IP Library › Granted Patent US 12,481,711
Granted Patent B2
US 12,481,711 · App. 18/479,754 · Granted Nov 25, 2025

Systems, apparatuses, and methods for providing a quality score based recommendation

Inventors: Chandra Khatri (Atlanta, GA); Steven Hui Luan (Fremont, CA); Michael Tanaka (San Ramon, CA); Praveen K. Boinapalli (Pleasanton, CA)
Assignee: eBay Inc.
G06F16/9535
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,481,711
App. No.
18/479,754
Granted
Nov 25, 2025
Kind
B2
Abstract

One or more of the systems, apparatuses, or methods discussed herein can include a quality score for a plurality of item listings or collections of item listings. Data sparseness can be avoided, as the quality score is based on inherent properties of the listing. An item listing can be recommended to a user based on the quality score. In one or more embodiments, a method can include determining a plurality of quality scores including a quality score for each of a plurality of item listings or a plurality of collections of item listings, the quality scores determined independent of a user's attributes and independent of the user's contextual information, the contextual information corresponding to details of the user's access to a website, and recommending an item listing or collection of item listings to a user based on the quality scores and the contextual information.

Claims (63)

1 . A system for contextual filtering, comprising:

one or more hardware processors; and

a non-transitory machine-readable medium storing instructions that, when executed by the one or more hardware processors, cause the one or more hardware processors to perform operations comprising:

generating contextual information for a client device used to access a website hosting a plurality of item listings by analyzing data traffic between the client device and the website, the contextual information independent of user attributes that are inherent to a user;

selecting one or more item listings from the plurality of item listings by:

filtering the plurality of item listings based on the contextual information, the filtering producing a subset of pre-filtered item listings of the plurality of item listings;

generating, using a machine-learning model, quality scores for respective item listings of the subset of pre-filtered item listings based on respective item listing attributes that are independent of the contextual information and independent of the user attributes; and

further filtering the subset of pre-filtered item listings based on the quality scores; and

causing display of the one or more selected item listings.

2 . The system of claim 1 , wherein selecting the one or more item listings from the plurality of item listings further comprises:

determining that the user attributes are available; and

responsive to determining that the user attributes are available, further filtering the subset of pre-filtered item listings based on the user attributes.

3 . The system of claim 1 , wherein the respective item listing attributes comprise at least one of:

an item listing freshness associated with an item listing included in a collection of item listings, the item listing freshness indicating how recently the item listing was posted for sale;

an item listing quality associated with the item listing;

an image quality associated with the item listing; or

a past performance of the item listing.

4 . The system of claim 1 , wherein further filtering the subset of pre-filtered item listings based on the quality scores comprises:

comparing the quality scores for the respective item listings of the subset of pre-filtered item listings to a threshold; and

filtering out each item listing having a quality score less than the threshold.

5 . The system of claim 1 , wherein the contextual information comprises at least one of a browser type used by the client device, an operating system used by the client device, a device type of the client device, and a time of access of the website by the client device.

6 . The system of claim 1 , wherein filtering the plurality of item listings based on the contextual information comprises:

ranking the plurality of item listings based on the contextual information; and

removing a particular item listing from the plurality of item listings based on a rank of the particular item listing.

7 . The system of claim 1 , wherein the quality scores are further based on collection level attributes of the respective item listings of the subset of pre-filtered item listings, the collection level attributes including attributes associated with a respective collection of item listings to which a given item listing is grouped based on a common theme.

8 . The system of claim 1 , wherein the machine-learning model includes a random forest classifier generated while using the respective item listing attributes as decision nodes, and wherein the generating, using the machine-learning model, the quality scores for the respective item listings of the subset of pre-filtered item listings based on the respective item listing attributes that are independent of the contextual information and independent of the user attributes comprises:

generating relative ranks of the respective item listing attributes based on a depth of a respective decision node of the random forest classifier; and

determining the quality scores for the respective item listings of the subset of pre-filtered item listings based on the relative ranks of the respective item listing attributes.

9 . The system of claim 1 , wherein the machine-learning model includes a random forest classifier in an ensemble technique with a binary classification scheme, and wherein the generating, using the machine-learning model, the quality scores for the respective item listings of the subset of pre-filtered item listings based on the respective item listing attributes that are independent of the contextual information and independent of the user attributes comprises:

generating the quality scores based on a percentage of sub-classifiers in the random forest classifier predicting a first class of the binary classification scheme for the respective item listing attributes.

10 . A method for contextual filtering, comprising:

generating contextual information for a client device used to access a website hosting a plurality of item listings by analyzing data traffic between the client device and the website, the contextual information independent of user attributes that are inherent to a user;

selecting one or more item listings from the plurality of item listings by:

filtering the plurality of item listings based on the contextual information, the filtering producing a subset of pre-filtered item listings of the plurality of item listings;

generating, using a machine-learning model, quality scores for respective item listings of the subset of pre-filtered item listings based on respective item listing attributes that are independent of the contextual information and independent of the user attributes; and

further filtering the subset of pre-filtered item listings based on the quality scores; and

causing display of the one or more selected item listings.

11 . The method of claim 10 , wherein selecting the one or more item listings from the plurality of item listings further comprises:

determining that the user attributes are available; and

responsive to determining that the user attributes are available, further filtering the subset of pre-filtered item listings based on the user attributes.

12 . The method of claim 10 , wherein further filtering the subset of pre-filtered item listings based on the quality scores comprises:

comparing the quality scores for the respective item listings of the subset of pre-filtered item listings to a threshold; and

filtering out each item listing having a quality score less than the threshold.

13 . The method of claim 10 , wherein filtering the plurality of item listings based on the contextual information comprises removing a particular item listing from being selected as the one or more item listings using a random forest classifier and the contextual information.

14 . The method of claim 10 , wherein filtering the plurality of item listings based on the contextual information comprises:

ranking item listings of the plurality of item listings based on the contextual information; and

comparing ranks of the item listings of the plurality of item listings to a threshold value to determine whether to remove a particular item listing from being selected as the one or more item listings.

15 . The method of claim 10 , wherein the contextual information comprises one or more of a browser type used by the client device, an operating system used by the client device, a device type of the client device, and a time of access of the website by the client device.

16 . A non-transitory machine-readable medium storing instructions that, when executed by one or more hardware processors, cause the one or more hardware processors to perform operations comprising:

generating contextual information for a client device used to access a website hosting a plurality of item listings by analyzing data traffic between the client device and the website, the contextual information independent of user attributes that are inherent to a user;

selecting one or more item listings from the plurality of item listings by:

filtering the plurality of item listings based on the contextual information, the filtering producing a subset of pre-filtered item listings of the plurality of item listings;

generating, using a machine-learning model, quality scores for respective item listings of the subset of pre-filtered item listings based on respective item listing attributes that are independent of the contextual information and independent of the user attributes; and

further filtering the subset of pre-filtered item listings based on the quality scores; and

causing display of the one or more selected item listings.

17 . The non-transitory machine-readable medium of claim 16 , wherein selecting the one or more item listings from the plurality of item listings further comprises:

determining that the user attributes are available; and

responsive to determining that the user attributes are available, further filtering the subset of pre-filtered item listings based on the user attributes.

18 . The non-transitory machine-readable medium of claim 16 , wherein the respective item listing attributes comprise an item freshness indicating how recently a corresponding item listing was posted for sale.

19 . The non-transitory machine-readable medium of claim 16 , wherein the contextual information comprises at least one of a device type, a browser, or a time associated with the data traffic between the client device and the website over a network.

20 . The non-transitory machine-readable medium of claim 16 , wherein filtering the plurality of item listings based on the contextual information further comprises:

tagging item listings of the plurality of item listings to indicate whether they are for user engagement or purchase; and

ranking the item listings based on a number of tags associated with a respective item listing that matches the contextual information.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 2, 2023
From: KHATRI, CHANDRA; LUAN, STEVEN HUI; TANAKA, MICHAEL; BOINAPALLI, PRAVEEN K.
To: EBAY INC.
Reel/Frame 065098/0573 →
Continuity (3)
Continuation 14586462 · Dec 30, 2014
Provisional Application 62043064 · Aug 28, 2014
Related Publication 20240028658A1 · Jan 25, 2024
References Cited (84)
US 7107254B1 · Dumais et al. · 2006 [cited by applicant]
US 7856444B2 · Silverbrook et al. · 2010 [cited by applicant]
US 8352299B1 · Seshadri · 2013 [cited by examiner]
US 8352465B1 · Jing et al. · 2013 [cited by applicant]
US 8831987B2 · Knapp et al. · 2014 [cited by applicant]
US 9111289B2 · Liu · 2015 [cited by examiner]
US 11809501B2 · Khatri et al. · 2023 [cited by applicant]
US 20070198485A1 · Ramer · 2007 [cited by examiner]
US 20080209339A1 · Macadaan · 2008 [cited by examiner]
US 20090165041A1 · Penberthy · 2009 [cited by examiner]
US 20100082627A1 · Lai et al. · 2010 [cited by applicant]
US 20110264663A1 · Verkasalo · 2011 [cited by applicant]
US 20120059819A1 · Wheeler et al. · 2012 [cited by applicant]
US 20120078873A1 · Ferrucci · 2012 [cited by examiner]
US 20120128239A1 · Goswami et al. · 2012 [cited by applicant]
US 20120158516A1 · Wooten, III · 2012 [cited by examiner]
US 20120289147A1 · Raleigh et al. · 2012 [cited by applicant]
US 20120323704A1 · Steelberg et al. · 2012 [cited by applicant]
US 20130073335A1 · Tang · 2013 [cited by examiner]
US 20130151383A1 · Gancarz et al. · 2013 [cited by applicant]
US 20130225439A1 · Princen et al. · 2013 [cited by applicant]
US 20130311408A1 · Bagga · 2013 [cited by examiner]
US 20130346234A1 · Hendrick et al. · 2013 [cited by applicant]
US 20140040245A1 · Rubinstein et al. · 2014 [cited by applicant]
US 20140067596A1 · McGovern · 2014 [cited by examiner]
US 20140079297A1 · Tadayon et al. · 2014 [cited by applicant]
US 20140106785A1 · Hawkins et al. · 2014 [cited by applicant]
US 20140108427A1 · Spiegel · 2014 [cited by applicant]
US 20140181193A1 · Mukund et al. · 2014 [cited by applicant]
US 20140229293A1 · Huang · 2014 [cited by examiner]
US 20140279196A1 · Wilson et al. · 2014 [cited by applicant]
US 20140321761A1 · Wang et al. · 2014 [cited by applicant]
US 20150142566A1 · Zhang et al. · 2015 [cited by applicant]
US 20160063065A1 · Khatri et al. · 2016 [cited by applicant]
US 20160078035A1 · Ball · 2016 [cited by examiner]
US 20160344758A1 · Cohen · 2016 [cited by examiner]
US 20200311790A1 · Keren · 2020 [cited by examiner]
US 20210337460A1 · Breaux, III · 2021 [cited by examiner]
“Explore Collections on eBay”, eBay Inc., [Online]. Retrieved from the Internet: <URL:http://www.ebay.com/cln>, 10 pages. [cited by applicant]
U.S. Appl. No. 14/586,462, , “Advisory Action Received for U.S. Appl. No. 14/586,462, mailed on May 27, 2020”, May 27, 2020, 3 pages. [cited by applicant]
U.S. Appl. No. 14/586,462, , “Advisory action received for U.S. Appl. No. 14/586,462 , mailed on Apr. 11, 2019”, Apr. 11, 2019, 3 pages. [cited by applicant]
U.S. Appl. No. 14/586,462, , “Advisory Action received for U.S. Appl. No. 14/586,462 mailed on Aug. 15, 2022”, Aug. 15, 2022, 3 pages. [cited by applicant]
U.S. Appl. No. 14/586,462, , “Applicant Initiated Interview Summary Received for U.S. Appl. No. 14/586,462, mailed on Jan. 21, 2020”, Jan. 21, 2020, 3 pages. [cited by applicant]
U.S. Appl. No. 14/586,462, , “Applicant Initiated Interview Summary Received for U.S. Appl. No. 14/586,462, mailed on May 18, 2020”, May 18, 2020, 3 pages. [cited by applicant]
U.S. Appl. No. 14/586,462, , “Applicant Initiated Interview Summary received for U.S. Appl. No. 14/586,462, mailed on Feb. 19, 2019”, Feb. 19, 2019, 3 pages. [cited by applicant]
U.S. Appl. No. 14/586,462, , “Applicant-Initiated Interview Summary received for U.S. Appl. No. 14/586,462, mailed on Sep. 11, 2018”, Sep. 11, 2019, 3 pages. [cited by applicant]
U.S. Appl. No. 14/586,462, , “Final Office Action received for U.S. Appl. No. 14/586,462, mailed on Apr. 13, 2021”, Apr. 13, 2021, 20 pages. [cited by applicant]
U.S. Appl. No. 14/586,462, , “Final Office Action received for U.S. Appl. No. 14/586,462, mailed on Aug. 4, 2017”, Aug. 4, 2017, 27 pages. [cited by applicant]
U.S. Appl. No. 14/586,462, , “Final Office Action received for U.S. Appl. No. 14/586,462, mailed on Jan. 25, 2019”, Jan. 25, 2019, 14 pages. [cited by applicant]
U.S. Appl. No. 14/586,462, , “Final Office Action Received for U.S. Appl. No. 14/586,462, mailed on Mar. 20, 2020”, Mar. 20, 2020, 16 pages. [cited by applicant]
U.S. Appl. No. 14/586,462, , “Final Office Action Received for U.S. Appl. No. 14/586,462, mailed on Mar. 24, 2023”, Mar. 24, 2023, 20 pages. [cited by applicant]
U.S. Appl. No. 14/586,462, , “Final Office Action Received for U.S. Appl. No. 14/586,462, mailed on May 20, 2022”, May 20, 2022, 22 pages. [cited by applicant]
U.S. Appl. No. 14/586,462, , “Non Final Office Action Received for U.S. Appl. No. 14/586,462, mailed on Oct. 30, 2020”, Oct. 30, 2020, 17 pages. [cited by applicant]
U.S. Appl. No. 14/586,462, , “Non-Final Office Action received for U.S. Appl. No. 14/586,462, mailed on Feb. 10, 2017”, Feb. 10, 2017, 39 pages. [cited by applicant]
U.S. Appl. No. 14/586,462, , “Non-Final Office Action received for U.S. Appl. No. 14/586,462, mailed on Jul. 2, 2018”, Jul. 2, 2018, 30 pages. [cited by applicant]
U.S. Appl. No. 14/586,462, , “Non-Final Office Action Received for U.S. Appl. No. 14/586,462, mailed on Oct. 5, 2022”, Oct. 5, 2022, 20 pages. [cited by applicant]
U.S. Appl. No. 14/586,462, , “Notice of Allowance”, U.S. Appl. No. 14/586,462, Aug. 9, 2023, 18 pages. [cited by applicant]
Adomavicius, et al., “Context-Aware Recommender Systems”, Recommender Systems Handbook, 2011, 217-253. [cited by applicant]
Adomavicius, et al., “Context-Aware Recommender Systems”, Artificial Intelligence Magazine, 32(3), 2011, 67-80. [cited by applicant]
Adomavicius, et al., “Incorporating Contextual Information in Recommender Systems Using a Multidimensional Approach”, ACM Transactions on Information Systems, 23(1), Jan. 2005, 103-145. [cited by applicant]
Adomavicius, Gediminas et al., “Toward the Next Generation of Recommender Systems: A Survey of the State-of-the-Art and Possible Extensions”, IEEE Transactions on Knowledge and Data Engineering, vol. 17, No. 6, Jun. 200… [cited by applicant]
Anand, et al., “Contextual Recommendation”, From Web to Social Web: Discovering and Deploying User and Content Profiles, Lecture Notes in Computer Science, vol. 4737, 2007, 142-160. [cited by applicant]
Bal Trunas, et al., “Context relevance assessment and exploitation in mobile recommender systems”, Personal and Ubiquitous Computing, 16(5), Jun. 2012, 507-526. [cited by applicant]
Bazire, et al., “Understanding Context Before Using It”, Modeling and Using Context, Lecture Notes in Computer Science, 3554, 2005, 29-40. [cited by applicant]
Cao, et al., “Learning to Rank: From Pairwise Approach to Listwise Approach”, Proceedings of the 24th international conference on Machine learning, Jun. 2007, pp. 129-136. [cited by applicant]
Donovan, et al., “Trust in Recommender Systems”, Proceedings of the 10th international conference on Intelligent user interfaces, Jan. 2005, pp. 167-174. [cited by applicant]
Herlocker, et al., “Evaluating collaborative filtering recommender systems”, ACM Transactions on Information Systems, 22(1), 2004, 5-53. [cited by applicant]
Jannach, et al., “Recommender Systems: An Introduction”, Retrieved from the Internet : <https://pdfs.semanticscholar.org/6abf/b1fbb04f1570e646cc8f9efeaad7d98a7495.pdf>, 2010, 16 pages. [cited by applicant]
Karatzoglou, et al., “Multiverse Recommendation: N-Dimensional Tensor Factorization for Context-Aware Collaborative filtering”, RecSys '10 Proceedings of the fourth ACM conference on Recommender systems, 2010, 79-86. [cited by applicant]
Karatzoglou, , “Recommender Systems”, ESSIR 2013, Sep. 6, 2013, 145 pages. [cited by applicant]
Liu, N et al., “Social Temporal Collaborative Ranking for Context Aware Movie Recommendations”, ACM Transactions on Intelligent Systems and Technology (TIST), 4(1), 2013, 15:1-15:26. [cited by applicant]
Panniello, et al., “Experimental Comparison of Pre- Versus Post Filtering Approaches in Context-Aware Recommender Systems”, Proceedings of the 2009 ACM Recommender Systems Conference, 2009, 265-268. [cited by applicant]
Pazzani, et al., “Content-Based Recommendation Systems”, The Adaptive Web, Lecture Notes in Computer Science, vol. 4321, 2007, 325-341. [cited by applicant]
Rendle, Steffen et al., “Fast Context-aware Recommendations with Factorization Machines”, SIGIR 11 Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval, Jul. 24… [cited by applicant]
Ricci, et al., “Recommender Systems Handbook”, Retrieved from the Internet URL : <https://rd.springer.com/book/10.1007/978-0-387-85820-3>, May 2010, 29 pages. [cited by applicant]
Salakhutdinov, et al., “Restricted Boltzmann Machines for Collaborative Filtering”, Proceedings of the 24th international conference on Machine learning, Jun. 2007, pp. 791-798. [cited by applicant]
Sarwar, Badrul et al., “Item-Based Collaborative Filtering Recommendation Algorithms”, In Proceedings of WWW10, Available at <http://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=53CDC5DC7FF8F88183770CD0C72DD017?doi… [cited by applicant]
Schafer, et al., “Recommender Systems In E-Commerce”, Proceedings of the 1st ACM conference on Electronic commerce, Nov. 1999, pp. 158-166. [cited by applicant]
Shi, et al., “Ranking and Context-awareness in Recommender Systems”, PHD Thesis, Institutional Repository, TU Delft. Entry 1 of 3, 2013, 177 pages. [cited by applicant]
Shi, , “Ranking and Context-awareness in Recommender Systems”, PHD Thesis, Institutional Repository, TU Delft. Entry 2 of 3., 2013, 177 pages. [cited by applicant]
Shi, , “Ranking and Context-awareness in Recommender Systems”, PHD Thesis, Institutional Repository, TU Delft. Entry 3 of 3., 2013, 177 pages. [cited by applicant]
Sinha, et al., “Beyond Algorithms: An HCI Perspective on Recommender Systems”, Retrieved from the Internet URL: <http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.23.9764>, 2001, 11 pages. [cited by applicant]
Tan, Pang-Ning et al., “Introduction to Data Mining”, Mining, (First Edition). Addison-Wesley Longman Publishing Co., Inc., Boston, MA, USA. (2005), 2005, 169 pages. [cited by applicant]
Verbert, et al., “Context-Aware Recommender Systems for Learning: A Survey and Future Challenges”, Journal of Universal Computer Science, 16(16), 2010, 18 pages. [cited by applicant]