The objective of the work was to identify the main variables that influence the purchase decision process. 400 interviews were conducted, as a data collection instrument, the multivariate analysis method called CHAID algorithm (Chi-squared Automatic Interaction Detection) was used, which allows segmentation of quantitative and categorical variables using contingency tables and determining the association between variables with the X2 statistic. It was found that the age, education, gender, and income of the individual are related to the preferences of the dairy consumer.