Application of Agglomerative Hierarchical Clustering to Classification of Housing Units in Nigeria by Types of Construction Materials

Abstract

Housing and quality of houses can be categorized based on several criteria including cost of construction, quality of materials, construction quality, and location of building among others. In this paper, Agglomerative Hierarchical Clustering (AHC) technique is utilized to classify housing by the types of material used in their construction as well as their locations. Single Linkage and Ward's methods along with Analysis of Variance (ANOVA) were used for analysis. The result showed that three (3), four (4), and four (4) clusters were respectively formed for the roof, floor, and wall types of materials. Cluster membership was used to identify the locations of the clusters that were formed and the materials used at these locations with the help of the final cluster center. The Analysis of variance (ANOVA) which validated the results in this paper showed that cluster classification of the roof, floor and wall types in Nigeria by the Hierarchical Agglomerative Clustering method was good.