Skip to content. | Skip to navigation

Informatik 5
Information Systems
Prof. Dr. M. Jarke
Personal tools
You are here: Home Theses An Expert Recommender System providing Decision Support for Production Network Adjustment


Prof. Dr. M. Jarke
RWTH Aachen
Informatik 5
Ahornstr. 55
D-52056 Aachen
Tel +49/241/8021501
Fax +49/241/8022321

How to find us

Annual Reports





An Expert Recommender System providing Decision Support for Production Network Adjustment

Thesis type
  • Bachelor
Status Open

The ongoing digitalization of industry has many facets - on the one hand, gathered and newly usable data can be related to machinery itself and can be used to improve production processes; on the other hand, different data can be used as a basis for automated decision making and decision support regarding, e.g., the planning or adjustment of production networks.

The context of this thesis is data-driven decision support for production network adjustment within the project "Internet of Production". The goal of this thesis is to develop an expert recommender system, that based on the learning input (telling us which indicators in the data caused what reaction in the past) shall give recommendations on how one should behave on newly incoming indicators.
The aspect "recommender" is important because the system shall give (multiple) recommendations on how the human decider shall react to this new information and rate those recommendations.
The aspect "expert" is significant because the idea is to incorporate knowledge of human experts into the system and combine their knowledge in such a way that the system not only knows what every single human expert knew (and could therefore give recommendations accordingly) but also combines their knowledge enabling it to provide recommendations that a single human could not have given.

The result shall be aligned to the concept of digital shadows, where the idea is that one real system, object, etc., can have multiple digital reflections serving different purposes or questions to be answered. In our context, this could mean that we could have different structures or components in the recommender system that serve to answer different hypothesis.

You are expected to have some knowledge in machine learning and will have to implement such a system. At the same time, you are expected to bring your own ideas and thoughts into it.

If you are interested in this thesis, a related topic or have additional questions, please do not hesitate to send a message to braun (AT)

Document Actions