Predict, manage, and monitor the call drops of cell towers using IBM Cloud Pak for Data

Summary

This code pattern is part of a series that explores telecom call-drop predictions using IBM Cloud Pak® for Data, data virtualization, IBM Watson® OpenScale™, and Cognos® Analytics.

Level Topic Type
201 Query across distributed data sources as one: Data virtualization for data analytics Tutorial
201 Monitor your machine learning models using Watson OpenScale in IBM Cloud Pak for Data Pattern
301 Build dashboards in Cognos Analytics on IBM Cloud Pak for Data Tutorial
301 Predict, manage, and monitor the call drops of cell towers using IBM Cloud Pak for Data Pattern

Description

This code pattern will show you how to create a model to predict call drops. With the help of an interactive dashboard, we’ll use a time series model to better understand call drops.

In this code pattern, you’ll learn how to:

  • Use data virtualization
  • Create connections from databases hosted on multiple cloud (AWS, Azure, or IBM Cloud) or on-premises environments
  • Create views from joins and publish data to your current project
  • Store custom models using open source technology on Watson Machine Learning
  • Deploy a model and connect the model deployment to Watson OpenScale on IBM Cloud Pak for Data and IBM Cloud
  • Set up model fairness and model quality monitors in Watson OpenScale on IBM Cloud Pak for Data and on IBM Cloud using a Python notebook
  • Create a project and set up a Python notebook on IBM Cloud Pak for Data

Flow

Predict and manage calls flow diagram

  1. AI models virtualize and join data stored across various sources, like AWS Cloud and IBM Cloud, as needed.
  2. Joined data is stored in the internal database of IBM Cloud Pak for Data and assigned to the current working project.
  3. Create machine learning models using Jupyter Notebooks to predict call drops per tower and a time-series model that projects a call-drop percentage based on real-time conditions.
  4. Model trained and stored in Watson Machine Learning, which is also connected to Watson OpenScale.
  5. Visualize and analyze insights from the trained models and the data using Cognos Analytics dashboards.
  6. Configure fairness, quality, and explainability monitors for each tower’s model.

Instructions

Find the detailed steps for this pattern in the README. The steps show you how to:

  1. Clone the repository.
  2. Obtain your data from data virtualization.
  3. Create a new project in IBM Cloud Pak for Data.
  4. Upload the data set to IBM Cloud Pak for Data.
  5. Import the notebook to IBM Cloud Pak for Data.
  6. Follow the steps in the notebook.
  7. Set up your notebook for call drop monitoring.
  8. Set up the Cognos Analytics Dashboard on your IBM Cloud Pak for Data instance for visualizations.