Segmenting Markets by Bagged Clustering

Abstract

We introduce bagged clustering as a new approach in the field of post hoc market segmentation research and illustrate the managerial advantages over both hierarchical and partitioning algorithms, especially with large binary data sets. The most important improvements are enhanced stability and interpretability of segments based on binary data. One of the main goals of the procedure is to complement more traditional techniques as an exploratory segment analysis tool. The merits of the approach are illustrated using a tourism marketing application. Segmenting Markets by Bagged ClusteringWe introduce bagged clustering as a new approach in the field of post hoc market segmentation research and illustrate the managerial advantages over both hierarchical and partitioning algorithms, especially with large binary data sets. The most important improvements are enhanced stability and interpretability of segments based on binary data. One of the main goals of the procedure is to complement more traditional techniques as an exploratory segment analysis tool. The merits of the approach are illustrated using a tourism marketing application.

Bagged fuzzy clustering for fuzzy data: An application to a tourism market

“…Then, the "correct" solution is obtained by combining the solutions of the partition method into a new data set on which a hierarchical method is applied [12]. For more technical information regarding this algorithm see [12,92,93].…”

“…In particular, as stated in section 1, k-means algorithm suffers of many disadvantages that the BC method overcomes [12,92,93]. Firstly, the BC is more stable than the k-means since it depends less on the starting solution; secondly, the final number of clusters is obtained at the end of the entire procedure and the starting value of C does not affect the result; thirdly, the BC method is able to discover the niche segments.…”

Tourism and discretionary income allocation. Heterogeneity among households

“…The bagged clustering procedure offers many advantages over more traditional data-driven segmentation methods such as single employment of k-means clustering. Bagged clustering results are less dependent on the starting solution as several independent computations form the basis of the final segmentation; they are more stable than classic clustering algorithms due to the inherent replication process; they are less dependent on the data set at hand as numerous bootstrap samples are used as starting points for the repeated calculations; and niche segments can be identified more easily than with classical algorithms like k-means, which tend to produce segments of equal size (Leisch, 1999;Dolnicar and Leisch, 2004). Bagged clustering has been used successfully for tourism market segmentation in the past (Dolnicar and Leisch, 2000;Dolnicar and Leisch, 2003) The fundamental logic behind bagged clustering is to increase the stability of the final result by computing repeated runs of the partition and combining the results into a final segmentation solution.…”

Bagged Clustering and its application to tourism market segmentation

“…Since the introduction of market segmentation in the late 1950s, the number and type of approaches for segmentation has grown enormously (Dolnicar & Leisch, 2004;Liao et al, 2012). Boone & Roehm (2002) pointed out that there are over 50 methods that can be applied to deal with market segmentation problems.…”

“…More recently, the Bagged Clustering (BC) algorithm, based on the Bagging ("bootstrap aggregating") procedure (Breiman, 1996), has been introduced in the tourism market segmentation (Dolnicar & Leisch, 2000, 2004Leisch, 1999).…”