Recommendations in a computing advice facility

• US 10,318,534 B2
• Filed: 03/16/2015
• Issued: 06/11/2019
• Est. Priority Date: 07/12/2011
• Status: Active Grant

• Current Assignee: PayPal, Inc. (PayPal Holdings, Inc.)
• Original Assignee: PayPal, Inc. (PayPal Holdings, Inc.)
• Inventors: Pinckney, Thomas, Dixon, Christopher, Gattis, Matthew Ryan
• Primary Examiner(s): Zhen, Li B.
• Assistant Examiner(s): Pellett, Daniel T
• Application Number:
  US14/659,127
• Publication Number:
  US 20150186383A1
• Time in Patent Office: 1,548 Days
• Field of Search: None
• CPC Class Codes: G06F 16/2425 Iterative querying; Query formulation based on the results of a preceding query
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/355 Class or cluster creation or modification
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/045 Explanation of inference; Explainable artificial intelligence [XAI]; Interpretable artificial intelligence
• CPC Class Codes: G06N 5/048 Fuzzy inferencing

Abstract

According to various embodiments, a ratings matrix including matrix values is generated, each row of the ratings matrix identifying one of a plurality of users, each column of the ratings matrix identifying one of a plurality of items, and each of the matrix values corresponding to a known affinity rating describing a degree of affinity associated with one of the users and one of the items. The ratings matrix may include a missing entry representing an unknown affinity rating. According to various embodiments, a revised ratings matrix is generated by factoring the ratings matrix into a user matrix and an item matrix, the revised ratings matrix being the product of the user matrix and the item matrix and including at least one entry representing a predicted affinity rating in place of the missing entry.

Claims

1. A method comprising:

tracking, by a computing facility, user online behavior of a plurality of users including buying behaviors, browsing behavior, social networking behavior, location-based behaviors;

determining one or more inferences of user preferences based on the tracking of the online behavior;

presenting one or more questions to one or more of the users based on the one or more inferences;

receiving one or more responses to the one or more questions;

generating a ratings matrix including matrix values based on the one or more inferences and based on the one or responses to the one or more questions, each row of the ratings matrix identifying one of a plurality of users, each column of the ratings matrix identifying one of a plurality of items, and each of the matrix values corresponding to a known affinity rating describing a degree of affinity associated with one of the users and one of the items, the ratings matrix including a missing entry representing an unknown affinity rating;

estimating, based on the one or more inferences and based on one or responses to the one or more questions, confidence values associated with one or more of the known affinity ratings in the ratings matrix;

generating a confidence matrix that includes the confidence values;

estimating a probability that a missing affinity rating in the ratings matrix that describes an affinity associated with a specific user and a specific item corresponds to a negative affinity rating;

replacing the missing affinity rating in the ratings matrix with a predicted affinity rating that is based on the one or more inferences and based on one or responses to the one or more questions;

inserting a confidence value associated with the specific user and the specific item in the confidence matrix, where the confidence value has a value equal to the probability;

receiving, from the specific user, an online search inquiry that is related to the specific item;

determining, based on the ratings matrix in response to receiving the online search inquiry, a recommendation for the specific user with respect to the specific item, the recommendation being based on the predicted affinity rating and the confidence value associated with the specific user and the specific item; and

providing the recommendation to the specific user as a search result of the online search inquiry.

2. The method of claim 1, further comprising:

generating a revised ratings matrix by factoring the ratings matrix into a user matrix and an item matrix, the revised ratings matrix being the product of the user matrix and the item matrix and including at least one entry representing the predicted affinity rating in place of the missing entry.

3. The method of claim 2, wherein each row of the user matrix includes user parameters describing each user in the ratings matrix, and wherein each column of the item matrix includes item parameters describing each item in the ratings matrix.

4. The method of claim 3, further comprising:

inserting a new row identifying a new user into the ratings matrix, the new row including a known affinity rating describing a degree of affinity associated with the new user; and

estimating user parameters describing the new user, based on the known affinity rating describing the degree of affinity associated with the new user and the item parameters included in the item matrix.

5. The method of claim 4, further comprising:

predicting an affinity rating describing a degree of affinity associated with the new user, based on the estimated user parameters and the item parameters included in the item matrix.

6. The method of claim 3, further comprising:

inserting a new column identifying a new item into the ratings matrix, the new column including a known affinity rating describing a degree of affinity associated with the new item; and

estimating item parameters describing the new item, based on the known affinity rating describing the degree of affinity associated with the new item and the user parameters included in the user matrix.

7. The method of claim 6, further comprising:

predicting an affinity rating describing a degree of affinity associated with the new item, based on the estimated item parameters and the user parameters included in the user matrix.

8. The method of claim 2, further comprising:

receiving a new affinity rating describing a degree of affinity associated with a particular user and a particular item; and

revising user parameters describing the particular user in the user matrix based on the new affinity rating.

9. The method of claim 2, further comprising:

receiving a new affinity rating describing a degree of affinity associated with a particular user and a particular item; and

revising item parameters describing the particular item in the item matrix based on the new affinity rating.

10. The method of claim 2, further comprising:

factoring the ratings matrix into the user matrix and the item matrix to generate the revised ratings matrix, by weighting the predicted affinity rating in the ratings matrix based on the confidence value in the confidence matrix.

11. The method of claim 2, further comprising:

estimating a second probability that the specific user had an opportunity to rate the specific item;

using a low affinity rating for the predicted affinity rating; and

giving the confidence value a value equal to the second probability.

12. The method of claim 11, further comprising:

factoring the ratings matrix into the user matrix and the item matrix to generate the revised ratings matrix, by weighting the low affinity rating in the ratings matrix based on the confidence value in the confidence matrix.

13. The method of claim 3, further comprising:

determining that a first user is similar to a second user, based on the user parameters in the user matrix describing the first and second users; and

generating a recommendation of a particular item for the second user, based on a recommendation of the particular item for the first user.

14. The method of claim 3, further comprising

determining that a first item is similar to a second item, based on the item parameters in the item matrix describing the first and second items;

and

generating a recommendation of the second item for a particular user, based on a recommendation of the first item for the particular user.

15. The method of claim 1, further comprising

counting a number of common affinity ratings between a first user and a second user,

wherein each of the common affinity ratings describe a degree of affinity associated with a first item or a second item that is determined to be similar to the first item;

and

determining that the first user is similar to the second user, based on the number of common affinity ratings.

16. One or more non-transitory machine-readable storage media having embodied thereon instructions executable by one or more machines to perform operations comprising:

tracking, by a computing facility, user online behavior of a plurality of users including buying behaviors, browsing behavior, social networking behavior, location-based behaviors;

determining one or more inferences of user preferences based on the tracking of the online behavior;

presenting one or more questions to one or more of the users based on the one or more inferences;

receiving one or more responses to the one or more questions;

generating a ratings matrix including matrix values based on the one or more inferences and based on the one or responses to the one or more questions, each row of the ratings matrix identifying one of a plurality of users, each column of the ratings matrix identifying one of a plurality of items, and each of the matrix values corresponding to a known affinity rating describing a degree of affinity associated with one of the users and one of the items, the ratings matrix including a missing entry representing an unknown affinity rating;

estimating, based on the one or more inferences and based on one or responses to the one or more questions, confidence values associated with one or more of the known affinity ratings in the ratings matrix;

generating a confidence matrix that includes the confidence values;

estimating a probability that a missing affinity rating in the ratings matrix that describes an affinity associated with a specific user and a specific item corresponds to a negative affinity rating;

replacing the missing affinity rating in the ratings matrix with a predicted affinity rating that is based on the one or more inferences and based on one or responses to the one or more questions;

inserting a confidence value associated with the specific user and the specific item in the confidence matrix, where the confidence value has a value equal to the probability;

receiving, from the specific user, an online search inquiry that is related to the specific item;

determining, based on the ratings matrix in response to receiving the online search inquiry, a recommendation for the specific user with respect to the specific item, the recommendation being based on the predicted affinity rating and the confidence value associated with the specific user and the specific item; and

providing the recommendation to the specific user as a search result of the online search inquiry.

17. The one or more storage media of claim 16, wherein the operations further comprise:

generating a revised ratings matrix by factoring the ratings matrix into a user matrix and an item matrix, the revised ratings matrix being the product of the user matrix and the item matrix and including at least one entry representing the predicted affinity rating in place of the missing entry.

18. The one or more storage media of claim 17, wherein the operations further comprise:

factoring the ratings matrix into the user matrix and the item matrix to generate the revised ratings matrix, by weighting the predicted affinity rating in the ratings matrix based on the confidence value in the confidence matrix.

19. A system comprising:

one or more processors;

one or more memory devices holding an instruction set executable the one or more processors to cause the system to perform operations comprising;

tracking, by a computing facility, user online behavior of a plurality of users including buying behaviors, browsing behavior, social networking behavior, location-based behaviors;

determining one or more inferences of user preferences based on the tracking of the online behavior;

presenting one or more questions to one or more of the users based on the one or more inferences;

receiving one or more responses to the one or more questions;

generating a ratings matrix including matrix values based on the one or more inferences and based on the one or responses to the one or more questions, each column of the ratings matrix identifying one of a plurality of items, and each of the matrix values corresponding to a known affinity rating describing a degree of affinity associated with one of the users and one of the items, the ratings matrix including a missing entry representing an unknown affinity rating;

estimating confidence values associated with one or more of the known affinity ratings in the ratings matrix;

generating a confidence matrix that includes the confidence values;

estimating, based on the one or more inferences and based on one or responses to the one or more questions, a probability that a missing affinity rating in the ratings matrix that describes an affinity associated with a specific user and a specific item corresponds to a negative affinity rating;

replacing the missing affinity rating in the ratings matrix with a predicted affinity rating that is based on the one or more inferences and based on one or responses to the one or more questions;

inserting a confidence value associated with the specific user and the specific item in the confidence matrix, where the confidence value has a value equal to the probability;

receiving, from the specific user, an online search inquiry that is related to the specific item;

determining, based on the ratings matrix in response to receiving the online search inquiry, a recommendation for the specific user with respect to the specific item, the recommendation being based on the predicted affinity rating and the confidence value associated with the specific user and the specific item; and

providing the recommendation to the specific user as a search result of the online search inquiry.

20. The system of claim 19, wherein the operations further comprise:

generating a revised ratings matrix by factoring the ratings matrix into a user matrix and an item matrix, the revised ratings matrix being the product of the user matrix and the item matrix and including at least one entry representing the predicted affinity rating in place of the missing entry.