Abstarct: Hansen solubility parameters (HSPs) are numerical values related to the intermolecular forces or adhesive energies that bind molecules together in a material. Quantitative structure–property relationship (QSPR) is an efficient method to predict the properties of various compounds baxsed on their molecular structure. In this study, QSPR models were developed to predict the Hansen solubility parameters (HSPs) of ethyl vinyl acetate in various organic solvents using molecular descxriptors. For this purpose, a comprehensive set of descxriptors was calculated and then reduced using genetic algorithm (GA), random forest (RF), and ant colony algorithm (ACO) as variable selection methods. Artificial neural network (ANN) was used to model the potential nonlinear relationships between molecular descxriptors and retention time. The performance of the models was evaluated baxsed on various statistical criteria, including coefficient of determination and error-baxsed indices, for each external test set. The results showed that the RF–ANN models have a relative advantage compared to other models, indicating the predictive power of this model, although other models also provided acceptable results. The proposed approach provides a reliable tool for predicting the Hansen solubility parameter (HSPs) of ethyl vinyl acetate in various organic solvents and can significantly reduce the need for extensive and costly experimental measurements.