One input-class and two input-class classifications for differentiating olive oil from other edible vegetable oils by use of the normal-phase liquid chromatography fingerprint of the methyl-transesterified fraction

•The methyl-transesterified fraction was used to differentiate olive oils from other vegetable oils.•Multivariate classification methods were applied on normal-phase liquid chromatography fingerprinting.•One input-class and two input-class classification strategies were tested to develop models capable of discriminating olive oil from other edible vegetable oils.•Dummy class was explained and applied for the first time to differentiate olive oils from other edible vegetable oils.•Quality performance metrics were collected and applied to evaluate of the performance of the classifications. A new method for differentiation of olive oil (independently of the quality category) from other vegetable oils (canola, safflower, corn, peanut, seeds, grapeseed, palm, linseed, sesame and soybean) has been developed. The analytical procedure for chromatographic fingerprinting of the methyl-transesterified fraction of each vegetable oil, using normal-phase liquid chromatography, is described and the chemometric strategies applied and discussed. Some chemometric methods, such as k-nearest neighbours (kNN), partial least squared-discriminant analysis (PLS-DA), support vector machine classification analysis (SVM-C), and soft independent modelling of class analogies (SIMCA), were applied to build classification models. Performance of the classification was evaluated and ranked using several classification quality metrics. The discriminant analysis, based on the use of one input-class, (plus a dummy class) was applied for the first time in this study.