The continuous innovation of its business models is an important task for a company to stay competitive. During this process, the company has to validate various hypotheses about its business models by adapting to uncertain and changing customer needs effectively and efficiently. This adaptation, in turn, can be supported by the concept of Software Product Lines (SPLs). SPLs reduce the time to market by deriving products for customers with changing requirements using a common set of features, structured as a feature model. Analogously, we support the process of business model adaptation by applying the engineering process of SPLs to the structure of the Business Model Canvas (BMC). We call this concept a Business Model Decision Line (BMDL). The BMDL matches business domain knowledge in the form of a feature model with customer needs to derive hypotheses about the business model together with experiments for validation. Our approach is effective by providing a comprehensive overview of possible business model adaptations and efficient by reusing experiments for different hypotheses. We implement our approach in a tool and illustrate the usefulness with an example of developing business models for a mobile application.

In the last years, store-oriented software ecosystems are gaining more and more attention from a business perspective. In these ecosystems, third-party developers upload extensions to a store which can be downloaded by end users. While the functional scope of such ecosystems is relatively similar, the underlying business models differ greatly in and between their different product domains (e.g. Mobile Phone, Smart TV). This variability, in turn, makes it challenging for store providers to find a business model that fits their own needs. To handle this variability, we introduce the Business Variability Model (BVM) for modeling business model decisions. The basis of these decisions is the analysis of 60 store-oriented software ecosystems in eight different product domains. We map their business model decisions to the Business Model Canvas, condense them to a variability model and discuss particular variants and their dependencies. Our work provides store providers a new approach for modeling business model decisions together with insights of existing business models. This, in turn, supports them in creating new and improving existing business models.

Mobile app stores like Apple's AppStore or Google's PlayStore are highly competitive markets for third-party developers wanting to develop successful applications. During the development process, many developers focus on the multitude of product functions but neglect the business model as an equally important part. As a result, developers often fail to meet customer needs, leading to unnecessary development costs and poor market penetration. This, in turn, raises the question of how we intertwine the business model and product functions during the development process to ensure a better alignment between the two. In this paper, we show this intertwined development by adapting the concept of Twin Peaks to the business model and product functions. Based on feature modeling as an abstraction layer, we introduce the concept of a Business Model Decision Line (BMDL) to structure the business model decisions and their relation to product functions structured in a Software Product Line (SPL). The basis of our feature models is the analysis of top listed applications in the app stores of Apple and Google. To create and modify both models, we provide an incremental feature structuring and iterative feature selection process. This combination of abstraction layer and development process supports third-party developers to build successful applications both from a business and a product perspective.

Ein wichtiges Element der Digitalen Transformation ist die Digitalisierung der Prozesse in Unternehmen. Eine Herausforderung besteht hierbei in der systematischen Erkennung von Digitalisierungspotenzialen in Prozessen. Bestehende Ansätze benötigen Experten, welche Potenziale über ihre Erfahrung oder zeitaufwendig mithilfe von Musterkatalogen identifizieren. In diesem Artikel werden verschiedene Digitalisierungspotenziale klassifiziert und Muster für ein zukünftiges musterbasiertes Analyseverfahren zur automatisierten Identifikation von Digitalisierungspotenzialen in BPMN-Diagrammen beschrieben. Im Vergleich zu bestehenden Ansätzen erlaubt es Experten die Identifizierung von Digitalisierungspotenzialen effizienter und effektiver durchzuführen.