A Multicriteria Clustering Approach Based on Similarity Indices and Clustering Ensemble Techniques

Abstract

This paper deals with the problem of multicriteria clusters construction. The aim is to propose a multicriteria clustering procedure aiming at discovering data structures from a multicriteria perspective by de¯ning a dissimilarity measure which takes into account the multicriteria nature of the problem. Comparing two objects in the multicriteria context is based on the preference information that expresses whether these objects are indi®erent, incomparable or one is preferred to the other. The proposed approach uses this preference information with an agreement-disagreement similarity index to compute a dissimilarity measure. The approach generates, according to the preference relations, a set of clusterings. Each clustering expresses a way of grouping objects according to the preference relation used. A good quality¯nal clustering is obtained by combining the clusterings generated previously using a clustering ensemble technique.

Multi-criteria clustering analysis for large-scale public transport performance diagnosis

“…An aggregation process of these partitions is then performed to produce the final optimal cluster. Following a similar strategy authors suggest in [40] the use of agreement-disagreement similarity index as distance measure for the clustering process and clustering ensemble technique to provide the final optimal partition. An other contribution in multi-criteria clustering by a meta-heuristic algorithm to cluster alternatives defined in terms of multiple incommensurable attributes on different types of scales [41].…”

“…It is possible to notice that ordered multi-criteria clustering methods can be divided in two categories according to their process. Some methods are based on a two-step process, the first one performs a classical clustering, and the second one allows to refine the final distribution [36], [37], [38], [39], [40] and [41]. The second category includes recent methods, those are based on an extension of the K-means algorithm by using outranking methods, notably the PROMETHEE method [42], [43], [44], [45] and [1].…”

A Stochastic Multi-criteria divisive hierarchical clustering algorithm

“…Then, Eppe et al (2014) valued the distance based on their outranking relation and proposed an adapted k-means algorithm to cluster the alternatives. On the same note, Rouba and Bahloul (2014) proposed several similarity indices between alternatives and used the k-medoids algorithm to cluster the alternatives instead.…”

Fuzzy Multi-Attribute Decision Making untuk Klasifikasi Potensi Kewirausahaan Berdasarkan Theory of Planned Behavior (Fuzzy Multi-Attribute Decision Making for Classifying Entrepreneurial Potential based on Theory of Planned Behavior)

“…Kombinasi teknik SAW, TOPSIS, dan GRA menghasilkan suatu model keputusan terbaik dengan cara meminimalkan pengaruh pengambil keputusan dalam memberikan bobot preferensi [15]. Teknik-teknik pengambilan keputusan dapat dikombinasikan dengan teknik data mining untuk tujuan yang lebih spesifik, seperti segmentasi pelanggan [16], analisis risiko keuangan [17], serta optimasi metode clustering [8], [18], [19]. Hasil analisis multikriteria kategori multiatribut adalah pemeringkatan yang berguna untuk menentukan skala potensi kewirausahaan mahasiswa.…”