In order to improve the efficiency and accuracy of predicting the thermal and moisture comfort of skin-tight clothing (also called skin-tight underwear), principal component analysis(PCA) is used to reduce the dimensions of related variables and eliminate the multicollinearity relationship among variables. Then, the optimized variables are used as the input parameters of the coupled intelligent model of the genetic algorithm (GA) and back propagation (BP) neural network, and the thermal and moisture comfort of different tights (tight tops and tight trousers) under different sports conditions is analysed. At the same time, in order to verify the superiority of the genetic algorithm and BP neural network intelligent model, the prediction results of GA-BP, PCA-BP and BP are compared with this model. The results show that principal component analysis (PCA) improves the accuracy and adaptability of the GA-BP neural network in predicting thermal and humidity comfort. The forecasting effect of the PCA-GA-BP neural network is obviously better than that of the GA-BP, PCA-BP, BP model, which can accurately predict the thermal and moisture comfort of tight-fitting sportswear. The model has better forecasting accuracy and a simpler structure.