Abstract: Store a subscription dataset for each tenant of a multi-tenant system, each of the subscription datasets having a common data format native to the system, the subscription datasets including billing data and not behavioral data. Determine primary features from a particular subscription dataset. Derive secondary features from the primary features. Generate a churn prediction model based on the primary features and the secondary features. Obtain a second subscription dataset, the second subscription dataset comprising billing data that is more recent than the particular subscription dataset. Identify, using the particular churn prediction model and the second subscription dataset, one or more subscribers as a churn-risk. Report the one or more subscribers identified as a churn-risk.

Abstract: Systems and methods for determining video infrastructure delivery problems using machine learning are presented. In an aspect, a system includes a reception component configured to receive information regarding videos streamed by the system to devices, wherein the information identifies video playback events at the devices and rebuffer events respectively associated with the video playback events. The system further includes a quality component configured to identify features related to quality of the playback events at the devices based on the information, and an analysis component configured to determine probabilities of occurrence of the re-buffer events based on different combinations of the features, and determine weighted values for each of the features that reflect their contribution to the probabilities of occurrence of the re-buffer events based on the different combinations of the features.

Abstract: Systems and methods for determining video infrastructure delivery problems using machine learning are presented. In an aspect, a system includes a reception component configured to receive information regarding videos streamed by the system to devices, wherein the information identifies video playback events at the devices and re-buffer events respectively associated with the video playback events. The system further includes a quality component configured to identify features related to quality of the playback events at the devices based on the information, and an analysis component configured to determine probabilities of occurrence of the re-buffer events based on different combinations of the features, and determine weighted values for each of the features that reflect their contribution to the probabilities of occurrence of the re-buffer events based on the different combinations of the features.

Abstract: A partially adhered label includes a carrier web and a substrate carried by the web. The substrate has a smaller area than an area of the carrier web. The substrate defines an outer indicia carrying surface and an inner surface. The inner surface is partially adhered to the carrier web by an adhesive. The inner surface of the substrate defines an active adhesive area and a central non-adhesive area. The adhesive area is by a border extending around a periphery of the non-adhesive area.

Abstract: A merchant who operates a physical store is able to communicate a message to a customer who is carrying one or more items for purchase. While the customer is moving through the store, the merchant uses electronic means to gather data identifying at least one of the items carried by the customer. A computer-implemented program applied to the data analyzes the data and identifies at least one alternative item that the customer might want to buy. The program then prepares a message about the alternative item and delivers the message to the customer while the customer is still in the store.

Abstract: A merchant in a virtual retail store uses a computer-implemented technique to communicate a message to a customer who has selected multiple items for purchase. On establishing an online shopping session with the customer, the merchant's system maintains a list of the items that the customer has selected for purchase during the session. The system provides information about these items to an analytical program, which in turn identifies at least one alternative item that the customer might want to buy. The system then prepares a message that includes information about the alternative item and, before the online shopping session has ended, delivers the message to the customer.