Introduction: The quantitative structure-property relationship (QSPR) is a successful strategy for prediction of surfactant properties based on modeling between calculated descriptors from molecular structures of the surfactants and chemical or physical properties of the solution. There are a great number of molecular descriptors that have been used in such QSPR studies, which can be divided into six types, namely constitutional descriptors, topological descriptors, electrostatic descriptors, geometrical descriptors, quantum chemical descriptors and thermodynamic descriptors. There are some reports about the applications of QSPR approaches to predict the CMC of anionic, nonionic and Gemini surfactants.Aim: In the present work, the logCMC of some tetra-alkylammonium and alkylpyridinium salts was mathematically related to the molecular structure properties.Material and Methods: All critical micelle concentrations data of this investigation were obtained from a set of cationic surfactants. They are measured in water at 25 oC. The data set consists of 44 surfactants were divided into two groups with 29 tetra-alkyl ammonium and 15 alkylpyridinium salts. The 3D molecular structures generated by ChemDraw 2005 and optimized by AM1 rotuine of MOPAC. The molecular descriptors generated ChemSAR and Dragon ver 3.0Results: OLS regression analysis provided useful equations that can be used to predict the logCMC of cationic surfactants in this study. Model (I) which was used to estimate the logarithm of CMC tetra-alkyl ammonium surfactants using four structural descriptors could be represented as:logCMC=-1.0097 - 0.1258Lc – 0.0123VH + 0.0960AHG +0.0053RHCIn=20.R2 =0.9860,s2 =0.0210F =135, model (I)The logCMC of alkylpyridinium surfactants with three descriptors can be effectively predicted using following Eq. for model (II).LogCMC=6.0291 – 0.2461Lc – 0.0011VH + 0.0249RHCIModel(II), n = 10,R2 =0.09940,s2 =0.0098,F =159, model (II)simultaneous model, which was used to estimate logCMC all cationic surfactants using four molecular structure descriptors, could be represented as log CMC = -1.4055 - 0.1529Lc - 0.0101VH + 0.1214 AHG + 0.0063RHCI n =30, R2 =0.9820,s2 =F =173,final model where n is the number of compounds used for regression, R2 is the squared correlation coefficient, s2 is the standard error of the regression, and F is the Fisher ratio for the regression.Conclusion: The results indicate that the CMC decreases as the hydrophobic character (L and V) increases and CMC increases as the hydrophilic character (A) of the surfactant increases.