Evaluation of Naive Bayes and Chi-Square performance for Classification of Occupancy House

Abstract

Occupancy status is one indicator of the rehabilitation and reconstruction program to support eruption victims in Indonesia. It needs to establish the rehabilitation and reconstruction in digital system with structured database. In this paper, we provide dataset 2,146 occupied and 370 unoccupied houses. We utilize a naive Bayes classifier to classify the objects and implement a chi-square algorithm to measure comparison data to actual observed data. This research uses a combination of Naive Bayes and Chi-Square by applying weighting to the dataset attributes. Our study conclude that the combination of the algorithms can achieve a promosing result in classifying the occupancy houses status. The combination of the proposed technique gain 89.59% accuracy and ROC-AUC value 0.839. Therefore, our approach is better than the standard Naive Bayes without combination with the Chi-Square approach