Where academic tradition
meets the exciting future

You are here: TUCS > PUBLICATIONS > Publication Search > A Weighting FCM Algorithm for ...

A Weighting FCM Algorithm for Clusterization of Companies as to their Financial Performances

Francisco Augusto Alcaraz Garcia, Adrian Costea, A Weighting FCM Algorithm for Clusterization of Companies as to their Financial Performances. TUCS Technical Reports 591, Turku Centre for Computer Science, 2004.

Abstract:

We apply fuzzy logic to group telecommunication companies into different clusters as to their financial performances. The objective is to build an easy-to-use financial assessment tool that can assist decision makers in their investment planning and be applied regardless of the economic sector to be analyzed. We characterize each cluster in terms of profitability, liquidity, solvency and efficiency. We implement a modified fuzzy C-means (FCM) algorithm and compare the results with those of normal FCM and previously reported SOM clustering. The results show an improvement in pattern allocation with respect to normal FCM and SOM. The interpretation of the clusters is done automatically representing each ratio as a linguistic variable.

BibTeX entry:

@TECHREPORT{tAlCo04a,
  title = {A Weighting FCM Algorithm for Clusterization of Companies as to their Financial Performances},
  author = {Alcaraz Garcia, Francisco Augusto and Costea, Adrian},
  number = {591},
  series = {TUCS Technical Reports},
  publisher = {Turku Centre for Computer Science},
  year = {2004},
  keywords = {Clustering, Fuzzy c-Means, Linguistic Variables, Financial Performance},
  ISBN = {952-12-1308-6},
}

Belongs to TUCS Research Unit(s): Data Mining and Knowledge Management Laboratory

Edit publication