公开(公告)号：US20240152955A1

公开(公告)日：2024-05-09

申请号：US17976089

申请日：2022-10-28

Applicant: Microsoft Technology Licensing, LLC

Inventor： Jialiang Mao ,  Rina Siller Friedberg ,  Karthik Rajkumar ,  Qian Yao ,  Min Liu ,  YinYin Yu

IPC: G06Q30/02 ,  G06F16/957

CPC classification number: G06Q30/0243 ,  G06F16/9577 ,  G06Q30/0277

Abstract: Methods, systems, and computer programs are presented for eliminating bias while training an ML model using training data that includes past experimental data. One method includes accessing experiment results, for A/B testing of a first model, that comprise information regarding engagement with a first set of items presented to users, each item being presented within an ordered list of results. A position bias is calculated for positions within the ordered list of results where the items were presented. A machine-learning program is trained to obtain a second model using a training set comprising values for features that include the calculated position bias. The method includes detecting a second set of items to be ranked for presentation to a first user, and calculates, using the second model, a relevance score for the second set of items, which are ranked based on the respective relevance score and presented on a display.

公开(公告)号：US12265987B2

公开(公告)日：2025-04-01

申请号：US17976089

申请日：2022-10-28

Applicant: Microsoft Technology Licensing, LLC

Inventor： Jialiang Mao ,  Rina Siller Friedberg ,  Karthik Rajkumar ,  Qian Yao ,  Min Liu ,  YinYin Yu

IPC: G06Q30/0241 ,  G06Q30/0242

Abstract: Methods, systems, and computer programs are presented for eliminating bias while training an ML model using training data that includes past experimental data. One method includes accessing experiment results, for A/B testing of a first model, that comprise information regarding engagement with a first set of items presented to users, each item being presented within an ordered list of results. A position bias is calculated for positions within the ordered list of results where the items were presented. A machine-learning program is trained to obtain a second model using a training set comprising values for features that include the calculated position bias. The method includes detecting a second set of items to be ranked for presentation to a first user, and calculates, using the second model, a relevance score for the second set of items, which are ranked based on the respective relevance score and presented on a display.