全球散裝航運市場中,不同船型市場運價變化有明顯差異。海岬型船主要承運鐵礦砂與煤礦運務為主,不但具有貨物屬性特殊與貨源集中之特性,而且運價波動風險最大,市場經營相當不容易。因此如何掌握市場運價之變化,實乃經營海岬型船之關鍵所在。本文假設在全球政經環境無顯著變動情況下,採用灰色理論之灰預測GM(1, 1)滾動檢驗建模方式,針對波羅地海海岬型船指數(BCI)不同期間,以不同樣本數進行BCI指數檢驗顯示,採用四點建模方式精確度最高。本文進行BCI指數預測,除藉由指數平滑法與之比較,進一步探討預測精確度之外,又以絕對百分比誤差(MAPE)與均方差(MSE)檢驗其精確度。以預測績效而言,灰預測高於指數平滑法,且較不受指數波動幅度之影響。研究結果可依悲觀與樂觀期望程度與個人不同之風險偏好,提供船東或傭船人制定傭船決策之參考。
In the global bulk shipping market, there are obvious differences in freight rates and charter hires among different vessel types. Capesize vessels are mainly used to transport iron ore and coal shipments. In addition, Capesize vessels have the characteristics of owning specific cargo attributes, concentration of cargo sources and the highest fluctuations of freight rates and charter hires; therefore it is difficult to operate in the Capsize market sector. Consequently, the key factor in operating Capsize vessels is to forecast the fluctuations in freight rates and charter hires. In this research, under the hypothesis of globally political and economic environment remaining generally unchanged, we adopted the GM (1, 1) model of the grey theory with rolling check to forecast the Baltic Capesize Index (BCI) in different periods with different sample sizes. It is found that the four-point model performs the most accurate predictions. We also used exponential smoothing to technique conduct a more profound analysis in the accuracy of the forecasts and examined the accuracy by applying both the mean absolute percentage error (MAPE) and the mean square error (MSE). Finally, in terms of the performance of the forecasts, the Grey model is better than the exponential smoothing method because it would not be affected by fluctuations of BCI. Depending upon the pessimistic or optimistic degree of expectation and the difference of managers' risk preferences, the results of this research can contribute as a good reference in developing operational chartering strategies for shipowners and charterers.