Systems and methods for casual spending recommendations to modify customer spending

1. A system for providing spending recommendations to a user, the system comprising:

at least one memory unit storing instructions; and

at least one processor configured to execute the instructions to perform operations comprising:

maintaining an account card service for an account associated with a first user;

receiving first user shopping data based on a plurality of user shopping purchases over a first time period;

determining, based on a Bayesian model, at least one of a temporal or a geographic trigger of the user shopping purchases by extrapolating rate of change data from a graph corresponding to the Bayesian model and determining an effect on user spending patterns based on the extrapolated rate of change data;

generating for displaying, on a user device, a message to the user indicating the trigger, wherein the message comprises a suggestion for a user spending recommendation based on the effect on the user spending patterns;

adding a spending recommendation rule to the Bayesian model based on user input; and

generating for displaying, on the user device, a personalized spending recommendation, based on the rule.

2. The system of claim 1 , wherein the operations further comprise categorizing the user shopping data by at least one of purchase quantity, purchase price, time of purchase, or total amount spent.

3. The system of claim 1 , wherein the graph is a directed graph or a bar graph.

4. The system of claim 3 , wherein the operations further comprise:

temporarily freezing a credit line of an account card associated with the account card service based upon at least the trigger; and

generating for displaying, on the user device, a message that informs the user of an ability to override a temporary freezing of the credit line.

5. The system of claim 4 , wherein the receiving second user shopping data and user behavior over a second time period.

6. The system of claim 5 , wherein the operations further comprise

modifying the rule based on the second user shopping data and user behavior.

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

monitoring the spending patterns of the user; and

updating the personalized spending recommendation.

8. A computer-implemented method for providing spending recommendations to a user, the method comprising:

maintaining an account card service for an account associated with a first user;

receiving first user shopping data based on a plurality of user shopping purchases over a first time period;

determining, based on a Bayesian model, at least one of a temporal or a geographic trigger of the user shopping purchases by extrapolating rate of change data from a graph corresponding to the Bayesian model and determining an effect on user spending patterns based on the extrapolated rate of change data;

generating for display, on a user device, a message to the user indicating the trigger, wherein the message comprises a suggestion for a user spending recommendation based on the effect on the user spending patterns;

adding a spending recommendation rule to the Bayesian model based on user input; and

generating for display, on the user device, a personalized spending recommendation, based on the rule.

9. The method of claim 8 , further comprising categorizing the user shopping data by at least one of purchase quantity, purchase price, time of purchase, or total amount spent.

10. The method of claim 8 , further comprising temporarily freezing a credit line of an account card associated with the account card service based upon at least the trigger.

11. The method of claim 10 , wherein

the graph is a directed graph or a bar graph.

12. The method of claim 10 , further comprising:

generating for display, on the user device, a message that informs the user of an ability to override a temporary freezing of the credit line; and

receiving second user shopping data and user behavior over a second time period.

13. The method of claim 12 , further comprising

modifying the rule based on the second user shopping data and user behavior.

14. The method of claim 13 , further comprising:

monitoring the spending patterns of the user; and

updating the personalized spending recommendation.

15. A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform operations comprising:

maintaining an account card service for an account associated with a first user;

receiving first user shopping data based on a plurality of user shopping purchases over a first time period;

determining, based on a Bayesian model, at least one of a temporal or a geographic trigger of the user shopping purchases by extrapolating rate of change data from a graph corresponding to the Bayesian model and determining an effect on user spending patterns based on the extrapolated rate of change data;

generating for display, on a user device, a message to the user indicating the trigger, wherein the message comprises a suggestion for a user spending recommendation based on the effect on the user spending patterns;

adding a spending recommendation rule to the Bayesian model based on user input; and

generating for display, on the user device, a personalized spending recommendation, based on the rule.

16. The computer-readable medium of claim 15 , wherein the operations further comprise categorizing the user shopping data by at least one of purchase quantity, purchase price, time of purchase, or total amount spent.

17. The computer-readable medium of claim 15 , wherein the graph is a directed graph or a bar graph.

18. The computer-readable medium of claim 15 , wherein the operations further comprise:

temporarily freezing a credit line of an account card associated with the account card service based upon at least the trigger; and

generating for display, on the user device, a message that informs the user of an ability to override a temporary freezing of the credit line.

19. The computer-readable medium of claim 18 , wherein the operations further comprise receiving second user shopping data and user behavior over a second time period.

20. The computer-readable medium of claim 19 , wherein the operations further comprise modifying the rule based on the second user shopping data and user behavior.