Abstract: Structural Equation Modeling (SEM) is used to analyze the complex relationships between observed variables and latent variables. Covariance-based structural equation modeling (CB-SEM) and partial least squares structural equation modeling (PLS-SEM) are the two types of SEM. SEM has been widely used in social science such as organizational management, information systems, marketing management and other disciplines. In recent years the number of research papers using PLS-SEM method has increased. Since CB-SEM and PLS-SEM are different in algorithm and requirements, the application of unsuitable methods may lead to inaccurate results. Therefore, it is necessary to understand the differences between the two methods and report guidelines. This paper reviews the conditions and application criteria of CB-SEM and PLS-SEM, and takes the use of fintech by wealth management enterprises as an example to compare the analysis process and results of the two methods, emphasizing the importance and necessity of choosing appropriate methods. This paper provides a valuable reference for researchers to use SEM for accurate data analysis.

Key words: Structural Equation Modeling(SEM), CB-SEM, PLS-SEM, Data analysis, Comparison of methods