This study compares two data processing techniques (fingerprinting and untargeted profiling) to authenticate hazelnut cultivar and provenance based on its unsaponifiable fraction by GC–MS. PLS-DA classification models were developed on a selected sample set (n = 176). As test cases, cultivar models were developed for “Tonda di Giffoni” vs other cultivars, whereas provenance models were developed for three origins (Chile, Italy or Spain). Both fingerprinting and untargeted profiling successfully classified hazelnuts by cultivar or provenance, revealing the potential of the unsaponifiable fraction. External validation provided over 90 % correct classification, with fingerprinting slightly outperforming. Analysing PLS-DA models' regression coefficients and tentatively identifying compounds corresponding to highly relevant variables showed consistent agreement in key discriminant compounds across both approaches. However, fingerprinting in selected ion mode extracted slightly more information from chromatographic data, including minor discriminant species. Conversely, untargeted profiling acquired in full scan mode, provided pure spectra, facilitating chemical interpretability.