Dea Supported Ann Approach to Operational Efficiency Assessment of Smes

Hidayet Talha Kus, Enis Bulak, Ali Turkyilmaz and Zbigniew Pastuszak
Additional contact information
Hidayet Talha Kus: Istanbul University, Turkey
Enis Bulak: Istanbul University, Turkey
Ali Turkyilmaz: Nazarbayev University, Kazakhstan
Zbigniew Pastuszak: Maria Curie-Sklodowska University, Poland

from ToKnowPress

Abstract: This study addresses to classify Turkish Small Medium Enterprises (SMEs) in terms of their efficiency scores by developing a DEA supported Neural Network classification model. For this purpose, 744 manufacturing companies from ten different industries are taken into consideration. First, by considering the input and output values of the firms, efficiency scores of the companies are calculated with Data Envelopment Analysis (DEA). Then, to perform the Artificial Neural Network (ANN) classification analysis, same inputs variables are used while the efficiency scores from the DEA model are used as target values. This DEA supported ANN model provides a powerful efficiency estimation of SMEs with 96.4% performance efficiency when their output measures (i.e. market share, profit margin etc.) are not available.

Keywords: operational efficiency; DEA; neural network; classification; SMEs (search for similar items in EconPapers)
Date: 2017
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.toknowpress.net/ISBN/978-961-6914-21-5/papers/ML17-144.pdf full text (application/pdf)
http://www.toknowpress.net/ISBN/978-961-6914-21-5/MakeLearn2017.pdf Conference Programme (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:tkp:mklp17:605-612

Access Statistics for this chapter

More chapters in Management Challenges in a Network Economy: Proceedings of the MakeLearn and TIIM International Conference 2017 from ToKnowPress
Bibliographic data for series maintained by Miha Jezovnik ().