This study explores the prediction of latent sweat fingerprint retention time on glass using hyperspectral imaging combined with multiple models. The hyperspectral image data of latent sweat fingerprints on glass were collected, and Savitzky-Golay (SG) convolutional smoothing and standard normal variate transformation were performed on the original spectral data. The feature bands were selected using successive projections algorithm, and then support vector machine (SVM), genetic algorithm back propagation (GA-BP) neural network, and partial least squares regression (PLSR) models were constructed and compared for predicting the latent sweat fingerprint retention time on glass in both full and feature bands. The results indicate that these three models are not applicable in the full band. In the feature band, the values of root mean square error of prediction of SVM, GA-BP neural network, and PLSR models reached 3.247 d, 3.035 d, and 3.060 d, respectively, with coefficient of determination reaching 0.627, 0.659, and 0.606, respectively. The relative percent deviation is higher than 1.4 with all the three models, thus predicting the retention time of fingerprints to a certain extent. Notably, hyperspectral imaging technology combined with multiple models can be used to predict the retention time of sweat latent fingerprints on glass.