Systems and methods for altering a graphical user interface
A system can include one or more processors and one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform: selectively aggregating in-session user activity of a user with historical activity data of the user into one or more respective groups based on interactions of the user with a GUI over a period of time; predicting, using a set of predictive algorithms, one or more intents of the user based on the one or more respective groups; and facilitating a display of an altered GUI on an electronic device of the user based on the one or more intents of the user, as predicted. Other embodiments are disclosed herein.
1. A system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform operations comprising:
selectively aggregating in-session user activity of a user with historical activity data of the user into one or more respective groups based on interactions of the user with a graphical user interface (GUI) over a period of time, wherein
selectively aggregating the in-session user activity of the user further comprises:
calculating a normalized point-wise mutual information (NPMI) score between two or more actions within the in-session user activity; and
grouping the two or more actions into a common intent when the NPMI score is above a threshold,
wherein the interactions are grouped based on at least one of:
recency of interactions;
a categorization level of a hierarchical categorization scheme of an item that is a subject of an interaction of the interactions;
a type of interaction performed on the GUI;
a distribution of interaction count in the categorization level of the hierarchical categorization scheme; or
a common intent;
predicting, using a set of predictive algorithms, one or more intents of the user based on the one or more respective groups; and
facilitating a display of an altered GUI on an electronic device of the user based on the one or more intents of the user, as predicted.
2. The system of claim 1 , wherein selectively aggregating the in-session user activity of the user with the historical activity data of the user comprises:
removing at least a portion of the historical activity data based on a user access portal of the in-session user activity of the user.
3. The system of claim 2 , wherein selectively aggregating the in-session user activity of the user with the historical activity data of the user further comprises:
creating a whitelist of actions, wherein the at least the portion of the historical activity data of the user does not include actions on the whitelist of actions.
4. The system of claim 3 , wherein selectively aggregating the in-session user activity of the user with the historical activity data of the user further comprises:
weighting the in-session user activity of the user and the historical activity data of the user by a price of an item interacted with during the in-session user activity or within the historical activity data of the user.
5. The system of claim 1 , wherein the set of predictive algorithms comprises a machine learning algorithm.
6. The system of claim 1 , wherein the set of predictive algorithms are based on at least one of:
user features from complementary intents; and
learned weights of a model of intent type.
7. The system of claim 1 , wherein using the set of predictive algorithms comprises:
applying a multi-class classification algorithm to the in-session user activity of the user and the historical activity data of the user.
8. The system of claim 1 , wherein the computing instructions, when executed on the one or more processors, further cause the one or more processors to perform an operation comprising:
training the set of predictive algorithms on the in-session user activity of the user and the historical activity data of the user as more data is gathered from a user session for the user.
9. The system of claim 1 , wherein facilitating the display of the altered GUI comprises:
re-ranking the one or more intents of the user, as predicted, into a re-ranked order; and
facilitating a display of GUI elements related to the one or more intents of the user, as predicted and re-ranked, in the re-ranked order.
10. The system of claim 1 , wherein the computing instructions, when executed on the one or more processors, further cause the one or more processors to perform an operation comprising:
re-ranking the one or more intents of the user based on a dot product of top ranked intents of the one or more intents of the user.
11. A method being implemented via execution of computing instructions configured to run at one or more processors and stored at non-transitory computer-readable media, the method comprising:
selectively aggregating in-session user activity of a user with historical activity data of the user into one or more respective groups based on interactions of the user with a graphical user interface (GUI) over a period of time, wherein selectively aggregating the in-session user activity of the user further comprises:
calculating a normalized point-wise mutual information (NPMI) score between two or more actions within the in-session user activity; and
grouping the two or more actions into a common intent when the NPMI score is above a threshold,
wherein the interactions are grouped based on at least one of:
recency of interactions;
a categorization level of a hierarchical categorization scheme of an item that is a subject of an interaction of the interactions;
a type of interaction performed on the GUI;
a distribution of interaction count in the categorization level of the hierarchical categorization scheme; or
a common intent;
predicting, using a set of predictive algorithms, one or more intents of the user based on the one or more respective groups; and
facilitating a display of an altered GUI on an electronic device of the user based on the one or more intents of the user, as predicted.
12. The method of claim 11 , wherein selectively aggregating the in-session user activity of the user with the historical activity data of the user comprises:
removing at least a portion of the historical activity data based on a user access portal of the in-session user activity of the user.
13. The method of claim 12 , wherein selectively aggregating the in-session user activity of the user with the historical activity data of the user further comprises:
creating a whitelist of actions, wherein the at least the portion of the historical activity data of the user does not include actions on the whitelist of actions.
14. The method of claim 13 , wherein selectively aggregating the in-session user activity of the user with the historical activity data of the user further comprises:
weighting the in-session user activity of the user and the historical activity data of the user by a price of an item interacted with during the in-session user activity or within the historical activity data of the user.
15. The method of claim 11 , wherein the set of predictive algorithms comprises a machine learning algorithm.
16. The method of claim 11 , wherein the set of predictive algorithms are based on at least one of:
user features from complementary intents; and
learned weights of a model of intent type.
17. The method of claim 11 , wherein using the set of predictive algorithms comprises:
applying a multi-class classification algorithm to the in-session user activity of the user and the historical activity data of the user.
18. The method of claim 11 further comprising:
training the set of predictive algorithms on the in-session user activity of the user and the historical activity data of the user as more data is gathered from a user session for the user.
19. The method of claim 11 , wherein facilitating the display of the altered GUI comprises:
re-ranking the one or more intents of the user, as predicted, into a re-ranked order; and
facilitating a display of GUI elements related to the one or more intents of the user, as predicted and re-ranked, in the re-ranked order.
20. A non-transitory computer-readable medium storing instructions, wherein the instructions, upon execution by a processor, cause the processor to perform operations comprising:
selectively aggregating in-session user activity of a user with historical activity data of the user into one or more respective groups based on interactions of the user with a graphical user interface (GUI) over a period of time, wherein
selectively aggregating the in-session user activity of the user further comprises:
calculating a normalized point-wise mutual information (NPMI) score between two or more actions within the in-session user activity; and
grouping the two or more actions into a common intent when the NPMI score is above a threshold,
wherein the interactions are grouped based on at least one of:
recency of interactions;
a categorization level of a hierarchical categorization scheme of an item that is a subject of an interaction of the interactions;
a type of interaction performed on the GUI;
a distribution of interaction count in the categorization level of the hierarchical categorization scheme; or
a common intent;
predicting, using a set of predictive algorithms, one or more intents of the user based on the one or more respective groups; and
facilitating a display of an altered GUI on an electronic device of the user based on the one or more intents of the user, as predicted.
21. The non-transitory computer-readable medium of claim 20 , wherein the operations further comprise:
removing at least a portion of the historical activity data based on a user access portal of the in-session user activity of the user.