Handling the Efficiency–Personalization Trade-Off in Service Robotics: A Machine-Learning Approach

While multiple mechanisms for value creation from big data analytics (BDA) exist, their application in everyday life can create trade-offs, particularly in the context of service robotics where the dispersion of autonomous digital technologies creates potentials for data-driven efficiency gains. Attending to personal preferences in such contexts, increasingly vital for customer acceptance, may run counter to efficiency, thus constraining value creation and rendering efficiency-personalization trade-offs a key managerial challenge. For the case of autonomous vehicles (AVs), we formalize this trade-off and design a machine-learning approach to handle it by drawing on a unique dataset comprising 35,000 drives by 1,850 users. We consider the real-time dynamics and user interactions that affect the decisions of AVs and develop a model extension that allows for leveraging the properties of sharing business models to make better-informed decisions. Our study contributes to information systems (IS) AV research by providing an artifact that targets both efficiency and personalization of AV operations as well as the dynamic balance between the two. With the focus on everyday life contexts, our study points to the value of incorporating trade-offs between competing goals as well as human-centered perspectives in information systems designs for research on BDA value creation. For practitioners, our work provides a practical and generalizable approach to realize the potentials of service robots without risking customer acceptance.