Abstract: Techniques are provided for using machine learning techniques to identify predictive features and predictive values for each feature. In one technique, a model is trained based on training data that comprises training instances, each of which corresponds to multiple usage-based features of an online service by a user. For each usage-based feature in a subset of the usage-based features, the model is used to generate a dependency graph, a histogram is generated, and an optimized value is selected based on the dependency graph and the histogram. A user of the online service is identified, along with a usage value that indicates a level of usage, by the user, of a usage-based feature. A comparison between the usage value and an optimized value of the usage-based feature is performed. Based on the comparison, it is determined whether to present data about that usage-based feature to the user.

Abstract: Techniques are provided for using machine learning techniques to identify predictive features and predictive values for each feature. In one technique, a model is trained based on training data that comprises training instances, each of which corresponds to multiple usage-based features of an online service by a user. For each usage-based feature in a subset of the usage-based features, the model is used to generate a dependency graph, a histogram is generated, and an optimized value is selected based on the dependency graph and the histogram. A user of the online service is identified, along with a usage value that indicates a level of usage, by the user, of a usage-based feature. A comparison between the usage value and an optimized value of the usage-based feature is performed. Based on the comparison, it is determined whether to present data about that usage-based feature to the user.

Abstract: The disclosed embodiments provide a system for performing unified propensity modeling across product versions. During operation, the system determines features and labels related to converting to multiple versions of a product by a first set of members, wherein the features and the labels span a unified timeframe and adhere to a unified data logic. Next, the system inputs the features and the labels as training data for one or more machine learning models. The system then applies the machine learning model(s) to additional features for a second set of members to produce scores representing likelihoods of the second set of members converting to the multiple versions of the product. Finally, the system generates, based on the scores, output for targeting the second set of members with the product.

Abstract: The disclosed embodiments provide a system for recommending related services. During operation, the system determines, using a set of data sources, matching pairs of related services offered through an online system, wherein the set of data sources includes historical interactions with recommended services and historical requests for proposal (RFPs). Next, the system ranks the matching pairs based on the set of data sources and popularities of the matching pairs. The system then identifies, based on the ranking, a set of related services for a service offered through the online system. Finally, the system outputs the set of related services as recommended services to a user of the online system.

Abstract: Techniques for searching for generating and using an online activity index for users of an online service are disclosed herein. In some example embodiments, for each one of a plurality of dimensions of online activity for an online service, the system determines a corresponding value for each one of a set of one or more activities corresponding to the dimension for a user of the online service, with the value representing a level of engagement by the user in the corresponding activity via the online service. The system generates a corresponding activity index for each one of the dimensions based on the corresponding value for each one of the set of one or more activities corresponding to the dimension. The system generates content based on the corresponding activity index of at least one of the dimensions, and causes the content to be displayed on a device associated with the user.

Abstract: Techniques for searching for generating and using an online activity index for users of an online service are disclosed herein. In some example embodiments, for each one of a plurality of dimensions of online activity for an online service, the system determines a corresponding value for each one of a set of one or more activities corresponding to the dimension for a user of the online service, with the value representing a level of engagement by the user in the corresponding activity via the online service. The system generates a corresponding activity index for each one of the dimensions based on the corresponding value for each one of the set of one or more activities corresponding to the dimension. The system generates content based on the corresponding activity index of at least one of the dimensions, and causes the content to be displayed on a device associated with the user.