Visual mining of user behavior patterns
Systems and methods of visual mining of user behavior patterns are disclosed. A plurality of clickstreams may be received. Each clickstream may represent a corresponding sequence of user actions. A visual representation of each clickstream may be caused to be displayed on a device. Each visual representation may comprise a distinct graphical element for each user action of the corresponding clickstream, and each visual representation may be configured to indicate a frequency level of the corresponding clickstream. Each distinct graphical element may comprise a geometric shape and a corresponding color that distinctly represents the corresponding user action. Graphical elements of each visual representation may comprise a size that is proportional to the frequency level of the corresponding clickstream. An indication of a selection of one of the visual representations may be received, and additional information about the corresponding clickstream may be caused to be displayed on the device.
1. A visual data analytics method comprising:
receiving, by an application server, a plurality of clickstreams associated with a user interaction with a website;
iteratively training, by the application server using a competitive learning algorithm, a self-organizing map framework to obtain a set of trained vector prototypes representing clusters of clickstreams, wherein the plurality of clickstreams is represented in the self-organizing map framework by a set of user actions and probabilities associated with individual user actions, wherein the training includes, for individual vector prototypes:
collecting a list of clickstreams that match the individual vector prototype based on a neighborhood size around the individual vector prototype;
adjusting the individual vector prototype using the list of clickstreams; and
decreasing the neighborhood size upon iteration;
generating, by the application server using the set of trained vector prototypes, a visual representation of a user behavior pattern; and
causing, by the application server, the visual representation of the user behavior pattern to be displayed on a device.
2. The method of claim 1 ,
wherein the plurality of clickstreams is represented in the self-organizing map framework by Markov chains, and wherein the competitive learning algorithm is an expectation-maximization algorithm.
3. The method of claim 1 , wherein the self-organizing map framework includes a plurality of nodes, and wherein each node is associated with one of a plurality of vector prototypes representative of a data input.
4. The method of claim 1 , wherein the plurality of clickstreams include data input and data upload in the user interaction with the website.
5. The method of claim 1 , wherein the visual representation comprises a geometric shape and color used to represent a user action.
6. The method of claim 1 , wherein a size of the visual representation is proportional to a frequency level of the plurality of clickstreams.
7. The method of claim 4 , wherein the data input includes at least one of a color preference, an item type, and a pricing selection.
8. A computer system comprising:
a computer processor circuit; and
a computer memory circuit storing instructions that when executed by the computer processor circuit cause the computer system to perform operations including:
receiving a plurality of clickstreams associated with a user interaction with a website;
iteratively training, using a competitive learning algorithm, a self-organizing map framework to obtain a set of trained vector prototypes representing clusters of clickstreams, wherein the plurality of clickstreams is represented in the self-organizing map framework by a set of user actions and probabilities associated with individual user actions, wherein the training includes, for individual vector prototypes:
collecting a list of clickstreams that match the individual vector prototype based on a neighborhood size around the individual vector prototype;
adjusting the individual vector prototype using the list of clickstreams; and
decreasing the neighborhood size upon iteration;
generating a visual representation of a user behavior pattern using the set of trained vector prototypes; and
causing the visual representation of the user behavior pattern to be displayed on a device.
9. The computer system of claim 8 , wherein the operations further include:
wherein the plurality of clickstreams is represented in the self-organizing map framework by Markov chains, and wherein the competitive learning algorithm is an expectation-maximization algorithm.
10. The computer system of claim 8 , wherein the self-organizing map framework includes a plurality of nodes, and wherein each node is associated with one of a plurality of vector prototypes representative of a data input.
11. The computer system of claim 8 , wherein the plurality of clickstreams include data input and data upload in the user interaction with the website.
12. The computer system of claim 8 , wherein the visual representation comprises a geometric shape and color used to represent a user action.
13. The computer system of claim 8 , wherein a size of the visual representation is proportional to a frequency level of the plurality of clickstreams.
14. The computer system of claim 11 , wherein the data input includes at least one of a color preference, an item type, and a pricing selection.
15. A non-transitory machine-readable medium having stored thereon machine-readable instructions executable to cause a computer system to perform operations comprising:
receiving a plurality of clickstreams associated with a user interaction with a website;
iteratively training, using a competitive learning algorithm, a self-organizing map framework to obtain a set of trained vector prototypes representing clusters of clickstreams, wherein the plurality of clickstreams is represented in the self-organizing map framework by a set of user actions and probabilities associated with individual user actions, wherein the training includes, for individual vector prototypes:
collecting a list of clickstreams that match the individual vector prototype based on a neighborhood size around the individual vector prototype;
adjusting the individual vector prototype using the list of clickstreams; and
decreasing the neighborhood size upon iteration;
generating a visual representation of a user behavior pattern using the set of trained vector prototypes; and
causing the visual representation of the user behavior pattern to be displayed on a device.
16. The non-transitory machine-readable medium of claim 15 , wherein the operations further include:
wherein the plurality of clickstreams is represented in the self-organizing map framework by Markov chains, and wherein the competitive learning algorithm is an expectation-maximization algorithm.
17. The non-transitory machine-readable medium of claim 15 , wherein the self-organizing map framework includes a plurality of nodes, and wherein each node is associated with one of a plurality of vector prototypes representative of a data input.
18. The non-transitory machine-readable medium of claim 15 , wherein the plurality of clickstreams include data input and data upload in the user interaction with the website.
19. The non-transitory machine-readable medium of claim 15 , wherein the visual representation comprises a geometric shape to represent a user action.
20. The non-transitory machine-readable medium of claim 18 , wherein the data input includes at least one of a color preference, an item type, and a pricing selection.