Sap Se

Sap Ag

Karsten Ploesser

Franz Weber

Alexander Dreiling

Patrick Schmidt

Daniel Ricketts

Shane Bracher

Mark Daniel Holmes

Liam Mischewski

Joerg Mann

Glenn Neuber

Asadul Islam

Hoyoung Jeung

Piyush Chandra

Xiaohua Cao

Keith Gill

Farah Jama

Prashant Gautam

Implementations are directed to identifying potential churn of a user of one or more computer-implemented systems provided by an enterprise. In some examples, actions include identifying potential churn of providing a plurality of event profiles based on historical data, each event profile being representative of interactions of users with the enterprise and corresponding to churn of the users, at least one event profile being representative of an interaction of users with the one or more computer-implemented services, providing a pulse of the user at least partially based on historical data associated with the user, and one or more event profiles of the plurality of event profiles, and determining that the user is at-risk of churn based on the pulse of the user and a risk index value, and in response, displaying an indication that the user is at-risk of churn in a graphical user interface.

Real-time system to identify and analyze behavioral patterns to predict churn risk and increase retention

Embodiments leverage capabilities of an in-memory database to manage measurement and modeling of Operational Leading Indicators (OLIs). An OLI template may comprise four model components: ratio calculation; factor calculation; predictive modeling; and cost estimation. Each model component is motivated and explained in terms of information sources, and analytical or statistical modelling tasks used in its definition. Embodiments combine analytical and statistical modelling utilizing in-memory computing, to process large amounts of unmodified source data, calculate cost measures rapidly without preaggregation, and/or run linear regression models on the same data set and in the same memory space without a need for separate hardware. An engine in communication with the in-memory database that comprises a large volume of available data, is configured to receive values for OLI factors as inputs. In response, the engine is configured to process these inputs according to the modeling template to provide corresponding cost measures as outputs.

Operational leading indicator (OLI) management using in-memory database

Methods, systems, and computer-readable storage media for automatically checking and acting on one or more claims. Implementations include actions of receiving claim information associated with one or more claims, wherein each of the one or more claims includes a factual claim, processing the claim information based on a domain vocabulary to identify at least one of one or more keywords and one or more categories, for each claim of the one or more claims: identifying one or more facts relevant to the claim, and determining an accuracy of the claim based on the one or more facts generating a confidence score reflecting an overall confidence in the one or more claims based on respective accuracies, and transmitting at least one of the one or more claims and the confidence score for display in a graphical user interface (GUI).

Fact checker engine

A system for monitoring processes of a distributed business application an integration builder tool. The integration builder tool includes a condition editor having a user interface providing an editing area on a display in which to receive a text-based expression of one or more conditions of a business application process. The editing area further includes an operator palette providing a plurality of operators for use in the text based expression of each of the one or more conditions, and a toolbar providing one or more editing tools for editing the text-based expressions.

Condition editor for business process management and business activity monitoring

A plurality of constraints are identified for a model of a software deployment in an integrated development environment. Each of the constraints are associated with one of a plurality of analysis levels. It is determined for each analysis level whether the corresponding associated constraints are met so that an identification indicating the same may be provided. Related techniques, apparatus, systems, and articles are described.

Integrated model checking and issue resolution framework

Growing community of inventors

Bulimba, Germany

Karsten Ploesser