ANALYZING DISTRIBUTION WITH SELF-ORGANIZING MAPS

The purpose of this paper is to illustrate how a self-organizing map, a specific type of neural network, can be used in distribution analysis. A self-organizing map is a clustering, visualization and abstraction method the ideas of which is to show the data set in another, more usable, representation form. Therefore, it is a usable method for data analysis and we anticipate that it might also assist in distribution analysis. In this paper, we analyze the profitability of a company's shipments. As a result, we found that a self-organizing map can simplify the analysis, since we concentrate on groups instead of single shipments. Furthermore, it shows how the profitability factors vary by customers or deliveries.

• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/isbn/0080435904
• Corporate Authors:

  Elsevier

  The Boulevard, Langford Lane
  Kidlington, Oxford  United Kingdom  OX5 1GB
• Authors:
  • Wilppu, E
• Conference:
  • World Transport Research: Selected Proceedings of the 8th World Conference on Transport Research
  • Location: Antwerp, Belgium
  • Date: 1998-7-12 to 1998-7-17
• Publication Date: 1999

Language

• English

Media Info

• Features: Figures; References; Tables;
• Pagination: p. 679-692

Subject/Index Terms

• TRT Terms: Abstracts; Analysis; Cluster analysis; Data collection; Distributed processing; Maps; Organizations; Self evaluation; Shipments; Visual media
• Subject Areas: Freight Transportation; Highways; Operations and Traffic Management;

Filing Info

• Accession Number: 00784061
• Record Type: Publication
• ISBN: 0080435904
• Report/Paper Numbers: Volume 3
• Files: TRIS
• Created Date: Feb 17 2000 12:00AM