-
公开(公告)号：US20220067122A1
公开(公告)日：2022-03-03
申请号：US17003218
申请日：2020-08-26
Applicant: COUPANG CORP.
Abstract: A computer-implemented systems and methods for capping outliers during an experiment test is disclosed. The computer implemented system comprises a memory storing instructions and at least one or more processors. The at least one or more processors may be configured to configured to execute the instructions to determine at least two groups of users comprising a plurality of users; obtain metric data related to each of the plurality of users; calculate a first value and a second value based on the metric data; identify an occurrence of a trigger event, using the metric data, the first value, and the second value; distribute the metric data into capped data and uncapped data and determine a threshold for the capped data; calculate a third value for the capped data and the uncapped data; determine if the capped data threshold has changed based on the third value; and implement at least one capping percentile value upon occurrence of the trigger event.
-
公开(公告)号：US20220067754A1
公开(公告)日：2022-03-03
申请号：US17005232
申请日：2020-08-27
Applicant: COUPANG CORP.
Inventor： Xiaowei GONG , Beibei YE , Jun YE , Chul SEO
IPC: G06Q30/02 , G06F16/955 , G06F16/958
Abstract: Embodiments of the present disclosure include computer-implemented systems and methods for predicting a minimum detectable effect. The system may include at least one processor configured to execute instructions to perform steps. The steps may include sending a first webpage to a first user device and a second webpage to a second user device. The second webpage may include at least one characteristic different than the first website. The steps may include collecting user interaction data from the first and second user devices and determining a current minimum detectable effect of a user experience. The steps may include retrieving a set of historic minimum detectable effect values associated with an earlier period of time and determining a percentile rank of the current minimum detectable effect based on the retrieved set of historic minimum detectable effect values. The steps may include predicting a first and second future value of the minimum detectable effect of the user experience and aggregating the first and second future values. The aggregated first and second future value may be compared with a threshold to determine whether or not to stop an experiment and implement a change on a website.
-
Search Results
2
records
(took 0.009 seconds)
