Skip to content

Materials Planning

Premium

Contact your account team to learn more about deploying this premium template for your organization.

The Materials Planning application template, part of the Supply Chain & Ops Suite, provides a predictive model development and deployment workflow in DataRobot for materials planning to predict the risk of delayed inbound deliveries. It utilizes data sourced from S/4HANA via SAP Datasphere and writes back predictions to Datasphere to allow exposure through Analytics Cloud.

This application template helps planners identify delays that can impact downstream manufacturing schedules, customer commitments, and lost revenue through out-of-stock conditions. It helps to identify persistent delay patterns for items, suppliers, source locations, and other attributes, so you can make systematic changes. You can flag items at risk of delay and then take the necessary actions to expedite the delivery, find alternatives, or adjust downstream expectations and dependencies to minimize the impact.

Key features

  • Accurate and transparent predictive models—Identify patterns across the many thousands of purchased items, leveraging DataRobot’s extensive set of algorithms and tuning capabilities to make sense of large volumes of data, and get access to key drivers and insights at the aggregate and individual levels.
  • Seamless SAP integration—Experience smooth data exchanges between SAP and DataRobot via the Datasphere connector, accessing source data and writing back predictive results. This closed loop allows you to continue using your current infrastructure while augmenting it with the advanced AI capabilities that DataRobot provides.
  • Flexible external data integration—Enhance models by leveraging both standard and custom fields in SAP, or incorporate third-party data sources, capturing complex patterns beyond traditional models. This template provides predefined data queries and has the flexibility to be adapted as required.

Architecture

This template provides the below end-to-end AI architecture, from raw inputs to deployed application, while remaining highly customizable for specific business requirements.