An Integrative Model to Predict Product Replacement Using Deep Learning on Longitudinal Data
Journal Title: BAR: Brazilian Administration Review - Year 2020, Vol 17, Issue 2
Abstract
Past research on product upgrades has focused either on understanding who and when will upgrade or on figuring out why consumers will upgrade, but seldom on all. It has also neglected the interplay between these matters with decision context and timing. This manuscript depicts a comprehensive approach where, for the first time, product characteristics, individual differences, process, and contextual variables are analyzed on a predictive model of real product upgrades, identified through the systematic collection of primary data from a panel of smartphone consumers. We tested one traditional linear logistic regression model and two types of non-linear, state-of-the-art machine-learning models (extreme gradient boosting and deep learning) to explain upgrading behavior. Results provide an integrative, yet parsimonious, product-upgrade model showing the importance of resources; news about the smartphone brand; sentimental value; predicted, current, and remembered enjoyment; update capacity; and how much the smartphone meets the user’s current needs as the most relevant variables to determine which consumers are more prone to upgrade their smartphones. Our findings advance upgrade decision theory by taking a holistic approach to the phenomenon and bridging different theoretical accounts of the replacement decision literature.
Authors and Affiliations
Vinicius Andrade Brei, Leonardo Nicolao, Maria Alice Pasdiora, Rodolfo Coral Azambuja
Keywords
Related Articles
- EP ID EP686656
- DOI http://dx.doi.org/10.1590/1807-7692bar2020190125
- Views 203
- Downloads 0
Corporate Reputation and Bankruptcy Risk
In view of the influence of corporate reputation on investors’ choices and risk concerns, the purpose of this study was to explore the relationship between corporate reputation and bankruptcy risk in public firms. The in...
A temporal model of perceived control to explain service failures
Research on service failure has neglected the temporal dimension of consumer-perceived control (i.e., past, present and future control). This paper introduces the temporal model of perceived control to service research a...
Implementing Strategies in Complex Systems: Lessons from Brazilian Hospitals
Hospitals, as social organizations, are seen as complex, surprising, ambiguous and paradoxical. The theoretical foundation finds its roots in organizational complexity, strategic management characterized by strategy im...
Fidelity and Game-based Technology in Management Education
This study explores educational technology and management education by analyzing fidelity in game-based management education interventions. A sample of 31 MBA students was selected to help answer the research question:...
A New Contingency View of the Organization: Mananging Complexity and Uncertainty Through Cognition
This paper proposes a new contingency view of the organization and it contributes to the theme through two complementary perspectives. First, it proposes cognition as a function which acts as the main mediator between...