تلفن: ۰۴۱۴۲۲۷۳۷۸۱
تلفن: ۰۹۲۱۶۴۲۶۳۸۴

دانلود رایگان مقاله یک رگرسیون بردار پشتیبانی ICA برای پیش بینی قیمت های نفت خام

عنوان فارسی: یک رگرسیون بردار پشتیبانی ICA برای پیش بینی قیمت های نفت خام
عنوان انگلیسی: An ICA-based support vector regression scheme for forecasting crude oil prices
تعداد صفحات مقاله انگلیسی : 9 تعداد صفحات ترجمه فارسی : ترجمه نشده
سال انتشار : 2016 نشریه : الزویر - Elsevier
فرمت مقاله انگلیسی : PDF کد محصول : E4684
محتوای فایل : PDF حجم فایل : Mb2
رشته های مرتبط با این مقاله: مهندسی نفت
گرایش های مرتبط با این مقاله: نفت خام
مجله: پیش بینی فنی و تغییر اجتماعی - Technological Forecasting & Social Change
دانشگاه: دانشکده بازرگانی، دانشگاه هوهی، چین
کلمات کلیدی: قیمت نفت خام، پیش بینی، تجزیه و تحلیل جزء مستقل، رگرسیون بردار پشتیبانی
برای سفارش ترجمه این مقاله با کیفیت عالی و در کوتاه ترین زمان ممکن توسط مترجمین مجرب سایت ایران عرضه؛ روی دکمه سبز رنگ کلیک نمایید.
چکیده

abstract

The fluctuations of crude oil prices affect the economic growth of importing and exporting countries as well as regional security and stability. The intrinsic complex features of oil prices and the uncertainty in economic policy pose challenge on the accurate forecasting of crude oil prices. This paper employs independent component analysis (ICA) to analyze crude oil prices which are decomposed into several independent components corresponding to different types of influential factors affecting oil price. We also propose a novel ICA-based support vector regression scheme, namely ICA-SVR2 , for forecasting crude oil prices. The ICA-SVR2 starts from the use of ICA to decompose oil price series into three independent components, which are respectively forecasted by SVR models. The forecasted independent components are then integrated together by developing a new SVR model with independent components as inputs for forecasting crude oil prices. Our experimental results show the usefulness of ICA in identifying the driving factors behind the fluctuations of crude oil prices. A comparative study between ICA-SVR2 and other two models shows that ICA-SVR2 is an effective tool in forecasting crude oil prices.

نتیجه گیری

4. Conclusions

This paper proposes to use ICA to analyze crude oil prices and develops an ICA-based SVR (ICA-SVR2 ) scheme for forecasting crude oil prices. ICA is helpful to identify the hidden factors behind the fluctuations of international crude oil prices. The proposed ICA-SVR2 model starts from the use of ICA to decompose four international oil price series into three independent components. Then we build three SVR models to forecast the three independent components, respectively. Based on the three independent components as well as the WTI crude oil price series, we construct one integrated SVR model to forecast crude oil prices. Our experimental results show that the integration of ICA with SVR can improve the forecasting accuracy of SVR significantly. Another advantage of ICA is that the independent components obtained may shed insights on understanding the driving forces behind crude oil prices.