An Analysis of Turkey's Energy Efficiency with Artificial Neural Networks and ARDL Approach

ÇAM S. , SİGEZE Ç. , Balli E.

EGE ACADEMIC REVIEW, vol.18, no.4, pp.661-670, 2018 (Journal Indexed in ESCI) identifier

  • Publication Type: Article / Article
  • Volume: 18 Issue: 4
  • Publication Date: 2018
  • Doi Number: 10.21121/eab.2018442994
  • Title of Journal : EGE ACADEMIC REVIEW
  • Page Numbers: pp.661-670


This study investigates Turkey's energy efficiency for the period of 1960-2013 utilizing the ARDL (Autoregressive Distributed Lag) in the context of TOPSIS (Technique for Order Preference by Similarity to the Ideal Solution) and Artificial Neural Networks algorithm. In the first stage of the analysis, energy efficiency scores obtained via TOPSIS, then efficiency scores employed as output for the Artificial Neural Networks. Finally, ARDL utilized to estimate the coefficients of the variables both in the short and the long run. The empirical results depict that Turkey's energy efficiency tends to increase over the years. Besides, according to Artificial Neural Networks results, the most important variable determining energy efficiency is found to be per capita capital stock.