<![CDATA[Analysis of Naive Bayes Classification Model of Livable Housing Model Based on Physical Characteristics is one of the crucial aspects in improving the quality of life and welfare of the community. This study aims to examine the application of the Naive Bayes classification method in determining the level of livability based on the physical characteristics of the building. The dataset used is house data that includes several variables, namely roof condition (good, damaged), wall type (wall, semi-permanent, wood), floor condition (ceramic, cement, soil), building area (<36 m², ≥36 m²), ventilation (adequate, inadequate), and sanitation access (adequate, inadequate). The target variable in this study is the housing category, namely livable and uninhabitable. The research stages include data collection, data preprocessing, dividing the dataset into training data and test data, and implementation of the Naive Bayes algorithm. The posterior probability calculation is carried out based on the probability distribution of each variable against the class with a maximum likelihood approach. Model performance evaluation is carried out using a confusion matrix with indicators of accuracy, precision, and recall. The results of the analysis show that the variables of floor condition and sanitation access have the highest probability value against the livable category, thus playing a dominant role in the classification process. Furthermore, these two variables were also shown to have the most significant influence in determining whether housing is habitable or uninhabitable.]]>
