Bagging Approach for Increasing Classification Accuracy of CART on Family Participation Prediction in Implementation of Elderly Family Development Program

Abstract

Classification and Regression Tree (CART) was a method of Machine Learning where data exploration was done by decision tree technique. CART was a classification technique with binary recursive reconciliation algorithms where the sorting was performed on a group of data collected in a space called a node / node into two child nodes (Lewis, 2000). The aim of this study was to predict family participation in Elderly Family Development program based on family behavior in providing physical, mental, social care for the elderly. Family involvement accuracy using Bagging CART method was calculated based on 1-APER value, sensitivity, specificity, and G-Means. Based on CART method, classification accuracy was obtained 97,41% with Apparent Error Rate value 2,59%. The most important determinant of family behavior as a sorter was society participation (100,00000), medical examination (98,95988), providing nutritious food (68.60476), establishing communication (67,19877) and worship (57,36587). To improved the stability and accuracy of CART prediction, used CART Bootstrap Aggregating (Bagging) with 100% accuracy result. Bagging CART classifies a total of 590 families (84.77%) were appropriately classified into implement elderly Family Development program class. Keywords: Bagging Classification and Regression Tree, Classification Accuracy, Family Participation