Discovery of Customer Communities – Evaluation Aspects
Jerzy Korczak , Maciej Pondel , Wiktor Sroka
AbstractIn the paper, a new multi-level hybrid method of community detection combining a density-based clustering with a label propagation method is evaluated and compared with the k-means benchmark and DBSCAN (Density-based spatial clustering of applications with noise). In spite of the sophisticated visualization methods, managers still usually find clustering results too difficult to evaluate and interpret. The article presents a set of key assessment measures that could be used to evaluate internal and external qualities of discovered clusters. The approach is validated on real life marketing database using advanced analytics platform, Upsaily.
|Publication size in sheets||0.7|
Ziemba Ewa (eds.): Information Technology for Management: Current Research and Future Directions, Lecture Notes in Business Information Processing, vol. 380, 2020, Springer, ISBN 9783030433529, , 264 p., DOI:10.1007/978-3-030-43353-6
Ziemba_E_Information_Technology.pdf / No licence information (file archived - login or check accessibility on faculty)
|Keywords in English||Clustering · Customer communities, Customer segmentation, Cluster evaluation, Marketing|
* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.