Forecasting the Baltic Dry Index by using an artificial neural network approach

Şahin B., Gürgen S., Ünver B., Altın İ.

TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES, cilt.26, ss.1673-1684, 2018 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 26
  • Basım Tarihi: 2018
  • Doi Numarası: 10.3906/elk-1706-155
  • Dergi Adı: TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, TR DİZİN (ULAKBİM)
  • Sayfa Sayıları: ss.1673-1684
  • Anahtar Kelimeler: Baltic Dry Index, forecasting, artificial neural network, crude oil, shipping industry, EMPIRICAL MODE DECOMPOSITION, CARGO FREIGHT RATES, TIME-SERIES, MARKET, PRICE, ELECTRICITY, TURKEY, ANN
  • Karadeniz Teknik Üniversitesi Adresli: Evet

Özet

The Baltic Dry Index (BDI) is a robust indicator in the shipping sector in terms of global economic activities, future world trade, transport capacity, freight rates, ship demand, ship orders, etc. It is hard to forecast the BDI because of its high volatility and complexity. This paper proposes an artificial neural network (ANN) approach for BDI forecasting. Data from January 2010 to December 2016 are used to forecast the BDI. Three different ANN models are developed: (i) the past weekly observation of the BDI, (ii) the past two weekly observations of the BDI, and (iii) the past weekly observation of the BDI with crude oil price. While the performance parameters of these three models are close to each other, the most consistent model is found to be the second one. Results show that the ANN approach is a significant method for modeling and forecasting the BDI and proving its applicability.