Abstract: A compound having a structure as shown in general formula (I), a deuterated compound, a stereoisomer, or a pharmaceutically acceptable salt thereof, a pharmaceutical composition comprising same, and use thereof. The compound has a good PIM kinase inhibitory effect, is a novel and ideal PIM inhibitor having high activity and low toxicity, and can be used for treating and/or preventing hematoma such as acute myeloid leukemia, bone marrow fibrosis and chronic lymphocytic leukemia, solid tumors such as gastric cancer and prostate cancer, and other diseases.

Abstract: Computer-implemented techniques for ex post facto accounting for interference from network effects in a one-to-one messaging experiment in an online service. With the techniques, is not necessary to identify isolated, non-interacting communities of users pre-experiment. Instead, unconventionally, a total lift for the treatment feature may be computed post-experiment based on the observed actual messages sent during the experiment by users in the treatment and control groups. Techniques for post-experiment computation of an experiment-specific message response rate, based on observed messages sent, and post-experiment computation of an instant lift, based on overserved message sent, are also disclosed.

Abstract: The disclosed embodiments provide a system for evaluating a performance of a mobile application. During operation, the system obtains a first set of data associated with adopters of a new version of a mobile application in a partial rollout of the new version and a second set of data associated with non-adopters of the new version in the partial rollout. Next, the system applies a statistical model to the first and second sets of data to select a subset of the non-adopters as potential adopters of the new version. The system then reduces a bias in a quasi-experimental design associated with the mobile application by using the first set of data and a third set of data associated with the potential adopters to estimate an average treatment effect (ATE) between the new version and an older version of the mobile application.

Abstract: The disclosed embodiments provide a system for evaluating a performance of a mobile application. During operation, the system obtains, for a statistical model used in a quasi-experimental design, a first predicted outcome produced from a first set of data that is collected from two substantially identical versions of a mobile application. Next, the system uses the first predicted outcome to assess a bias of the statistical model. The system then improves an accuracy of the statistical model by using the assessed bias to normalize a second predicted outcome of the statistical model.

Abstract: A machine may be configured to generate A/B test reports on demand. For example, the machine causes a display of a user interface for receiving a request of a customized report of result data of an A/B test. The machine receives, via the user interface, an identifier of the A/B test, a specification of a metric associated with the result data, a specification of a dimension of the metric, a specification of a location of the result data, and a request to generate the customized report. The machine generates the metric based on the identifier of the A/B test, the specification of the metric, and the result data. The machine generates the customized report pertaining to the dimension of the metric based on the generated metric and the specification of the dimension of the metric. The machine causes a display of the customized report in the user interface.

Abstract: The disclosed embodiments provide a system for evaluating a performance of a mobile application. During operation, the system obtains, for a statistical model used in a quasi-experimental design, a first predicted outcome produced from a first set of data that is collected from two substantially identical versions of a mobile application. Next, the system uses the first predicted outcome to assess a bias of the statistical model. The system then improves an accuracy of the statistical model by using the assessed bias to normalize a second predicted outcome of the statistical model.

Abstract: The disclosed embodiments provide a system for evaluating a performance of a mobile application. During operation, the system obtains a first set of data associated with adopters of a new version of a mobile application in a partial rollout of the new version and a second set of data associated with non-adopters of the new version in the partial rollout. Next, the system applies a statistical model to the first and second sets of data to select a subset of the non-adopters as potential adopters of the new version. The system then reduces a bias in a quasi-experimental design associated with the mobile application by using the first set of data and a third set of data associated with the potential adopters to estimate an average treatment effect (ATE) between the new version and an older version of the mobile application.

Abstract: Techniques for conducting A/B experimentation of online content are described. According to various embodiments, a user specification of a metric associated with operation of an online social networking service is received. A set of one or more A/B experiments of online content is then identified, each A/B experiment being targeted at a segment of members of the online social networking service. Thereafter, each of the A/B experiments is ranked, based on an inferred impact on the value of the metric in response to application of a treatment variant of each A/B experiment to the online social networking service. A list of one or more of the ranked A/B experiments is then displayed, via a user interface displayed on a client device.

Abstract: Techniques for conducting A/B experimentation of online content are described. According to various embodiments, a site-wide impact value for an A/B experiment that is associated with a metric is calculated, the site-wide impact value indicating a predicted percentage change in the value of a metric responsive to application of a treatment variant to an entire portion of a targeted segment of members, in comparison to application of a control variant to an entire portion of the targeted segment of members.

Abstract: Techniques for conducting A/B experimentation of online content are described. According to various embodiments, a user specification of targeting criteria defining a targeted segment of members of an online social networking service for an A/B experiment is received. A set of members of the online social networking service satisfying the user-specified targeting criteria is then identified. Thereafter, a user specification of allocation criteria defining one or more variants of an A/B experiment and one or more corresponding allocation percentages is received. A subset of the set of members (corresponding to the user-specific allocation percentage associated with the respective user-specified variant) is then assigned to each of the user-specified variants. Further, at least one data record associated with each of the variants is recorded in a database, each data record indicating the subset of the set of members assigned to the respective variant.

Abstract: Techniques for conducting A/B experimentation of online content are described. According to various embodiments, it is determined that a member of an online social networking service is accessing electronic content that is associated with an A/B experiment, the member being associated with a given member ID. The given member ID and a request for a correct variant of the A/B experiment for display for the given member ID is transmitted, from a service associated with the online content, to an A/B experiment server. The correct variant of the A/B experiment for display for the given member ID is accessed from a database, and information regarding the correct variant of the A/B experiment is transmitted to the service associated with the online content. Thereafter, the correct variant of the A/B experiment in conjunction with the online content is displayed, to a client device associated with the member.