One of the tasks of modern biological anthropology is to develop a system that could objectively classify humanity on the basis of measurements. Here, the decision tree algorithm was chosen to create a classification of groups. The method helps to evaluate the differentiating power of specific dimensions for separating samples and to assess the composition of clusters at each step of the analysis. Standard cranial measurements were used, and the entropy index was chosen as a heterogeneity measure. Classification units were 39 ethno-territorial groups from 13 major regions of the Old World. At the first step, differentiation is made between broad-faced and narrow-faced groups, demonstrating the classificatory value of this trait. The first cluster includes only Mongoloids, admixed Southern Siberian populations, and Ainu. The second cluster is heterogeneous, but its further subdivision is more in line with the traditional classification. Traits underlying the branching of the tree may be the same in different branches, evidencing their taxonomic importance. Capabilities of the decision tree method proved sufficient to construct a system largely similar to the traditional one. Certain traits separate large groups of populations, while others are efficient at the regional level. The method, therefore, can be recommended as a supplementary tool at the intraspecific level.