Integrating machine learning techniques and the unified theory of acceptance and use of technology to evaluate drivers for the acceptance of blockchain-based loyalty programmes
Blockchain technology is emerging as an innovative solution to overcome the traditional limitations of customer loyalty programmes by offering transparency, decentralization, and interoperability. This study investigates the factors that drive the acceptance of blockchain-based loyalty programmes (B...
| Autores: | , , , |
|---|---|
| Tipo de recurso: | artículo |
| Fecha de publicación: | 2026 |
| País: | España |
| Institución: | Universidad Complutense de Madrid (UCM) |
| Repositorio: | Docta Complutense |
| Idioma: | inglés |
| OAI Identifier: | oai:docta.ucm.es:20.500.14352/129836 |
| Acceso en línea: | https://hdl.handle.net/20.500.14352/129836 |
| Access Level: | acceso abierto |
| Palabra clave: | Blockchain Blockchain-based loyalty programmes UTAUT Explainable machine learning Decision tree regression Random forest Extreme gradient boosting Shapley additive explanations Ciencias Sociales 53 Ciencias Económicas |
| Sumario: | Blockchain technology is emerging as an innovative solution to overcome the traditional limitations of customer loyalty programmes by offering transparency, decentralization, and interoperability. This study investigates the factors that drive the acceptance of blockchain-based loyalty programmes (BBLPs) among U.S. digital natives. The analysis is grounded in the Unified Theory of Acceptance and Use of Technology (UTAUT), extended with trust, and incorporates advanced machine learning techniques. The main objectives are: (1) to generate an exploratory, data-driven understanding of the factors that explain and predict the acceptance of BBLPs using Decision Tree Regression (DTR) and its ensemble extensions—Random Forest (RF) and Extreme Gradient Boosting (XGBoost); and (2) to identify the relative importance of explanatory variables in predicting the behavioural intention to use BBLPs. The results show that while DTR effectively captures how variables interact to generate acceptance, and RF provides a slightly greater predictive capability to XGBoost and both predict better than DTR. According to the Shapley Additive Explanations metric, performance expectancy emerges as the most influential factor in the intention to use BBLPs, followed by trust, facilitating conditions and effort expectancy. Social influence and prior experience using loyalty programmes have a moderate impact, while gender plays a marginal role. This study reinforces the relevance of the UTAUT model in the analysis of emerging technologies and highlights the value of integrating machine learning and interpretability to understand blockchain acceptance patterns in a marketing context. |
|---|