Detection of Calving interval trait using decision tree and support vector machine methods in Holstein dairy cows

Decreased reproductive traits in cows are a major problem in raising dairy cows. There has been a negative relationship between milk production and reproductive performance in different breeds of dairy cows. By focusing on reproductive traits such as calving interval, production in later generations will be improved. Because calving interval is one of the factors that indicate the efficiency and adequacy of reproduction. Using intellectual algorithms of machine learning methods to investigate complex systems are growing and these algorithms could be assumed as right approach to analysis dairy cattle industry data. In the present work, was carried out to investigate the possibility of calving interval classification in Holstein dairy cattle using two methods of decision tree (algorithms of j48, random forest and Naive Bayes) and support vector machine. Were used accuracy and root mean square error to investigate the efficiency of methods. The results of this study showed that decision tree methods (j48) have a higher performance than support vector machine in classification of as calving interval. Calving age and milk production showed high amount of correlation with calving interval. The present work is the first study to detection of calving interval using decision tree and support vector machine methods that may provide information to greater understanding on calving interval management. Tree models don’t require the establishment of no default for making model and feasibility of tree models results interpretation are two essential beneficiary of these models which for this reason seem to be useful for bovine breeding researches.