Our group includes PostDocs, PhD student and student assistants. It is headed by Prof. Dr. Hasso Plattner and represented by Dr. Matthias Uflacker. If you are interested to be part of our team please contact Dr. Matthias Uflacker.
Our team is giving a series of lectures and seminars with a focus on enterprise systems design and in-memory data management. Strong links to the industry ensure a close connection between theory and its implementation in the real world.
Our research focuses on the principles of in-memory data management on modern hardware and the integration of different hard- and software systems to meet business requirements. This involves studying the conceptual and technological aspects of modern enterprise applications as well as tools and methods for enterprise systems design.
We continually strive to translate our research into practical outputs that improve the quality of enterprise applications. A close link to industry partners ensures relevance and impact of our work. Get here an overview of our current and previous projects.
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.
Nowadays, machine learning techniques are utilized in many fields and use cases. In cooperation with the SAP Innovation Center Network, this bachelor project investigated opportunities to apply machine learning techniques to the problem of order delay prediction. The recent development and in-practice application of in-memory database technology (e.g. SAP HANA) enabled the efficient execution of these techniques on large enterprise datasets.
Edison: Predictive Analytics for Order Fulfillment
Delays and problems during sales order fulfillment processes are caused by a multitude of factors. Oftentimes issues causing the delay only become obvious when the process is already interrupted. To improve the handling of these issues, one needs to analyze and extract the factors commonly responsible for delays.
Enterprise systems contain often data of millions of historic sales orders. These can be utilized to draw conclusions for current and upcoming orders. Based on real world data of historic sales order fulfillment processes, we apply decision trees that estimate which issues may interrupt the process for a currently open order. This flexible machine learning technique enables to display details of the most pressing sales orders on the one hand, and furthermore to review the reasons why a particular sales order is considered to become delayed on the other hand. Therefore, the user receives the relevant information about critical indicators of an open sales order right at the beginning of the fulfillment process.
In order to proactively use the received information, a partially observable Markov decision process (POMDP) model is applied to propose the best long-term action. Therefore, based on the previously derived risks for issues of an open sales order, and the information about all action’s costs and consequences the user receives the best action to mitigate a delayed sales order.
ERROR: Content Element with uid "168620" and type "media" has no rendering definition!
"A Course in In-Memory Data Management" by Prof. Dr. h.c. Hasso Plattner. This book is the culmination of six years work of in-memory research. As such, it provides the technical foundation for combined transactional and analytical workloads inside one single database as well as examples of new applications that are now possible given the availability of the new technology. The book is available at Springer.