Extended Technology Acceptance Model to Predict Mobile-Based Money Acceptance and Sustainability: A Multi-Analytical Structural Equation Modeling and Neural Network Approach
| Autor: | Yongan Xu, Komlan Gbongli, Komi Mawugbe Amedjonekou |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Computer science
Geography Planning and Development TJ807-830 Developing country Management Monitoring Policy and Law TD194-195 Renewable energy sources Structural equation modeling technology acceptance model (TAM) 0502 economics and business Mobile payment Econometrics GE1-350 Payment service provider adoption Financial inclusion Environmental effects of industries and plants Artificial neural network Renewable Energy Sustainability and the Environment business.industry artificial neural networks (ANN) 05 social sciences sustainability structural equation modeling (SEM) Environmental sciences Sustainability mobile-based money service Survey data collection 050211 marketing Technology acceptance model business 050203 business & management |
| Zdroj: | Sustainability Volume 11 Issue 13 Sustainability, Vol 11, Iss 13, p 3639 (2019) |
| ISSN: | 2071-1050 |
| DOI: | 10.3390/su11133639 |
| Popis: | This research is a pioneering study into the adoption of mobile-based money services for financial inclusion and sustainability in developing countries like Togo. Owing to their differences from more usual mobile-based banking and payment services, such technology is being aggressively promoted by providers of network telecommunication companies. However, the factors influencing its sustainable acceptance remain largely unknown. This paper extends the original Technology Acceptance Model (TAM), by integrating self-efficacy (SEMM), technology anxiety (TAMM), and personal innovativeness (PIMM). The research model is assessed with survey data of 539 actual and prospective mobile money users employing structural equation modeling&ndash artificial neural networks (SEM&ndash ANN) approach. A feed-forward-back-propagation (FFBP) multi-layer perceptron (MLP) ANN with significant predictors obtained from SEM as the input units and the root mean square of errors (RMSE) indicated that the ANN method achieves high prediction accuracy. The results present conclusive evidence that perceived ease-of-use (PEMM) is the most significant factor affecting consumers&rsquo attitudes to mobile-based money. While perceived usefulness (PUMM) and PIMM affect adoption decisions, their impact is much lower. Consumer attitudes and intentions were found to have a significant relationship with TAM. SEMM and TAMM however, they showed mixed results. These findings will be useful to retain prevailing users and attract new ones. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|