Quantitative Structure-Retention Relationship (QSRR) studies were performed for predicting the retention times of 43 constituents of saffron aroma, which were analyzed by solid-phase micro-extraction gas chromatography–mass spectrometry (SPME-GC–MS). The chemical descriptors were calculated from the molecular structures of the constituents of saffron aroma alone, and the linear and non-linear QSRR models were constructed using the Best Multi-Linear Regression (BMLR) and Projection Pursuit Regression (PPR) methods. The predicted results of the two approaches were in agreement with the experimental data. The coefficients of determination ( R 2) of the linear BMLR model were 0.9434 and 0.8725 for the training and test sets, respectively. The other non-linear PPR model gave a more accurate prediction with R 2 values of 0.9806 (training set) and 0.9456 (test set). The proposed models could also identify and provide some insights into structural features that may play a role on the retention behaviors of the constituents of saffron aroma in the SPME-GC–MS system. This study affords a simple but efficient approach for studying the retention behaviors of other similar plants and herbs.