Using the Self-Organizing Map as a Visualization Tool in Financial Benchmarking

Abstract

In this paper, we illustrate the use of the self-organizing map technique for financial performance analysis and benchmarking. We build a database of financial ratios indicating the performance of 91 international pulp and paper companies for the time period 1995–2001. We then use the self-organizing map technique to analyze and benchmark the performance of the five largest pulp and paper companies in the world. The results of the study indicate that by using the self-organizing maps, we are able to structure, analyze, and visualize large amounts of multidimensional financial data in a meaningful manner.

The language of quarterly reports as an indicator of change in the company’s financial status

“…The SOM has been used in a variety of economic and financial applications; for example, economic welfare and poverty distribution [8], economic environment analysis [14,15], bankruptcy prediction [1,10,19,20], credit rating [23] and financial benchmarking [2,6]. Back et al [3] and Kloptchenko et al [11] also explored the possibility of combining SOMs and text mining techniques in order to extract qualitative information from annual or quarterly reports.…”

Combining visual customer segmentation and response modeling

“…Previously, trajectories have been a common means to illustrate temporal movements of individual data records on the SOM grid (see e.g., Eklund, Back, Vanharanta and Visa, 2003;Sarlin and Marghescu, 2011). The use of trajectories suffers, however, from the deficiency that they can only be used on a limited set of data in order not to clutter the display, and give no indications of overall patterns and their strengths.…”

Customer portfolio analysis using the SOM

“…For example, the SOM has been used for financial benchmarking (Back et al 1998;Eklund et al 2003), macro-economic analysis (Kaski and Kohonen 1996;Länsiluoto 2007) , and bankruptcy prediction (Back et al 1995;Kiviluoto 1998;Martín-del-Brío and Serrano-Cinca 1993) . However, regardless of its obvious benefits, the SOM has not been widely applied in customer segmentation tasks.…”