System and Method for Context-Aware Recommendation through User Activity Change Detection

• US 20150332372A1
• Filed: 05/19/2014
• Published: 11/19/2015
• Est. Priority Date: 05/19/2014
• Status: Active Grant

• Current Assignee: Monetate, Inc. (StartApp, Inc.)
• Original Assignee: Baynote Incorporated (StartApp, Inc.)
• Inventors: Hariri, Negar, Chan, HawWuen
• Granted Patent: US 9,836,765 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/90324 using system suggestions
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 3/048 Interaction techniques based on graphical user interfaces [GUI]
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G06Q 30/0631 Item recommendations

Abstract

Example systems and methods for context-aware recommendation generation are described. In one implementation, item models are built using user preference data of multiple users and item information of multiple items. When a recommendation request corresponding to a user is received, the profile of that user is retrieved from the user profile database. Given the profile of the user and the item models, utility scores are then computed for the candidate items. Our system exploits a novel approach to detect any sudden and significant changes in the preference data of the given user. If a change is detected, the utility scores are adapted to prioritize the user'"'"'s most recent preferences. The computed utility scores are used as the basis for ranking the items. A subset of items with highest scores is then selected as recommendations and is presented to the user.

Claims

1. A method comprising:

receiving, by one or more processors of a computing device, a recommendation request corresponding to a user;

retrieving a user profile of the user based on the recommendation request, the user profile comprising user preference data of the user associated with one or more items and user demographic information of the user;

computing a utility value of an item based on the user profile and item models built based on user preference data of a plurality of users and item information of a plurality of items; and

selecting a subset of items with highest utility values as the recommendation list.

2. The method of claim 1, further comprising:

detecting any activity changes of the user; and

modifying the item utility values in response to the predicted user activity changes.

3. The method of claim 2, wherein at each round t of interaction with a user, the user'"'"'s activities (interactions) in the interval I_t=(t−

L, t] are modeled and compared with the model of activities in the interval I_(t-L)=(t−

2L, t−

L] where L is a fixed pre-specified parameter representing the length of the activity interval. Any significant change between the models of I_t and I_(t-L) is determined as an activity change of the user.

4. The method of claim 3, wherein detecting significant changes between the models of I_t and I_(t-L) comprises applying a change point analysis approach such as cumulative sum control chart (CUSUM) analysis.

5. The method of claim 3, wherein the modifying the value in response to the user activity change comprises:

computing an additional value of the item based on an additional user profile and the item models, the additional user profile comprising user preference data that is collected after the user activity change is detected; and

modifying the value based on the additional value.

6. The method of claim 4, wherein the additional user profile excludes user preference data that is collected before the user activity change is detected.

7. The method of claim 1, further comprising:

tracking user activities of a plurality of users;

generating activity events based on the user activities;

extracting the user preference data of the plurality of users associated with the plurality of items based on the activity events; and

generating the item models based on the user preference data and the item information of the plurality of items; and

providing the recommendations using the item models.

8. The method of claim 6, wherein the generating the item models based on the user preference data and the item information of the plurality of items comprises generating the item models using a combination of content-based features associated with the plurality of items and collaborative-based features associated with the user preference data.

9. The method of claim 7, further comprising:

generating the content-based features based on the item information of the plurality of items, the item information comprising at least one of categorical information, a title, a price, a color, and an item description that are associated with an individual item of the plurality of items.

10. The method of claim 7, further comprising:

extracting the collaborative-based features from the user preference data and the item information of the plurality of items.

11. The method of claim 7, further comprising:

generating the collaborative-based features by applying a dimensionality reduction method on user preference data.

12. The method of claim 10, wherein the dimensionality reduction method comprises a principal component analysis (PCA) analysis.

13. The method of claim 7, wherein the providing the recommendation using the item models comprises:

receiving a recommendation request corresponding to a user;

computing a value of an item based on a user profile associated with the user and the item models, the user profile comprising the user preference data of the user associated with one or more items and user demographic information of the user;

detecting a user activity change of the user;

modifying the value in response to the user activity change; and

generating the recommendation associated with the item based on the value.

14. An apparatus comprising:

a memory configured to store data and one or more sets of instructions; and

one or more processors coupled to the memory, the one or more processors configured to execute the one or more sets of instructions and perform operations comprising;

receiving, by one or more processors of a computing device, a recommendation request corresponding to a user,

retrieving a user profile of the user based on the recommendation request, the user profile comprising user preference data of the user associated with one or more items and user demographic information of the user,

computing a value of an item based on the user profile and item models built based on user preference data of a plurality of users and item information of a plurality of items, and

generating a recommendation associated with the item based on the value.

18. The apparatus of claim 19, wherein the additional user profile excludes user preference data that is collected before the user activity change is detected.

15. The apparatus of claim 16, wherein the operations further comprise:

detecting a user activity change of the user; and

modifying the value in response to the user activity change.

16. The apparatus of claim 17, wherein the detecting a user activity change of the user comprises detecting the user activity change by applying a change point analysis approach such as cumulative sum control chart (CUSUM) analysis.

17. The apparatus of claim 18, wherein the modifying the value in response to the user activity change comprises:

computing an additional value of the item based on an additional user profile and the item models, the additional user profile comprising user preference data that is collected after the user activity change is detected; and

modifying the value based on the additional value.