Large enterprises and their information systems produce and collect large amounts of data related to different areas, e.g., manufacturing, finance or human resources. This data can be used to complete tasks more efficiently, automate tasks that are currently executed manually, and also generate insights in order to solve certain challenges.
We picked the prediction of order delays as an example. Larger enterprises producing a broad variety of different goods realize large amounts of orders and shipments per day. Not all orders reach customers on time. Today’s systems do not offer automated processes to predict the occurrence of delayed orders or the amount of time by which orders will be delayed. Delayed orders are usually recognized when it is already too late.
Nowadays, machine learning techniques are utilized in many fields and use cases. In cooperation with SAP, we investigate opportunities to apply machine learning techniques to the problem of order delay prediction and also evaluate possibilities for a more generally applicable framework to provide machine learning techniques for the intelligent enterprise. The recent development and in-practice application of in-memory database technology (e.g. SAP HANA) enables us to efficiently execute these techniques on large enterprise datasets.
