Resumen
In this study, official data from Russia?s regions for the period from 2015 to 2019 were analysed on the basis of 12 predictor variables in order to explain the regional raw milk price. Model training and hyperparameter optimisation were performed with a spatiotemporal cross-validation technique using the machine learning (ML) algorithm. The findings of the study showed that the RF algorithm had a good predictive performance Variable importance revealed that drinking milk production, income, livestock numbers and population density are the four most important determinants to explain the variation in regional raw milk prices in Russia.