The aim work was to evaluate the capacity of a smart electronic tongue in the geographical origin discrimination of milk samples of different provenance. The analysis was carried out with a smart electronic tongue formed by a polypyrrole voltammetric sensor array doped with different doping agents, a multichannel potentiostat, and an Android app installed on a smartphone for signal recording, data storage, and device control. The analyzed samples were collected in different localities belonging to different agroclimatic and environmental zones in Cordoba - Colombia. The registered voltammetric signals showed particular responses to each one of the milk samples, evidencing crosssensitivity, which constituted a "fingerprint" of the samples with information about their characteristics. The pattern recognition analysis showed that the smart electronic tongue was able to discriminate each sample. In addition, the spatial distribution of the samples showed a certain correlation with the subregions of origin. The results made it possible to establish that the smart electronic tongue could be capable of discriminating milk samples of different geographical origins and that its classification may be related to the particularities of the areas of origin