Prediction of body weight from morphological traits of South African non-descript indigenous goats of Lepelle-Nkumbi Local Municipality using different data mining algorithm.

Body weight is a vital trait which can assist farmers on selecting animals to use during breeding season. Therefore, the study was conducted to develop the best model to predict body weight from morphological traits through classification and regression tree (CART) and chi-square automatic interaction detector (CHAID) and to determine the relationship between body weight and some morphological traits. A total of 700 South African non-descript indigenous goats (female = 417 and male = 283) between the age of 1 and 5 years old were used in the study. Body weight and some morphological traits viz. body length (BL), heart girth (HG), withers height (WH), rump height (RH), and rump length (RL) were measured in the study. CART, CHAID, and Pearson's correlation were used for data analysis. CART and CHAID algorithms indicated that predictor factors such as BL, HG, age, and villages had statistical influence on body weight of goats. The study suggests that BL can be used to estimate body weight of South African non-descript indigenous goats. Goodness of fit test suggests that CHAID is a suitable algorithm for prediction of body weight of South African non-descript indigenous goats. Correlation findings indicated that BW had positive highly statistical correlation (P < 0.01) with BL in male and female goats with correlation values of r = 0.65 and r = 0.65, respectively. Findings suggest that improving BL of South African non-descript indigenous goats might improve body weight.