Digital Developer Conference on Cloud Native Security: Register for free and choose your sessions. June 24, 25, & July 1, 2020 Learn more

Create a smarter procurement system with Watson services


Currently, customers perform analyses of various market reports on their own or hire experts to make procurement decisions. These experts analyze reports captured from data sources, a process that can be time-consuming and prone to human error, which could potentially cause a chain effect of issues that can impact production. This code pattern explains how to create a complete end-to-end solution for a procurement use case. With this intelligent procurement system, based on Watson Knowledge Studio (WKS) and Watson Discovery, a customer can receive expert analysis more quickly and accurately.


With this intelligent procurement system, based on Watson Knowledge Studio and Watson Discovery, customers can receive expert analysis more quickly and accurately. The code pattern uses data from newsletters retrieved from Borica, a global specialty chemical company. This data contains information regarding global market suppliers such as the status of the facility or supply capacities and shortages.

The process involves building and integrating a Watson Knowledge Studio (WKS) model into Watson Discovery. The first step is training the WKS model with various use cases (via reports) to better categorize and structure the data so that Watson Discovery can deliver more accurate results. The data extracted from Watson Discovery is fed into a knowledge graph that you can then query to extract relevant info.

As a developer going through this code pattern, you’ll learn how to:

  • Build a data model in Watson Knowledge Studio
  • Import that model into Watson Discovery
  • Graph the dependencies of a procurement-type system

As an end user, you will be able to:

  • Query suppliers for a specific commodity
  • Retrieve information about a supplier and their facility
  • Query to retrieve supplier constraints
  • Query the supply status based on the region



  1. Load the type system and corpus files into Watson Knowledge Studio.
  2. Generate a model by training and evaluating data.
  3. The WKS model is deployed to Watson Discovery.
  4. The application queries Watson Discovery for procurement data.
  5. The application sends procurement data to JanusGraph to build a graph.
  6. Use the app to select a query to perform, which retrieves the graph data from JanusGraph.


Ready to put this code pattern to use? Complete details on how to get started running and using this application are in the README.

Ramesh Poomalai
Rajesh Gudikoti
Richard Hagarty