Invention Grant
- Patent Title: Deep learning approach to mitigate the cold-start problem in textual items recommendations
-
Application No.: US17531530Application Date: 2021-11-19
-
Publication No.: US11687612B2Publication Date: 2023-06-27
- Inventor: Elik Sror , Oren Sar Shalom , Rami Cohen
- Applicant: Intuit Inc.
- Applicant Address: US CA Mountain View
- Assignee: INTUIT INC
- Current Assignee: INTUIT INC
- Current Assignee Address: US CA Mountain View
- Agency: Ferguson Braswell Fraser Kubasta PC
- Main IPC: G06F16/957
- IPC: G06F16/957 ; G06F17/16 ; G06N3/08 ; G06F12/06 ; G06F12/02 ; G06F12/0895
Abstract:
A method for mitigating cold starts in recommendations includes receiving a request that identifies a requested page and identifying a content vector of the requested page. The content vector is generated based on providing text of the requested page to a neural network text encoder. The method further includes selecting, based on the content vector, a link to a cold start page that does not satisfy a threshold level of interaction data. The selected link is ranked above a second link to a warm page that does satisfy the threshold level of the interaction data. The method further includes presenting the requested page with the selected link.
Public/Granted literature
- US20220075840A1 DEEP LEARNING APPROACH TO MITIGATE THE COLD-START PROBLEM IN TEXTUAL ITEMS RECOMMENDATIONS Public/Granted day:2022-03-10
Information query
