Modeling Demand Spikes in Continuously Evolving Products Using Dynamic Customer Preferences

Abstract As the digital marketplace continues to evolve with rapid changes in consumer preferences and the frequent introduction of product updates, traditional models for estimating demand are often unsuitable for use. These models often fail to account for the dynamic nature of product development and the complex decision-making processes of consumers, particularly in the face of product updates. To bridge this gap, this study extends a demand model based on decision field theory (DFT), focusing on a phenomenon largely unexplored in the existing literature: the update engagement spike (UES). Being able to capture this phenomenon, where demand surges following a product update, is crucial for accurately modeling demand around product updates. We extend the DFT-based demand model to capture consumer responses to updates more effectively. We then validate this extended model using real-world data from competing software products, demonstrating its practical use. Furthermore, we outline avenues for future research, including methods for distinguishing between customer segments and attributes with greater accuracy.