The aim of the study was to apply various data mining techniques to determine coat colour and live weight of Kars shepherd dog. C5.0, MARS (Multivariate Adaptive Regression Splines) and Bagging MARS (Bootstrap Aggregating Multivariate Adaptive Regression Splines) were used in the study. The coat colours were pied, black, brown, white and Roan. The age range of the 52 shepherd dogs were between 2 and 8. Morphological characteristics were live weight (LW), withers height (WH), rump height (RH), body length (BL), chest circumference (CC), chest depth (CD) and front shinbone length (FSL). Verification rate of C5.0 algorithm to determine the coat of the dog was found 71.2%. R2 (determination coefficient), Adjust R2, Root-mean-square error (RMSE), Standard deviation ratio (SDratio), Mean absolute percentage error (MAPE) and Akaike Information Criteria (AIC) values of MARS algorithm estimating live weight were as follows: 0.845, 0.828, 2.893, 0.393, 5.047 and 122 respectively. Same statistics for Bagging MARS algorithm were 0.893, 0.881, 2.4, 0.326, 4.158 and 101 respectively. It was observed that data mining methods have revealed correct results according to goodness of fit statistics.