Ross 308 broiler chickens are raised specifically for meat production, as they are fast growing and can be slaughtered at six weeks of age. This study aimed to use multivariate adaptive regression splines (MARS) and classification and regression tree (CART) data mining algorithms to predict the live body weights of Ross 308 male and female chickens from their morphological traits, and to compare the predictive performances of these two approaches. One hundred and twenty birds (60 males and 60 females) were used. The flock was reared under intensive conditions, and the entire flock was kept in the same house. Body weight and morphological traits such as wing length, beak length, shank length, body girth, body length, and shank circumference were measured for every Ross 308 chicken. Two data mining algorithms, MARS and CART, were used for body weight prediction, and goodness-of-fit criteria were used to select the best model. The CART data mining algorithm was found to be the best model, as it had greater predictive accuracy, and higher Pearson’s correlation coefficient, coefficient of determination, and adjusted coefficient of determination test results, when predicting body weight in both male and female Ross 308 chickens. These results suggest that the CART data mining algorithm could be used to help farmers recognise the morphological traits that are most influential in determining body weight.