00000nam a22000004a 4500 UP-1685675941131510167 Buklod 20240229142243.0 m |o d | ta 240213s2023 xxu r |||| u|eng d DSTC rda eng LG 995 2023 S8 A58 Antonio, Czarinne Antoinette A. author Modified silhouette score for evaluating cluster solutions Czarinne Antoinette A. Antonio. c2023 Quezon City University of the Philippines 93 p. Thesis (M.S.) --University of the Philippines, Diliman. ABSTRACT The assessment of the quality of a clustering solution and the proper identification of the number of clusters to be used is crucial step in doing cluster analysis. A class of silhouette-based indices, as modification to the widely used silhouette index, is developed to measure cluster validity. The performance of the proposed indices is demonstrated via a simulation study and through the application to actual data sets. The results revealed that the use of the second and third nearest cluster in the computation instead of just the nearest neighboring cluster relative to an observation was advantageous in identifying the number of natural clusters as a viable choice in the cluster analysis. Any of the proposed indices were useful in the presence of noisy data and not well-separated clusters. Further, dimension reduction techniques employed in the calculation of the distance measures provided an added benefit when dealing with high-dimensional data. Cluster analysis. Cluster validation. Silhouette index. UP Monograph UPD DSTC LG 995 2023 S8 A58 Book