On the way: Hailing a taxi with a smartphone? A hybrid SEM-neural network approach

• Published in: Machine learning with applications 2021-06, Vol.4, p.100034, Article 100034
• Main Authors: Lau, Amos Junke, Tan, Garry Wei-Han, Loh, Xiu-Ming, Leong, Lai-Ying, Lee, Voon-Hsien, Ooi, Keng-Boon
• Format: Article
• Language: English
• Subjects: Artificial Neural Network (ANN); Malaysia; Mobile taxi booking services; Mobile Technology Acceptance Model (MTAM); Partial Least Squares-Structural Equation Modeling (PLS-SEM); Sharing economy
• ISSN: 2666-8270; 2666-8270
• DOI: 10.1016/j.mlwa.2021.100034

Undoubtedly, mobile taxi booking (MTB) services have resulted in a significant disruption to the lives of the general public. However, with a lot of firms offering the service in Malaysia, this will bring about confusion to users, especially in deciding which MTB service is the best for their usage. As such, this research looks into determining the antecedents that affect the adoption of MTB services. This was achieved through the utilization of an extended Mobile Technology Acceptance Model (MTAM). A total of 330 usable responses were analyzed using Partial Least Squares-Structural Equation Modeling​ (PLS-SEM) and Artificial Neural Network (ANN) that yielded novel insights which will significantly benefit numerous stakeholders. Furthermore, this research extends the literature on MTB services from the perspective of a developing country and verifies the robustness of using an extended MTAM. •69.11%, 62%, 66.3% and 68.58% variances in TRS, MU, MEU and BI were explained.•TRS, word-of-mouth and MEU significantly predict MU.•TRS, word-of-mouth and TRB significantly predict MEU.•Word-of-mouth and MU significantly predict BI.•The study provides substantial theoretical and practical implications.