Introduce structural equation modelling to machine learning problems for building an explainable and persuasive model

With the development of artificial intelligence technologies, high accuracy machine learning methods has become a non-unique standard. People are beginning to be more concerned about understandability between humans and machines. The interference procedure machines is hoped accord with human thinking as much possible, which spawned recent ongoing demands for developing explainable models. present study proposes new persuasive model problems by introducing Structural Equation Modelling into picture. Six parts make up model, from data collection evaluation. can used analysis, learning, causal analysis. proposed also transparent interpreted design application. A practical experiment shows its effectiveness in healthcare problem.