Acta Univ. Agric. Silvic. Mendelianae Brun. 2011, 59(2), 149-154 | DOI: 10.11118/actaun201159020149
Evolution of insurance company service quality survey, using self-learning neural network
- Ústav informatiky, Mendelova univerzita v Brně, Zemědělská 1, 613 00 Brno, Česká republika
The objective of the paper is to demonstrate the abilities and possible approaches to classification of set of objects using self-organizing maps. As the objects, clients of an insurance company that made an agreement regarding mandatory insurance of motor vehicles were selected. The opinions of the clients and their overall satisfaction reflected in responses to presented answers.
The clients were classified into three groups. The first two contained satisfied clients (i.e. good clients for the company), the last group contained clients that could potentially switch to the competitors. Subsequent analysis enabled discovering the reasons of low customer satisfaction and critical factors of losing the least satisfied clients.
For the analysis of the responses (one hundred fifty-one) and the insurance company, experimental model of self-organizing map realized at the Department of informatics was used. Used experimental model has proved very effective software tool.
Keywords: insurance company, neural network, self-learning, classification, class representative, plane projection
Received: December 17, 2010; Published: July 7, 2014 Show citation
ACS | AIP | APA | ASA | Harvard | Chicago | IEEE | ISO690 | MLA | NLM | Turabian | Vancouver |
References
- KONEČNÝ, V., TRENZ, O., 2009a: Rozhodování s podporou umělé inteligence. Folia Mendelovy zemědělské a lesnické univerzity v Brně, Folia II, 2009, 8, ISSN 1803-2109, ISBN 978-80-7375-344-3.
- KONEČNÝ, V., TRENZ, O., 2009b: Classification of Companies with Assistance of Self-Learning Neural Network. Agricultural Economics. ISSN 0139-570X.
- KOHONEN, T., 2001: Self-Organizing Maps. 3rd edition, Springer Verlag Berlin. ISBN 3-540-67921-9.
Go to original source...
This is an open access article distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY NC ND 4.0), which permits non-comercial use, distribution, and reproduction in any medium, provided the original publication is properly cited. No use, distribution or reproduction is permitted which does not comply with these terms.