Model feature analysis method based on building indoor sunlight perception evaluation prediction model

The invention provides a model feature analysis method based on a building indoor sunlight perception evaluation prediction model. The method comprises the following steps: step 1, collecting building indoor light environment characteristic data and a subjective sunlight perception evaluation result, and establishing a basic database of sunlight perception evaluation; 2, exploratory factor analysis and verification factor analysis are carried out, and sunlight perception common factors are obtained; 3, screening an optimal performance machine learning algorithm, and constructing a sunlight perception evaluation prediction model; and 4, performing feature interpretation analysis on the sunlight perception evaluation prediction model by using an SHAP method to obtain light environment feature parameters and influence weights of interactive combinations of the light environment feature parameters on a sunlight perception evaluation result. The sunlight perception evaluation prediction model provided by the inven