• TUCS Publication Series
• How to Publish in TUCS Series
• Publication Search
• Publication Graph
• Publication Input
• Publication Input Guide
• JuFo Browser

Making Economic-Financial Predictions using SOM and two Different Classification Techniques: Multinomial Logistic Regression and Decision Tree Induction

Adrian Costea, Tomas Eklund, Jonas Karlsson, Making Economic-Financial Predictions using SOM and two Different Classification Techniques: Multinomial Logistic Regression and Decision Tree Induction. In: Proceedings of Central & Eastern European Workshop on Efficiency and Productivity Analysis, Bucharest, Romania, June 28-29., 2002.

Abstract:

In this paper we apply the new methodology presented in our previous work. We have two goals: to validate our methodology and, using it, to gain insights in one relatively new and very sensitive industry: the telecommunications sector. We have obtained higher accuracy rates for the classification models than in the previous study, and smaller differences between training and test dataset accuracy rates. The two classification techniques have performed similarly in terms of accuracy rates (decision tree, slightly better) and class predictions (multinomial logistic regression, slightly more optimistic). We have analyzed the movements of Scandinavian telecommunications companies. The results are similar to Karlsson et al.’s (2001) findings and show a strong connectivity with what had really happened to Scandinavian telecommunication companies during the second part of the last decade.

BibTeX entry:

@INPROCEEDINGS{inpCoEkKa02a,
  title = {Making Economic-Financial Predictions using SOM and two Different Classification Techniques: Multinomial Logistic Regression and Decision Tree Induction},
  booktitle = {Proceedings of Central & Eastern European Workshop on Efficiency and Productivity Analysis, Bucharest, Romania, June 28-29.},
  author = {Costea, Adrian and Eklund, Tomas and Karlsson, Jonas},
  year = {2002},
}

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

Edit publication