FORECASTING VOLATILITY IN OIL PRICES WITH ARCH/GARCH MODELS AND ARTIFICIAL NEURAL NETWORK ALGORTIHMS

Abstract

In this study, we analyze volatility in crude oil prices using ARCH-GARCH models and Artificial Neural Network ANN over the time periods from January 02, 2008 to October 23, 2017. To investigate the relationship, financial variables included in the model such as the DJIA and FTSE stock market indexes, EUR/USD and Yen/USD exchange rates. According to the artificial neural network results, the most important effect on oil price comes from volatility of DJIA and FTSE stock market indexes. Artificial Neural network evidence shows that the R-square coefficient is 87% for the sample period

Keywords

• volatility
• oil prices
• artificial neural networks
• GARCH models

PETROL FİYATLARINDAKİ OYNAKLIĞIN ARCH/GARCH MODELLERİ VE YAPAY SİNİR AĞLARI ALGORİTMASI İLE TAHMİNİ

Öz

Bu çalışmada Otoregresif Koşullu Değişen Varyans ARCH modeli, Genelleştirilmiş Otoregresif Koşullu Değişen Varyans GARCH modeli ve yapay sinir ağları algoritması kullanılarak petrol fiyatlarındaki oynaklık 2 Ocak 2008 ve 23 Ekim 2017 dönemi esas alınarak tahmin edilmiştir. Modelde finansal değişkenler olarak Dow Jones endeksi, FTSE endeksi, EUR/USD, Yen/USD döviz kurları kullanılmıştır. Yapay sinir algoritması ile petrol fiyatları getiri serisinin oynaklık değerleri tahmin edilmesinin yanı sıra hangi değişkenin bu oynaklık değerleri üzerinde en çok etkiye sahip olduğu önem analizi yardımıyla belirlenmiştir. Tahmin edilen yapay sinir ağları sonuçlarına göre R2 değeri %87 bulunurken, petrol fiyatına en fazla etki eden değişkenler Dow Jones ve FTSE endeksleri olmuştur.

Anahtar Kelimeler

• oynaklık
• petrol fiyatları
• yapay sinir ağları
• GARCH modelleri

Kaynakça

1. Aloui, C., & Mabrouk, S. (2010). Value-at-risk estimations of energy commodities via long-memory, asymmetry and fat-tailed GARCH models. Energy Policy, 38(5), 2326-2339.
2. Alvarez-Ramirez, J., Soriano, A., Cisneros, M., & Suarez, R. (2003). Symmetry/anti-symmetry phase transitions in crude oil markets. Physica A: Statistical Mechanics and its Applications, 322, 583-596.
3. Arouri, M. E. H., Jouini, J., & Nguyen, D. K. (2011). Volatility spillovers between oil prices and stock sector returns: Implications for portfolio management. Journal of International money and finance, 30(7), 1387- 1405.
4. Azadeh, A., Moghaddam, M., Khakzad, M., & Ebrahimipour, V. (2012). A flexible neural network-fuzzy mathematical forecasting. Computers & Industrial Engineering, 62(2), 421-430. algorithm for improvement of oil price estimation and
5. Bildirici, M., & Ersin, Ö. Ö. (2009). Improving forecasts of GARCH family models with the artificial neural networks: An application to the daily returns in Istanbul Stock Exchange. Expert Systems with Applications, 36(4), 7355-7362.
6. Bildirici, M., & Ersin, Ö. Ö. (2013). Forecasting oil prices: Smooth transition and neural network augmented GARCH family models. Journal of Petroleum Science and Engineering, 109, 230-240.
7. Charles, A., & Darné, O. (2017). Forecasting crude-oil market volatility: Further evidence with jumps. Energy Economics, 67, 508-519.
8. Cheong, C. W. (2009). Modeling and forecasting crude oil markets using ARCH-type models. Energy policy, 37(6), 2346-2355.

9. Dhamija, A. K., & Bhalla, V. K. (2010). Financial time series forecasting: comparison of neural networks and ARCH models. International Research Journal of Finance and Economics, 49, 185-202.
10. Donaldson, R. G., & Kamstra, M. (1997). An artificial neural network-GARCH model for international stock return volatility. Journal of Empirical Finance, 4(1), 17-46. EIA. (2017). International energy outlook 2017. Erişim Tarihi: 24.08.2017, https://www.eia.gov/outlooks/ieo/pdf/0484(2017).pdf
11. Engle, R. F. (1982). Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation. Econometrica: Journal of the Econometric Society, 987-1007.
12. Godarzi, A. A., Amiri, R. M., Talaei, A., & Jamasb, T. (2014). Predicting oil price movements: A dynamic Artificial Neural Network approach. Energy Policy, 68, 371-382.
13. Hajizadeh, E., Seifi, A., Zarandi, M. F., & Turksen, I. B. (2012). A hybrid modeling approach for forecasting the volatility of S&P 500 index return. Expert Systems with Applications, 39(1), 431-436.
14. Hou, A., & Suardi, S. (2012). A nonparametric GARCH model of crude oil price return volatility. Energy Economics, 34(2), 618-626.
15. Liu, L., & Wan, J. (2012). A study of Shanghai fuel oil futures price volatility based on high frequency data: Long-range dependence, modeling and forecasting. Economic Modelling, 29(6), 2245-2253.
16. Mohammadi, H., & Su, L. (2010). International evidence on crude oil price dynamics: Applications of ARIMA- GARCH models. Energy Economics, 32(5), 1001-1008.
17. Monfared, S. A., & Enke, D. (2014). Volatility forecasting using a hybrid GJR-GARCH neural network model. Procedia Computer Science, 36, 246-253.
18. Narayan, P. K., & Narayan, S. (2007). Modelling oil price volatility. Energy Policy, 35(12), 6549-6553.
19. Özden, Ü. H. (2008). İMKB bileşik 100 endeksi getiri volatilitesinin analizi. İstanbul Ticaret Üniversitesi Sosyal Bilimler Dergisi, 13(7),339-350.
20. Sadorsky, P. (2006). Modeling and forecasting petroleum futures volatility. Energy Economics, 28(4), 467-488.
21. Vejendla, A., & Enke, D. (2013a). Evaluation of GARCH, RNN and FNN models for forecasting volatility in the financial markets. IUP Journal of Financial Risk management, 10(1), 41.
22. Vejendla, A., & Enke, D. (2013b). Performance evaluation of neural networks and GARCH models for forecasting volatility and option strike prices in a bull call spread strategy. Journal of Economic Policy and Research, 8(2), 1.
23. Yu & Lai Shouyang (2007). Foreign-exchange-rate forecasting with artificial neural network. Springer Publisher.
24. Wang, Y. H. (2009). Nonlinear neural network forecasting model for stock index option price: Hybrid GJR– GARCH approach. Expert Systems with Applications, 36(1), 564-570.
25. Wang, Y., & Wu, C. (2012). Forecasting energy market volatility using GARCH models: Can multivariate models beat univariate models?. Energy Economics, 34(6), 2167-2181.
26. Wei, Y., Wang, Y., & Huang, D. (2010). Forecasting crude oil market volatility: Further evidence using GARCH-class models. Energy Economics, 32(6), 1477-1484.