Join our Webinar on June, 16th, 11am (CEST) on Contract and Billing.
So that processes also run smoothly in the warehouse during seasonal order peaks, many companies subjectively trust the advance planning of their logistics processes on their previous experience. However, in order to make precise predictions of future capacities, logistics professionals must be able to translate these experiences into available and usable data at any time. The Ehrhardt + Partner Group (EPG) supports this process through predictive analytics. Integrated AI (Artificial Intelligence) components process all the relevant data from the supply chain which constantly increases the precision of the predictions. This makes networked logistics processes even more economical and efficient.
Solid advance planning is essential in times of high competitive pressures, scarcity of resources and just-in-time deliveries. For example, in daily logistics operations, forecasts for raw material requirements, the order situation, transportation volumes, numbers of packing units and picking times are urgently required. The predictive analytics concept from EPG supports companies in making reliable future forecasts through the analysis of past data. Together with its technology partner IBM, EPG creates models in which relevant logistics data from customer systems are processed. External influencing factors such as the weather or the news can also be incorporated into forecasts on future capacity levels. And with each passing day, the accuracy of the predictions increases.
How does predictive analytics work in the field?
EPG has extensively tested a wide range of applications for predictive analytics. One example of this is the predictive resource management system at Ehrhardt + BOMAG Logistics GmbH (EBL) in Boppard. EBL holds more than 50,000 spare parts of various shapes and sizes for BOMAG’s construction machines in its warehouse. To allow for comprehensive, precise, and reliable planning and scheduling of all resources, the existing resource management system has been expanded by a predictive component. Assisted by IBM Watson Studios, EPG has created a self-learning model of current and past order data. Previously unstructured data such as emails and reports have also been integrated into the forecast as external influencing factors using the Discovery API. The data model created enables control center staff members to now use the predictive analytics dashboard as a smart assistant for predictive resources planning. The ongoing data synchronization increases the precision of the forecasts on an ongoing basis.