2026-06-28T20:40:17Zhttps://docta.ucm.es/rest/oai/requestoai:docta.ucm.es:20.500.14352/1323092026-02-14T00:53:07Zcom_20.500.14352_14col_20.500.14352_15
Docta Complutense
author
Andrés-Sánchez, Jorge de
author
Arias Oliva, Mario
author
Llorens Marín, Miguel
author
Souto Romero, Mar
2026-02-13T11:27:50Z
2026-02-13T11:27:50Z
2026-02-11
Jorge de Andrés-Sánchez, Mario Arias-Oliva, Mar Souto-Romero, Miguel Llorens-Marín. Evaluating explanatory factors of the acceptance of blockchain-based loyalty programs with neural networks[J]. Data Science in Finance and Economics, 2026, 6(1): 58-84. doi: 10.3934/DSFE.2026003
2769-2140
10.3934/DSFE.2026003
https://hdl.handle.net/20.500.14352/132309
https://www.aimspress.com/article/doi/10.3934/DSFE.2026003
This study examined the factors influencing the adoption of loyalty programs powered by blockchain (BBLPs) among older adult consumers in the United States. Drawing on stablished
technology acceptance models—such as the Unified Theory of Acceptance and Use of Technology (UTAUT), the Technology Acceptance Model 3 (TAM3), and the Cognitive–Affective–Normative (CAN) framework—a conceptual model is proposed that integrates six explanatory variables: perceived usefulness (PU), perceived ease of use (PEoU), perceived external control (PEC), positive emotions (PEM), negative emotions (NEM), and subjective norm (SN). To assess the model’s explanatory power and predictive accuracy regarding the intention to use BBLPs, five multilayer perceptron neural networks with different architectures were implemented. The study pursues two main objectives: (1) to evaluate the explanatory and predictive capabilities of the proposed model using deep learning techniques, and (2) to determine the relative importance of each explanatory variable using the permutation feature importance method. The results show that all neural network (NN) models achieved high explanatory power and strong predictive performance under Monte Carlo crossvalidation. A single-hidden-layer network based on Kolmogorov’s theorem (13 neurons) offered the best balance between fit and predictive ability. PU consistently emerged as the most influential predictor of usage intention, whereas NEM and SN were the least relevant factors across all configurations. The relative importance of PEoU, PEC, and PEM varied across architectures. These findings confirm the primacy of cognitive variables over affective and normative factors in explaining the acceptance of BBLPs and highlight the usefulness of NNs for modeling technology adoption in marketing research. They also demonstrate that explainable NNs can simultaneously enhance prediction and provide transparent, ranked insights for managerial prioritization in consumers’ loyalty settings.
eng
Evaluating explanatory factors of the acceptance of blockchain-based loyalty programs with neural networks
journal article
UGFyYSBxdWUgZWwgcmVwb3NpdG9yaW8gaW5zdGl0dWNpb25hbCBkZSBsYSBVbml2ZXJzaWRhZCBkZSBNYWRyaWQgcHVlZGEgYWxtYWNlbmFyIHkgZGlzdHJpYnVpciBlbCBvYmpldG8gZGlnaXRhbCBkZXBvc2l0YWRvLCBlcyBuZWNlc2FyaW8gcXVlIGxhIHBlcnNvbmEgcXVlIGhhZ2EgZWwgZGVww7NzaXRvIGxlYSB5IGFjZXB0ZSBsYXMgY29uZGljaW9uZXMgZXN0YWJsZWNpZGFzIGVuIGVzdGEgbGljZW5jaWE6CuKAoiBBY2VwdGFuZG8gZXN0YSBsaWNlbmNpYSwgdXN0ZWQgY29tbyBhdXRvci9yZXMgeS9vIHByb3BpZXRhcmlvL3MgZGUgbG9zIGRlcmVjaG9zIGRlIHByb3BpZWRhZCBpbnRlbGVjdHVhbCwgbyBsYSBwZXJzb25hIGRlbGVnYWRhIHBhcmEgaGFjZXJsbyAsIG90b3JnYSBhbCByZXBvc2l0b3JpbyBkZSBsYSBVbml2ZXJzaWRhZCBDb21wbHV0ZW5zZSBkZSBNYWRyaWQgZWwgZGVyZWNobyBubyBleGNsdXNpdm8gZGUgcmVwcm9kdWNjacOzbiB5IGRpc3RyaWJ1Y2nDs24gZGUgc3Ugb2JyYSBlbiBjdWFscXVpZXIgZm9ybWF0byB5IG1lZGlvLgrigKIgRWwgZGVwb3NpdGFudGUsIGVuIGNhc28gZGUgdW5hIG9icmEgY29uIG3DoXMgZGUgdW4gYXV0b3IsIGdhcmFudGl6YSBxdWUgbG8gaGFjZSByZXNwb25zYWJsZW1lbnRlIGVuIG5vbWJyZSB5IGNvbiBjb25zZW50aW1pZW50byBkZSBsb3MgZGVtw6FzIGF1dG9yZXMuCuKAoiBBY2VwdGEgcXVlIGVsIHJlcG9zaXRvcmlvIGRlIGxhIFVuaXZlcnNpZGFkIENvbXBsdXRlbnNlIGRlIE1hZHJpZCBwdWVkYSBjb25zZXJ2YXIgbcOhcyBkZSB1bmEgY29waWEgZGUgZXN0ZSBkb2N1bWVudG8geSwgc2luIGFsdGVyYXIgc3UgY29udGVuaWRvLCBjb252ZXJ0aXJsbyBhIGN1YWxxdWllciBmb3JtYXRvIGRlIGZpY2hlcm8sIG1lZGlvIG8gc29wb3J0ZSwgcGFyYSBwcm9ww7NzaXRvcyBkZSBzZWd1cmlkYWQgeSBwcmVzZXJ2YWNpw7NuLgrigKIgRGVjbGFyYSBxdWUgZWwgZG9jdW1lbnRvIGVzIHVuIHRyYWJham8gb3JpZ2luYWwgc3V5bywgbyBxdWUgZXMgbGEgcGVyc29uYSBkZWxlZ2FkYSBwYXJhIHJlYWxpemFyIGVsIGRlcMOzc2l0byB5LCBwb3IgdGFudG8sIGN1ZW50YSBjb24gbGEgcG90ZXN0YWQgcGFyYSBvdG9yZ2FyIGxvcyBkZXJlY2hvcyBjb250ZW5pZG9zIGVuIGVzdGEgbGljZW5jaWEuIFRhbWJpw6luIGRlY2xhcmEgcXVlIHN1IGRvY3VtZW50byBubyBpbmZyaW5nZSBsbyBlc3RhYmxlY2lkbyBlbiBsYSB2aWdlbnRlIGxlZ2lzbGFjacOzbiBkZSBwcm9waWVkYWQgaW50ZWxlY3R1YWwuCuKAoiBTaSBlbCBkb2N1bWVudG8gY29udGllbmUgbWF0ZXJpYWxlcyBkZSBsb3MgY3VhbGVzIG5vIHRpZW5lIGxvcyBkZXJlY2hvcyBkZSBhdXRvciwgZGVjbGFyYSBxdWUgaGEgb2J0ZW5pZG8gZWwgcGVybWlzbyBzaW4gcmVzdHJpY2Npw7NuIGRlbCBwcm9waWV0YXJpbyBwYXJhIG90b3JnYXIgYSBsYSBVbml2ZXJzaWRhZCBDb21wbHV0ZW5zZSBkZSBNYWRyaWQgbG9zIGRlcmVjaG9zIHJlcXVlcmlkb3MgcG9yIGVzdGEgbGljZW5jaWEsIHkgcXVlIGVzZSBtYXRlcmlhbCwgY3V5b3MgZGVyZWNob3Mgc29uIGRlIHRlcmNlcm9zLCBlc3TDoSBjbGFyYW1lbnRlIGlkZW50aWZpY2FkbyB5IHJlY29ub2NpZG8gZGVudHJvIGRlbCBjb250ZW5pZG8gZGVsIGRvY3VtZW50by4K4oCiIFNpIGVsIGRvY3VtZW50byBzZSBiYXNhIGVuIHVuYSBvYnJhIHF1ZSBoYSBzaWRvIHBhdHJvY2luYWRhIG8gYXBveWFkYSBwb3IgdW5hIGFnZW5jaWEgdSBvcmdhbml6YWNpw7NuIGRpZmVyZW50ZSBkZSBsYSBVbml2ZXJzaWRhZCBDb21wbHV0ZW5zZSBkZSBNYWRyaWQsIHVzdGVkIGRlY2xhcmEgcXVlIGhhIGN1bXBsaWRvIGNvbiBsYXMgb2JsaWdhY2lvbmVzIHJlcXVlcmlkYXMgcG9yIGVzdGUgY29udHJhdG8gbyBhY3VlcmRvLgrigKIgTGEgVW5pdmVyc2lkYWQgQ29tcGx1dGVuc2UgZGUgTWFkcmlkIGlkZW50aWZpY2Fyw6EgY2xhcmFtZW50ZSBzdS9zIG5vbWJyZS9zIGNvbW8gZWwvbG9zIGF1dG9yL2VzIG8gcHJvcGlldGFyaW8vcyBkZSBsb3MgZGVyZWNob3MgZGVsIGRvY3VtZW50bywgeSBubyBoYXLDoSBuaW5ndW5hIGFsdGVyYWNpw7NuIGRlIHN1IGRvY3VtZW50byBkaWZlcmVudGUgYSBsYXMgcGVybWl0aWRhcyBlbiBlc3RhIGxpY2VuY2lhLgrigKIgVHJhYmFqb3MgZGVwb3NpdGFkb3MgcG9yIHN1IHByb3BpbyBhdXRvcjogYWwgYXV0by1hcmNoaXZhciBlc3RhIGNvbGVjY2nDs24gZGUgZmljaGVyb3MgeSBtZXRhZGF0b3MgYmlibGlvZ3LDoWZpY29zIGFzb2NpYWRvcywgb3RvcmdvIGFsIHJlcG9zaXRvcmlvIGluc3RpdHVjaW9uYWwgZGUgbGEgVW5pdmVyc2lkYWQgQ29tcGx1dGVuc2UgZGUgTWFkcmlkIGVsIGRlcmVjaG8gcGFyYSBhbG1hY2VuYXJsb3MgeSBkaXN0cmlidWlybG9zLiBEZWNsYXJvIHF1ZSBlc3RlIG1hdGVyaWFsIGVzIGRlIG1pIHByb3BpZWRhZCBpbnRlbGVjdHVhbCB5IHF1ZSBlbCByZXBvc2l0b3JpbyBpbnN0aXR1dGljaW9uYWwgZGUgbGEgVW5pdmVyc2lkYWQgQ29tcGx1dGVuc2UgZGUgTWFkcmlkLCBubyBhc3VtZSByZXNwb25zYWJpbGlkYWQgYWxndW5hIGVuIGNhc28gZGUgcXVlIHNlIHByb2R1emNhIHVuYSB2aW9sYWNpw7NuIGRlIGRlcmVjaG9zIGRlIHByb3BpZWRhZCBhbCBkaXN0cmlidWlyIGVzdG9zIGZpY2hlcm9zIG8gbWV0YWRhdG9zLgrigKIgVHJhYmFqb3MgZGVwb3NpdGFkb3MgcG9yIG90cm9zIHF1ZSBubyBzZWFuIHN1IGF1dG9yOiBkZWNsYXJvIHF1ZSBsb3MgbWV0YWRhdG9zIGJpYmxpb2dyw6FmaWNvcyBxdWUgZXN0b3kgYXJjaGl2YW5kbyBlbiBlbCByZXBvc2l0b3JpbyBpbnN0aXR1Y2lvbmFsIGRlIGxhIFVuaXZlcnNpZGFkIENvbXBsdXRlbnNlIGRlIE1hZHJpZCwgc29uIGRlIGRvbWluaW8gcMO6YmxpY28uIFNpIG5vIGZ1ZXNlIGVsIGNhc28sIGFjZXB0byBwbGVuYSByZXNwb25zYWJpbGlkYWQgcG9yIGN1YWxxdWllciBpbmZyYWNjacOzbiBkZSBkZXJlY2hvcyBkZSBhdXRvciBxdWUgY29ubGxldmUgbGEgZGlzdHJpYnVjacOzbiBkZSBlc3RvcyBmaWNoZXJvcyBvIG1ldGFkYXRvcy4K4oCiIFBvciB0YW50bywgdG9kb3MgbG9zIG1ldGFkYXRvcyBwdWJsaWNhZG9zIGVuIGVsIHJlcG9zaXRvcmlvIGluc3RpdHVjaW9uYWwgZGUgbGEgVW5pdmVyc2lkYWQgQ29tcGx1dGVuc2UgZGUgTWFkcmlkLCBlc3TDoW4gZGlzcG9uaWJsZXMgY29uIGxhIGxpY2VuY2lhIENyZWF0aXZlIENvbW1vbnMgQ0MwIDEuMCBVbml2ZXJzYWwgT2ZyZWNpbWllbnRvIGFsIERvbWluaW8gUMO6YmxpY28gKENDMCAxLjApLiBFc3RhIGxpY2VuY2lhIHBlcm1pdGUgY29waWFyLCBtb2RpZmljYXIsIGRpc3RyaWJ1aXIsIHJldXRpbGl6YXIgeSBjb21wYXJ0aXIgcMO6YmxpY2EgeSBsaWJyZW1lbnRlIGxvcyBtZXRhZGF0b3MgKGluY2x1eWVuZG8gc3UgdXNvIGNvbWVyY2lhbCksIHNpbiB0ZW5lciBxdWUgcGVkaXIgcGVybWlzby4gU2kgdGVyY2VyYXMgcGFydGVzIHVzYW4gZXN0b3MgbWV0YWRhdG9zLCBkZWJlbiBoYWNlciB1biByZWNvbm9jaW1pZW50byB5IHVuYSBhdHJpYnVjacOzbiBhIGxhcyBmdWVudGVzIGRlIGxvcyBtaXNtb3MuIExhIHJldXRpbGl6YWNpw7NuIGRlIGVzdG9zIG1ldGFkYXRvcyB0YW1iacOpbiBlcyBsaWJyZSwgdGFsIHkgY29tbyBlc3RhYmxlY2UgbGEgbGljZW5jaWEgZGUgdXNvIENDMC4K
URL
https://docta.ucm.es/bitstreams/708dd7e8-b1ce-4c62-9399-689ada5ebec8/download
File
MD5
ef326c72841aa380a0adb6c4955969f4
893142
application/pdf
Evaluating explanatory factors.pdf