Systems and methods for machine learning based execution of actions based on calendar event data
A method for executing actions based on event data using machine learning is disclosed. The method comprises: receiving occasion data associated with a user; analyzing, using a trained machine learning model, the occasion data to identify an occasion associated with a first classification, wherein the trained machine learning model has been trained based on (i) training occasion data that includes information regarding one or more occasions associated with the training occasion data and (ii) training classification data that includes a prior classification for each of the occasions, to learn relationships between the training occasion data and the training classification data, such that the trained machine learning model is configured to use the learned relationships to identify an occasion associated with a first classification in response to input of the occasion data; determining an action based on the occasion associated with the first classification; and automatically executing the action.
1. A computer-implemented method for executing actions based on event data using one or more machine learning models, the method comprising:
receiving, by one or more processors, occasion data from an electronic database associated with a user, wherein the electronic database includes a plurality of occasions;
analyzing, by the one or more processors, using a trained machine learning model, the occasion data to identify an occasion associated with a first classification, wherein the trained machine learning model has been trained based on (i) training occasion data that includes information regarding one or more occasions associated with the training occasion data and (ii) training classification data that includes a prior classification for each of the one or more occasions, to learn relationships between the training occasion data and the training classification data, such that the trained machine learning model is configured to use the learned relationships to identify an occasion associated with a first classification in response to input of the occasion data;
upon identifying the occasion associated with the first classification;
(i) tuning the trained machine learning model by inputting to the trained machine learning model the occasion associated with the first classification; and
(ii) determining, by the one or more processors, an action based on the occasion associated with the first classification; and
automatically executing, by the one or more processors, the action, wherein the action includes modifying the occasion data in the electronic database.
2. The computer-implemented method of claim 1 , wherein determining the action further includes determining the action using a second trained machine learning model, wherein the second trained machine learning model has been trained based on (i) training classification data that includes information regarding one or more occasions associated with the first classification and (ii) training action data that includes prior actions for each of the one or more occasions associated with the first classification, to learn relationships between the training classification data and the training action data, such that the trained machine learning model is configured to use the learned relationships to determine an action in response to input of the occasion associated with the first classification.
3. The computer-implemented method of claim 1 , further comprising:
causing to display, by the one or more processors, via a graphical user interface associated with the user, a notification that the action has been automatically executed.
4. The computer-implemented method of claim 3 , further comprising:
automatically receiving, by the one or more processors, data indicating a change to the occasion associated with the first classification; and
upon receiving the data indicating the change, automatically executing, by the one or more processors, a second action based on the data indicating the change.
5. The computer-implemented method of claim 4 , wherein the data indicating the change includes user input data received via the graphical user interface.
6. The computer-implemented method of claim 1 , wherein:
the first classification is financial transactions; and
the action further includes one or more of:
scheduling a bill payment for the user;
transmitting a payment from a financial institution account associated with the user to an entity; or
transmitting instructions to remove the occasion associated with the first classification from the electronic database.
7. The computer-implemented method of claim 2 , wherein the training action data further includes prior user input data indicating a prior action for each of the one or more occasions associated with the first classification.
8. The computer-implemented method of claim 1 , further comprising:
causing to display, by the one or more processors, graphical depictions of the plurality of occasions via a graphical user interface;
analyzing, by the one or more processors, using the trained machine learning model, the occasion data to identify all occasions of the plurality of occasions associated with a first classification; and
modifying, by the one or more processors, the graphical user interface to only present graphical depictions of occasions associated with the first classification.
9. The computer-implemented method of claim 1 , wherein the trained machine learning model is a natural language processing model.
10. The computer-implemented method of claim 1 , wherein the determining the action based on the occasion associated with the first classification is further determined based on a user input received via a graphical user interface.
11. A computer-implemented method for executing actions based on event data using machine learning models, the method comprising:
receiving, by one or more processors, occasion data from an electronic database associated with a user, wherein the electronic database includes a calendar comprising a plurality of occasions;
causing to display, by the one or more processors, graphical depictions of the plurality of occasions;
analyzing, by the one or more processors, using a first trained machine learning model, the occasion data to identify an occasion associated with a first classification, wherein the first trained machine learning model has been trained based on (i) training occasion data that includes information regarding one or more occasions associated with the training occasion data and (ii) training classification data that includes a prior classification for each of the one or more occasions, to learn relationships between the training occasion data and the training classification data, such that the trained machine learning model is configured to use the learned relationships to identify an occasion associated with a first classification in response to input of the occasion data;
upon identifying the occasion associated with the first classification, determining, by the one or more processors, using a second trained machine learning model, an action based on the occasion associated with the first classification, wherein the second trained machine learning model has been trained based on (i) training classification data that includes information regarding one or more occasions associated with the first classification and (ii) training action data that includes prior actions for each of the one or more occasions associated with the first classification, to learn relationships between the training classification data and the training action data, such that the trained machine learning model is configured to use the learned relationships to determine an action in response to input of the occasion associated with the first classification;
tuning the second trained machine learning model by inputting to the second trained machine learning model the action in response to the occasion associated with the first classification; and
automatically executing, by the one or more processors, the action, wherein the action comprises modifying the calendar in the electronic database to generate one or more of:
a scheduled bill payment for the user;
a reminder to transmit a payment from a financial institution account associated with the user to an entity; or
removal of the occasion associated with the first classification from the electronic database.
12. The computer-implemented method of claim 11 , further comprising:
causing to display, by the one or more processors, via a graphical user interface associated with the user, a notification that the action has been automatically executed.
13. The computer-implemented method of claim 12 , further comprising:
automatically receiving, by the one or more processors, data indicating a change to the occasion associated with the first classification; and
upon receiving the data indicating the change, automatically executing, by the one or more processors, a second action based on the data indicating the change.
14. The computer-implemented method of claim 13 , wherein:
the data indicating the change includes user input data received via the graphical user interface; and
the training action data further includes prior user input data indicating a prior action for each of the one or more occasions associated with the first classification.
15. The computer-implemented method of claim 11 , wherein the first classification is financial transactions.
16. The computer-implemented method of claim 15 , wherein the action further includes one or more of:
scheduling a bill payment for the user;
transmitting the payment from the financial institution account associated with the user to an entity; or
transmitting instructions to remove the occasion associated with the first classification from the electronic database.
17. The computer-implemented method of claim 11 , further comprising:
analyzing, by the one or more processors, using the first trained machine learning model, the occasion data to identify all occasions of the plurality of occasions associated with a first classification; and
modifying, by the one or more processors, a graphical user interface to only present graphical depictions of occasions associated with the first classification.
18. The computer-implemented method of claim 11 , wherein the first trained machine learning model is a natural language processing model.
19. The computer-implemented method of claim 11 , wherein the determining the action based on the occasion associated with the first classification is further determined based on a user input received via a graphical user interface.
20. A system for executing actions based on event data using machine learning models, the system comprising:
at least one memory storing instructions; and
at least one processor executing the instructions to perform a process including:
receiving occasion data from a plurality of electronic databases associated with a user, wherein at least one of the electronic databases includes a calendar comprising a plurality of occasions;
analyzing, using a trained machine learning model, the occasion data to identify an occasion associated with a first classification;
upon identifying the occasion associated with the first classification;
(i) tuning the trained machine learning model by inputting to the trained machine learning model the occasion associated with the first classification; and
(ii) determining an action based on the occasion associated with the first classification; and
automatically executing the action, wherein the action includes modifying the occasion data in the calendar.