Certain chemometrical tools allow an efficient way to provide valuable data to evaluate the retention behavior of analytes in liquid chromatography. In this study of the retention behavior of azole antifungals, the experimental design was applied in combination with artificial neural networks (ANNs). Three potentially significant factors (methanol content, pH of the mobile phase and column temperature) were incorporated in the plan of experiments, defined by central composite design. As the system outputs, the retention factors of all six investigated substances (fluconazole, ketoconazole, bifonazole, clotrimazole, econazole and miconazole) were determined. The pattern for the analyzed behavior of the system was created by employing ANNs. The final, optimized topology of the highly predictive network was 3-8-6. Twelve experiments were used in a training set, whereas a back-propagation algorithm was optimal for network training. The ability of the defined network to predict the retention of the investigated azoles was confirmed by correlations higher than 0.9912 for all analytes. The presented approach allowed the adequate prediction of the retention behavior of azoles, in addition to the extraction of important information for a better understanding of the analyzed system.