Rocky Mountain elk (Cervus elaphus nelsoni) seasonal migration, body-condition and sex ratios are important parameters for characterizing elk populations but have thus far been outside the scope of non-invasive methods. Fecal microbiomes can be surveyed non-invasively from scat samples and are associated with changes in diet, stress, age, disease and physical condition of the host, as well as differences between sexes. With this in mind, we surveyed the fecal microbiome of Montana elk that varied geographically (i.e. populations), by body condition, age and by sex. Our goal was to explore an approach for evaluating linkages between the host animal and its microbiome composition, and to develop bioinformatic techniques useful for characterizing host categories and population parameters based on microbiome analysis. We built a supervised-machine learning classifier based on bacterial taxa with cross validation to predict each fecal microbiome’s affiliation to known host categories. The microbiome classifier predicted host population, sex, age and body-condition with promising cross validation results. Monitoring wildlife microbiomes represents a breakthrough for non-invasive conservation biology, and we provide proof of concept for obtaining low cost, fine scale, management-relevant information from scat samples.