Decision Tree Algorithms and their Applicability in Agriculture for Classification

Abstract

Machine learning approaches has the advantage that in most of machine leaning algorithms data transformation is unnecessary, can handle missing predictor variables, success of prediction is not dependent on data meeting normality conditions or covariance homogeneity, variable selection is intrinsic to the methodology and provides good accuracy over the traditional methods. The decision tree is one of such machine learning algorithms which is capable of handling both complete and incomplete data, so it can be applied in the field of agriculture where such data occurs frequently. The algorithms which were considered for this study includes ID3 (Iterative Dichotomizer 3), Classification and Regression Tree (CART) and C4.5. This paper provides a detailed approach on the development of decision tree using its various algorithms. It is anticipated that this study will be a layman guide to all agriculture researchers towards enhancing awareness of the potential advantages of using decision tree in agriculture, and contributing to its wide applicability in the agriculture data. The secondary data of cotton genotypes was used for classifying the genotypes into two classes, and hold out method was used for cross validation for checking the performance of the algorithms.