| |
|
|
|
Structural Equation Modeling and Machine Learning Models for Modeling Consumers’ Adoption of Cryptocurrencies |
|
|
|
PP: 1463-1479 |
|
|
|
doi:10.18576/amis/190618
|
|
|
|
Author(s) |
|
|
|
Ala’aldin Alrowwad,
Evon Abu-Taieh,
Suha Afaneh,
Rami S. Alkhawaldeh,
Thurasamy Ramayah,
Omar Jawabrah,
Ra’ed Masa’deh,
Hamed S. Albdour,
Issam AlHadid,
Sufian Khwaldeh,
|
|
|
|
Abstract |
|
|
| This study examines the adoption of cryptocurrencies in restrictive regulatory environments, focusing on Jordan, and explores the factors influencing adoption using the model evaluates the effects of performance expectancy, effort expectancy, social influence, and facilitating conditions on behavioral intention, alongside trust and multiple risk dimensions (financial, performance, privacy, and security). Data from 395 respondents were evaluated with structural equation modeling (SEM) and seven machine learning models to evaluate proposed hypotheses. The findings reveal that trust significantly drives behavioral intentions, while perceived risks, despite being acknowledged, do not deter adoption. Younger, tech-savvy users were less influenced by effort expectancy, highlighting demographic differences in adoption behavior. The integration of SEM and ML provides both theory-driven insights and predictive accuracy, revealing complementary perspectives on adoption dynamics. The study concludes that building trust, enhancing security and leveraging social influence are critical for wider cryptocurrency adoption, with implications for service providers and policymakers. |
|
|
|
|
 |
|
