Combining data from different analytical sources could be a way to improve the performances of chemometric models by extracting the relevant and complementary information for food authentication. In this study, several data fusion strategies including concatenation (low-level), multiblock and hierarchical models (mid-level), and majority vote (high-level) are applied to near-and mid-infrared (NIR and MIR) spectral data for the varietal discrimination of olive oils from six French cultivars by partial least square discriminant analysis (PLS1-DA). The performances of the data fusion models are compared to each other and to the results obtained with NIR or MIR data alone, with a choice of chemometric pre-treatments and either an arbitrarily fixed limit or a control chart decision rule. Concatenation and hierarchical PLS1-DA fail to improve the prediction results compared to individual models, whereas weighted multiblock PLS1-DA models with the control chart approach provide a more efficient differentiation for most, but not all, of the cultivars. The high-level models using a majority vote with the control chart decision rule benefit from the complementary results of the individual NIR and MIR models leading to more consistently improved results for all cultivars.