{"id":{"repo_id":"calpoly","oai_identifier":"oai:digitalcommons.calpoly.edu:theses-4997"},"canonical_url":"https://search.ndltd.org/etd/calpoly/oai:digitalcommons.calpoly.edu:theses-4997","repository":{"repo_id":"calpoly","name":"Cal Poly","base_url":"https://digitalcommons.calpoly.edu/do/oai/"},"display":{"title":"Determining k Clusters in K-means Clustering with the CRAB Algorithm","abstract":"Unsupervised clustering often faces the challenge of determining the correct number of clusters in the absence of a true target variable. Traditional methods such as the Elbow Method and the Silhouette Score can produce ambiguous results and rely on assumptions about cluster shape or separation. To address this, we created the Clustering Rivals and Buddies (CRAB) algorithm which evaluates clusters based on stability across multiple subsamples. CRAB uses pairwise classifications to identify points that consistently group together called “Buddies” and points that remain separated called “Rivals.” Applied with K-means, CRAB accurately recovers underlying cluster structures in both spherical and non-spherical datasets, even under varying sample sizes and variances. An accompanying R package implements CRAB with a tidy workflow and easy to follow syntax, making it accessible for research and educational use. By emphasizing stability, CRAB offers a robust alternative for selecting cluster numbers in datasets where traditional methods may fall short.","abstract_html":"Unsupervised clustering often faces the challenge of determining the correct number of clusters in the absence of a true target variable. Traditional methods such as the Elbow Method and the Silhouette Score can produce ambiguous results and rely on assumptions about cluster shape or separation. To address this, we created the Clustering Rivals and Buddies (CRAB) algorithm which evaluates clusters based on stability across multiple subsamples. CRAB uses pairwise classifications to identify points that consistently group together called “Buddies” and points that remain separated called “Rivals.” Applied with K-means, CRAB accurately recovers underlying cluster structures in both spherical and non-spherical datasets, even under varying sample sizes and variances. An accompanying R package implements CRAB with a tidy workflow and easy to follow syntax, making it accessible for research and educational use. By emphasizing stability, CRAB offers a robust alternative for selecting cluster numbers in datasets where traditional methods may fall short.","abstract_has_math":false,"creators":["Cabrera, Jasmine Kristine S"],"institution":null,"degree_name":"MS in Statistics","degree_level":null,"degree_discipline":"Statistics","degree_department":null,"school":null,"contributors":["Kelly Bodwin","Statistics","College of Science and Mathematics"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:12:58Z","subjects":["Clustering","Data Science","K-means"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.calpoly.edu/theses/3329","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.calpoly.edu/theses/3329","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.calpoly.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.calpoly.edu%3Atheses-4997","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Kelly Bodwin","Statistics","College of Science and Mathematics"]},{"key":"dc:creator","label":"Author","values":["Cabrera, Jasmine Kristine S"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2026-06-11T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2026-06-01T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Statistics"]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS in Statistics"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Clustering","Data Science","K-means"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.calpoly.edu/theses/3329"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Unsupervised clustering often faces the challenge of determining the correct number of clusters in the absence of a true target variable. Traditional methods such as the Elbow Method and the Silhouette Score can produce ambiguous results and rely on assumptions about cluster shape or separation. To address this, we created the Clustering Rivals and Buddies (CRAB) algorithm which evaluates clusters based on stability across multiple subsamples. CRAB uses pairwise classifications to identify points that consistently group together called “Buddies” and points that remain separated called “Rivals.” Applied with K-means, CRAB accurately recovers underlying cluster structures in both spherical and non-spherical datasets, even under varying sample sizes and variances. An accompanying R package implements CRAB with a tidy workflow and easy to follow syntax, making it accessible for research and educational use. By emphasizing stability, CRAB offers a robust alternative for selecting cluster numbers in datasets where traditional methods may fall short."]},{"key":"dc:title","label":"Title","values":["Determining k Clusters in K-means Clustering with the CRAB Algorithm"]}]}],"canonical_facts":{"dc:contributor":["Kelly Bodwin","Statistics","College of Science and Mathematics"],"dc:creator":["Cabrera, Jasmine Kristine S"],"dc:date.available":["2026-06-11T07:00:00Z"],"dc:date.created":["2026-06-01T07:00:00Z"],"dc:description.abstract":["Unsupervised clustering often faces the challenge of determining the correct number of clusters in the absence of a true target variable. Traditional methods such as the Elbow Method and the Silhouette Score can produce ambiguous results and rely on assumptions about cluster shape or separation. To address this, we created the Clustering Rivals and Buddies (CRAB) algorithm which evaluates clusters based on stability across multiple subsamples. CRAB uses pairwise classifications to identify points that consistently group together called “Buddies” and points that remain separated called “Rivals.” Applied with K-means, CRAB accurately recovers underlying cluster structures in both spherical and non-spherical datasets, even under varying sample sizes and variances. An accompanying R package implements CRAB with a tidy workflow and easy to follow syntax, making it accessible for research and educational use. By emphasizing stability, CRAB offers a robust alternative for selecting cluster numbers in datasets where traditional methods may fall short."],"dc:identifier":["https://digitalcommons.calpoly.edu/theses/3329"],"dc:subject":["Clustering","Data Science","K-means"],"dc:title":["Determining k Clusters in K-means Clustering with the CRAB Algorithm"],"thesis:degree_discipline":["Statistics"],"thesis:degree_name":["MS in Statistics"]},"updated_at":"2026-11-19T07:12:58Z"}