The study aimed was to determine the best nonlinear function describing the growth stages of the Japanese quail breed. To this aim, growth functions such as exponential, logistic, von Bertalanffy, Brody, and Gompertz were used as nonlinear functions is used in the description of the body weight- age relationship of male and female Japanese quails. The Multivariate Adaptive Regression Splines (MARS) data mining algorithm was applied to the individual growth parameters obtained from the determined as the best fit model, and the relationship between sex and growth parameters with it has been revealed. The study dataset was 1267 body weight-age records collected from the hatching to the 6th week of age of 181 Japanese quails consisting of 90 females and 91 males. Each model was applied separately for both males and females. Model fit criteria such as coefficient of determination (R2), adjusted coefficient of determination (R2adj), Akaike's information criterion (AIC), and Bayes information criterion (BIC) were used to evaluate the performances of the growth functions used individually. All the statistical analyses were made by the R package program. The growth curve models were ranked in the form of Logistic > Gompertz > von Bertalanffy > Brody > Exponential according to the goodness of fit criteria. The most suitable model among the non-linear models in terms of performance was logistic. When the relationship between the growth curve parameters and body weight of the logistic model was explained with the MARS algorithm, the goodness of fit criteria showed that the obtained MARS model showed reliable performance. In addition, Pearson’s correlation coefficient between real and estimated body weight was found quite strong for the MARS algorithm (r=0.935). The results showed that the MARS algorithm can be presented as a good reference for breeders to establish breed standards and selection strategies for Japanese quails in growth parameters for breeding purposes.