Publikationen

Data plays a central role in many of today's business models. With the help of advanced analytics, knowledge about real-world phenomena can be discovered from data. This may lead to unintended knowledge spillover through a data-driven offering. To properly consider this risk in the design of data-driven business models, suitable decision support is needed. Prior research on approaches that support such decision-making is scarce. We frame designing business models as a set of decision problems with the lens of Behavioral Decision Theory and describe a Design Science Research project conducted in the context of an automotive company. We develop an artefact that supports identifying knowledge risks, concomitant with design decisions, during the design of data-driven business models and verify knowledge risks as a relevant problem. In further research, we explore the problem in-depth and further design and evaluate the artefact within the same company as well as in other companies.

Increasing digitization is generating more and more data in all areas ofbusiness. Modern analytical methods open up these large amounts of data forbusiness value creation. Expected business value ranges from process optimizationsuch as reduction of maintenance work and strategic decision support to businessmodel innovation. In the development of a data-driven business model, it is usefulto conceptualise elements of data-driven business models in order to differentiateand compare between examples of a data-driven business model and to think ofopportunities for using data to innovate an existing or design a new businessmodel. The goal of this paper is to identify a conceptual tool that supports datadrivenbusiness model innovation in a similar manner: We applied three existingclassification schemes to differentiate between data-driven business models basedon 30 examples for data-driven business model innovations. Subsequently, wepresent the strength and weaknesses of every scheme to identify possible blindspots for gaining business value out of data-driven activities. Following thisdiscussion, we outline a new classification scheme. The newly developed schemecombines all positive aspects from the three analysed classification models andresolves the identified weaknesses.