Cluster Quality Analysis Using Silhouette Score

By Ketan Rajshekhar Shahapure, Charles K. Nicholas. International Conference on Data Science and Advanced Analytics, 2020

854 citations recorded by the source corpus.

Clustering is an important phase in data mining. Selecting the number of clusters in a clustering algorithm, e.g. choosing the best value of k in the various k-means algorithms [1], can be difficult. We studied the use of silhouette scores and scatter plots to suggest, and then validate, the number of clusters we specified in running the k-means clustering algorithm on two publicly available data sets. Scikit-learn's [4] silhouette score method, which is a measure of the quality of a cluster, was used to find the mean silhouette co-efficient of all the samples for different number of clusters. The highest silhouette score indicates the optimal number of clusters. We present several instances of utilizing the silhouette score to determine the best value of k for those data sets.

Subfields: Artificial Intelligence, Information Systems, Signal Processing

View Paper: https://www.semanticscholar.org/paper/f6e1d5c336d15ebc1907d7f28fc2c82419bf9bb7

Citations in the corpus

• Bridging verbal coordination and neural dynamics (2025, unknown): “Precisely, we used the silhouette score method on the k-means result (Rousseeuw, 1987; Shahapure & Nicholas, 2020).”
• Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval (2024, unknown): “To determine the optimal clustering thresholds θ e and θ r for entities and relations, we refer to the silhouette score (Shahapure & Nicholas, 2020; Jiang et al., 2024b), which considers both intra-cluster similarity and inter-cluster dissimilarity.”