Warehouse Management with SAP

Machine Learning (ML) for Monitoring Purposes: 
Put an End to Slow-Moving Materials!  

Machine Learning (ML) offers enormous potential for automation and process insights. SAP customers can also benefit from machine learning: For example, the S/4HANA 2020 release delivered approximately 20 ML scenarios while S/4HANA Cloud 2105 has already delivered 24 ML scenarios, one of which is used to monitor slow-moving materials. XEPTUM can help you to make the best use of these scenarios. 

We have already reported in detail on the basics of ML as a branch of Artificial Intelligence (AI) and SAP Intelligence Scenario Lifecycle Manager (ISLM). ISLM is the control center for ML approaches within SAP S/4HANA. The ML scenarios available in ISLM are fully integrated into the processes and cover different features from document recognition to predictions based on historical process data. Forecast results are displayed in operational and analytical SAP Fiori apps, allowing employees to respond to specific situations much earlier or more proactively.

How Can Slow or Non-Moving Materials Be Monitored?

The ISLM scenario "Slow or Non-Moving Materials for Inventory Manager" is a milestone on the road to a digital warehouse. XEPTUM will gladly accompany you on this journey and provide competent advice along the way. This intelligent scenario enables SAP customers to use the predictive analytics model in warehouse management to monitor slow-moving materials. The two components here are namely the predefined forecast scenarios MMSLO_CONSUMPTION_02 (Consumption Data for Slow or Non-Moving Materials) and MMSLO_STOCK_LEVEL_02 (Stock level Data for Slow or Non-Moving Materials). The predictive analytics model needs to be trained with different data sets in the SAP Fiori app "Predictive Models". Afterwards, the quality of the trained model (accuracy, loss) is evaluated and the newly created version is activated.

How Is the Development of the Slow-Moving Indicator Calculated?

The intelligent "Slow or Non-Moving Materials for Inventory Manager" scenario allows companies to track the development of the slow-moving indicator over a defined period of time. If the predictive model is active, the system calculates a predicted future value – based on your company's historical data – for how the slow-moving indicator will develop over the course of the next three months.

The predictive analytics features are fully integrated into the SAP Fiori app "Slow or Non-Moving Materials".

This Fiori app can be used to monitor and make time-dependent investigations of the slow or non-moving materials in your stock. Non-moving materials represent a combination of storage locations and materials where the stock level is not zero and no consumption postings were made for a defined period of time. It is also possible to monitor slow-moving materials. Based on these results, companies can react immediately with follow-on activities such as scrapping or stock transfers.

The app supports inventory managers in their daily work to achieve maximum inventory accuracy and optimize the inventory situation.

The predicted data is displayed in the app as a colored line.

Would You Like to use ML to Optimize Your Inventory Situation?

Are you interested in improving your inventory situation with SAP S/4HANA's intelligent "Slow or Non-Moving Materials for Inventory Manager" scenario? Contact us today. The consultants at XEPTUM will be happy to outline the various ML opportunities for monitoring slow or non-moving materials in your warehouse stock.