Score contribution per author:
α: calibrated so average coauthorship-adjusted count equals average raw count
The identification of the temporal scales related to market activities is crucial for understanding the dynamics of international crude oil prices. Standard analysis techniques fail in producing consistently good results due to the non-linear behaviour of the oil market. In this paper we propose an innovative approach based on the concurring application of a new non-linear data analysis method, Fast Iterative Filtering (FIF), and a multi-scale statistical analysis (Standardized Mean Test). This approach proves to be able to separate automatically crude oil price data into three components: a long term trend, an intermediate or middle period behaviour, and a transitory or short-run behaviour. The economic meaning of each component is clearly identified as: high frequency variations, caused by normal supply-demand disequilibrium; medium term fluctuations, driven by geopolitical, financial, and technological shocks; a low frequency trend reflecting the global business cycle. All these results make the proposed approach a more performing tool for analysing oil price data structure and dynamics. Such a method, if coupled with different prediction techniques (e.g., ARIMA, ARCH, etc., or ANN, SVM, etc.), can potentially show higher performance than existing hybrid models in forecasting crude oil prices.