Real time prediction of telco customer churn using Watson Machine Learning from Cognos dashboard
Invoke machine learning models dynamically and create a real-time dashboard
Cognos is a leader in business intelligence and analytics, with thousands of clients driving insights every day. IBM Cognos Analytics builds on this legacy of success by adding self-service data preparation, visualization, and dash boarding capabilities. Redesigned from the ground up with a modern, intuitive user interface and cognitive capabilities borrowed from the world-famous Watson supercomputer, IBM Cognos Analytics delivers a personal approach to analytics by empowering business users to solve individual or workgroup challenges on their own – while providing IT with a proven solution that can be easily scaled as business needs grow.
Cognos dashboard traditionally displays content from descriptive analytics. As an adoption of predictive analytics in the surge, it would make more sense to bring in both descriptive and predictive content to the same plane(page/dashboard). Things like invoking an ML model or scoring real-time, through Watson Machine learning API, you will be able to access a model across a different platform, be it Spark, R, Python or IBM’s Proprietary Library SPSS.
The latest version (11.0.x) of Cognos comes with a custom control feature, and by leveraging Cognos Analytics extensions we can extend the traditional capability of Cognos and extend it to predictive space using Watson ML API.
This code pattern demonstrates the capability to create a real-time dashboard where you can pass the inputs through a custom control built widget, which internally invokes the model through REST API, gets the output of the model, and displays it on the Cognos dashboard.