Performance measure of breast cancer prediction using decision tree approach

Abstract

This paper investigations choice tree calculation for Breast disease discovery. The effectiveness of choice tree calculation can be broke down dependent on their precision and the quality choice measure utilized. The paper likewise gives a thought of the trait choice measure utilized by different choice tree calculation utilizes data gain and GINI Index as the quality choice measure. In this paper, the expectation of Decision Tree characterization is evaluated using two property trait choice decision measures for Breast Cancer sickness dataset. Choice tree uses separate and vanquish framework for the fundamental learning technique. From the result examination we can reason that the execution of Decision Tree grouping relies upon the trademark quality choice decision measures. Choice Tree is significant since improvement of decision tree classifiers doesn't need any territory learning. The essential objective is to produce a capable assumption show for Breast Cancer sickness expectation returns with high precision.