a plurality of periods of time including the period of time, wherein the user interface identifies the surplus funds for the period of time, and wherein the user interface includes an interactive element for indicating disposition of the surplus funds; and

in response to receiving an indication of an action to perform with respect to the surplus funds via the interactive element of the user interface, automatically sending at least one instruction for performing the indicated action to improve a yield associated with the surplus funds.

16. The one or more non-transitory computer readable media of claim 15 , wherein the indicated action includes transferring at least a portion of the surplus funds to a second account, and the at least one trained predictive machine learning model is further trained to predict times when respective balances of user accounts are predicted to fall below respective minimum balances, the operations further comprising:

inputting, into the at least one trained predictive machine learning model, at least one of: additional account data related to the first account of the user, or transaction data related to the user; and

based at least on an output of the at least one trained predictive machine learning model indicating that the first account of the user is predicted to fall below a minimum balance for the first account of the user, sending at least one communication for transferring funds from the second account back to the first account.

17. The one or more non-transitory computer readable media of claim 15 , wherein the at least one trained predictive machine learning model is further trained to predict respective timings at which user accounts are predicted to fall below respective minimum balances, the operations further comprising:

inputting, into the at least one trained predictive machine learning model, at least one of: additional account data related to the first account of the user, or transaction data related to the user; and

based at least on an output of the at least one trained predictive machine learning model indicating a time at which the first account of the user is predicted to fall below a minimum balance for the first account of the user, sending, to the user device of the user, a communication to cause the user device to present another user interface including a timing at which the first account of the user is predicted to fall below the minimum balance, and further presenting an offer to extend financing to the user.

18. The one or more non-transitory computer readable media of claim 15 , wherein the indicated action includes moving at least a portion of the surplus funds to a second account, the operations further comprising:

receiving information related to a transaction in which the user is a participant; and

transferring an amount associated with the transaction to the second account, wherein the amount transferred corresponds at least to a difference between a transaction amount for the transaction and a rounded-up amount associated with the transaction.

19. The one or more non-transitory computer readable media of claim 15 , wherein at least a portion of the historical account data for the plurality of accounts of the plurality of users that is included in the data structure, and that is included in the training data used to train the at least one predictive machine learning model, is received from a plurality of point-of-sale devices associated with a plurality of merchants that use a payment service system associated with the at least one processor.

20. The one or more non-transitory computer readable media of claim 15 , the operations further comprising:

aggregating a portion of the historical account data in the data structure associated with users determined to be similar to each other based on at least one similarity characteristic; and

using the aggregated portion of the historical account data for training the at least one predictive machine learning model, wherein the account data related to the first account of the user is inputted into the at least one trained predictive machine learning model based at least on the user being associated with the at least one similarity characteristic.

Assignments (2)

Continuity (4)

References Cited (22)