A general approach is proposed to estimate the number of occupants in a zone using different kinds of mea- surements such as motion detection, power consump- tion or CO2 concentration. The proposed approach is inspired from machine learning. It starts by deter- mining among different measurements those that are the most useful by calculating the information gains. Then, an estimation algorithm is proposed. It relies on a C4.5 learning algorithm that yields human read- able decision trees using measurements to estimate the number of occupants. It has been applied to an office setting.