Purpose: The purpose of this paper is to investigate if there is a difference in hygiene parameters of raw milk produced in organic and conventional farm of similar size. In parallel, the aim was to determine if there are differences in pasteurized organic and conventional milk samples delivered on the market. Design/methodology/approach: Raw milk samples were analyzed for aerobic colony count (ACC), somatic cell count (SCC), acidity, temperature, fat and protein content. On the other side, final products of organic and conventional pasteurized milk with 2.8 percent declared milk fat were analyzed for Raman spectroscopy, color change and sensorial difference. Findings: Results of raw milk analysis showed statistically significant differences in fat content, SCC, acidity, temperature and ACC (p<0.05). It is of note that ACC for organic milk were lower for approx. 1 log CFU/ml compared to conventional milk samples. Pasteurized organic milk samples had a significantly higher L* value than those samples originating from conventional farms, indicating that organic is “more white” compared to conventional milk. According to the results of triangle test, with 95 percent confidence no more than 10 percent of the population is able to detect a difference. Research limitations/implications: A limitation of this research is the fact that good veterinary practices at farms, namely, animal health and adequate usage of medicine for treating the animals, animal welfare and animal feeding were not analyzed. Originality/value: This study analyzed potential differences in organic and conventional milk at two important production stages of the milk chain – at receipt at dairy plant (raw milk) and perceived by consumers (final product).

Food fraud in meat products presents serious economic and public health challenges, underscoring the need for rapid and reliable detection methods. This study investigates the potential of Raman spectroscopy combined with machine learning to accurately discriminate between pure and mixed minced meat preparations. We evaluated three classification algorithms: Support Vector Machines (SVMs), Artificial Neural Networks (ANNs), and Random Forests (RFs). Raman spectra were collected from 19 distinct samples consisting of different ratios of pork, beef, and lamb minced meat. Our findings suggest that homogenization markedly enhances spectral consistency and classification accuracy. In the pure meat samples case, all three models (SVM, ANN, and RF) achieved notable increases in classification accuracies (from 0.50–0.70 to above 0.85), a dramatic improvement over unhomogenized samples. In more complex homogenized mixtures, SVM delivered the highest performance, achieving an accuracy of up to 0.88 for 50:50 mixtures and 0.86 for multi-ratio samples, often outperforming both ANN and RF. While the underlying interpretation of the classification models remains complex, the findings consistently underscore the critical role of homogenization on model performance. This work demonstrates the robust potential of the Raman spectroscopy-coupled machine learning approach for the rapid and accurate identification of minced meat species.