Quantitative structure-property relationship (QSPR) modeling of normal boiling point temperature (T-az) and the composition (weight fraction, X-1w) of 176 binary azeotropic mixtures was performed using ensemble multiple linear regression analysis and fragment descriptors implemented in ISIDA software. The models have been validated in external 5-fold cross-validations procedure and on an additional test set of 24 azeotropes. The prediction errors (3-4 K for T-az and 10-14 wt % for X-1w) are comparable with the noise in experimental data. A simple empirical relationship linking T with boiling points of two molecular components of azeotrope has been suggested.