Comparative of ID3 and Naive Bayes in Predictid Indicators of House Worthiness

Abstract

Decision making is method of solving problems using certain way / techniques so that can be accepted. After making some calculations and considerations through several stages, the decision have taken that decision maker goes through. This stage will be selected until the best decision has made. Decision-making aims to solve problems that solve problems so that decisions with final goals can be implemented properly and effectively. This study uses a simulation of decision making from seven attributes to the proportion of the feasibility of a house based on data from Central Statistics Agency (BPS). There are several techniques for presenting decision making including: ID3 (decision tree) algorithm concept and Naive Bayes algorithm. Both classification are learning-supervised data grouping. ID3 algorithm depicts the relationship in the form of a tree diagram whereas Naive Bayes makes use of probability calculations and statistics. As a result, in data training, decision trees are able to model decision making more accurately. The prediction results using the decision tree model = 90.90%, while Naive Bayes = 72.73%. Meanwhile, the speed of the Naive Bayes algorithm is better