Prediction of the Influential Factors on Eating Behaviors: A Hybrid Model of Structural Equation Modelling-Artificial Neural Networks

Table 1

Literature review of SEM-ANN research.

No	Research	Year	Hybrid model	Case study input	Evaluation criteria	Results and discussion	Statistical model
1	[37]	2016	SEM-ANN	Students’ intention towards academic use of Facebook	R^2 RMSEA	The hybrid model helps to better understand factors that predict the usage of Facebook in higher education	CB-SEM
2	[30]	2015	SEM-ANN	Influence of SERVPERF on customer satisfaction and customer loyalty among low cost and full service	RMSEA	The use of the two-stage predictive-analytic SEM-neural network analysis may provide a more holistic understanding and thus may provide a significant methodological contribution from the statistical point of view	CB-SEM
3	[38]	2013	SEM-ANN	Factors that influence consumers’ mobile-commerce adoption intention	RMSEA	Employing a multianalytic approach demonstrated how combining two different data analysis approaches in either methodology and the alternative analysis is able to improve the validity and confidence in the results	CB-SEM
4	[39]	2012	SEM-ANN	Adoption of an interorganizational system standard and its benefits by using RosettaNet	RMSEA	Improved existing technology adoption methodology was achieved by integrating both SEM and neural network for examining the adoptions of RosettaNet	CB-SEM
5	[40]	2014	SEM-ANN	User’s intention to adopt mobile learning, Malaysia	RMSEA	This has provided a novel perspective in examining the key determinants of m-learning acceptance, while a greater amount of variance was explained in this model	CB-SEM
6	[41]	2014	SEM-ANN	Predictors of open interorganizational systems (IOS) adoption by using RosettaNet as a case study	RMSE	The neural network supports the antecedents of RosettaNet adoption in SMEs	PLS-SEM
7	[42]	2019	SEM-ANN	Predict customers’ intention to purchase battery electric	RMSE	A new approach solved the analytical problems in this research field	PLS-SEM