The paper presents CLIQUE, a clustering algorithm designed to address the challenges of clustering high-dimensional data. CLIQUE identifies dense clusters in subspaces of maximum dimensionality, generates cluster descriptions in the form of minimized DNF expressions for ease of comprehension, and produces identical results regardless of the order of input records. The algorithm is scalable and does not assume any specific distribution of the data. The authors demonstrate through experiments that CLIQUE efficiently finds accurate clusters in large, high-dimensional datasets. The paper also discusses related work and provides a detailed algorithmic description of CLIQUE, including steps for identifying subspaces containing clusters, finding clusters, and generating minimal cluster descriptions. The performance of CLIQUE is evaluated using synthetic and real datasets to assess its efficiency and accuracy.The paper presents CLIQUE, a clustering algorithm designed to address the challenges of clustering high-dimensional data. CLIQUE identifies dense clusters in subspaces of maximum dimensionality, generates cluster descriptions in the form of minimized DNF expressions for ease of comprehension, and produces identical results regardless of the order of input records. The algorithm is scalable and does not assume any specific distribution of the data. The authors demonstrate through experiments that CLIQUE efficiently finds accurate clusters in large, high-dimensional datasets. The paper also discusses related work and provides a detailed algorithmic description of CLIQUE, including steps for identifying subspaces containing clusters, finding clusters, and generating minimal cluster descriptions. The performance of CLIQUE is evaluated using synthetic and real datasets to assess its efficiency and accuracy.