Amazon Technologies, Inc.

Siwei Jia

Rui Chen

Serguei B Stepaniants

Tian Chen

Feng Zhu

Mengyun Lv

Tae Yeon Kim

Jeff Brooks

Chunlei Zhang

Mia Kilborn

Hansu Gu

Zhen Liu

Chuanhai Zhang

Methods, systems, and computer-readable media for user engagement modeling for engagement optimization are disclosed. Based (at least in part) on one or more user engagement models, a user engagement modeling system determines an uplift score for a user of an Internet-accessible service. The uplift score comprises an estimated effect on one or more user engagement metrics of an incentive to interact with the service. The uplift score is determined based (at least in part) on values of the user engagement metric(s) for the user in a treatment group and values of the metric(s) for the user in a control group, in view of propensity score to be in either group. The treatment group is offered the incentive, and the control group is not offered the incentive. The system determines that the user is or is not offered the incentive based at least in part on the uplift score.

User engagement modeling for engagement optimization

Technologies are disclosed for determining validity of data obtained from an A/B experiment, where the experiment evaluates the desirability of a potential change at a website. The experiment is run for a period of time and based upon an expected allocation of users into the A group (control group) and the B group (e.g., treatment group), along with an actual number of users directed into the two groups, it is determined if a minimal detectable error of allocation has been exceeded and, if it has, the data is deemed to be invalid. If not, the data is deemed to be valid.

Determining the validity of data collected by experiments performed at a network accessible site

Technologies are disclosed for determining a runtime length for an A/B experiment, where the experiment evaluates the desirability of a potential change at a website. The experiment is run for an initial period of time and based upon initial data from the initial period of time, an equation is iteratively solved until a minimal amount of time is determined that that indicates when a statistically significant change will be observed in the data. The experiment is then run for the minimal amount of time.

Determining a run time for experiments performed at a network accessible site

Growing community of inventors

Bellevue, WA, United States of America

Siwei Jia