Demir Cevheri Fiyatlarının Modellenmesi ve Tahmini
No Thumbnail Available
Date
2024
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Open Access Color
OpenAIRE Downloads
OpenAIRE Views
Abstract
Çalışmada demir cevheri fiyatlarını etkileyen faktörler analiz edilmiştir ve demir cevheri tek değişken olarak kullanılarak haftalık fiyat tahmin modelleri oluşturulmuştur. Fiyatlar, ETS, ARIMA, XGBoosting modelleri ve bu modellerin kombine edilmesi ile elde edilen melez bir model (forecast combination) kullanılmıştır. Model parametrelerinin tahminleri, model çıktıları ve öngörüleri R programı kullanılarak elde edilmiştir. Çalışma sonunda kullanılan modeller karşılaştırılmış ve model başarıları tartışılmıştır. Çalışmanın sonuçları incelendiğinde kukla değişkenler kullanılarak çalıştırılan XGBoosting modeli diğer modellere nazaran daha güçlü sonuçlar sunmuştur. Anahtar Kelimeler: Demir cevheri, Fiyat tahmini, Tahmin modelleri, ETS, ARIMA, XGBoosting
In this study, the factors affecting iron ore prices are analyzed, and price forecasting models are developed using iron ore as a univariate time series. For forecasting, ETS, ARIMA, XGBoosting, and a hybrid model combining these approaches are utilized. All models are constructed and implemented within the R environment, and their outputs are derived through R. At the end of the study, the models are compared, and their predictive performances are critically evaluated. The XGBoosting model has delivered stronger results compared to the other models. Keywords: Iron ore, Price forecasting, Forecasting models, ETS, ARIMA, XGBoosting
In this study, the factors affecting iron ore prices are analyzed, and price forecasting models are developed using iron ore as a univariate time series. For forecasting, ETS, ARIMA, XGBoosting, and a hybrid model combining these approaches are utilized. All models are constructed and implemented within the R environment, and their outputs are derived through R. At the end of the study, the models are compared, and their predictive performances are critically evaluated. The XGBoosting model has delivered stronger results compared to the other models. Keywords: Iron ore, Price forecasting, Forecasting models, ETS, ARIMA, XGBoosting
Description
Keywords
Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrol, Ekonometri, İnşaat Mühendisliği, Computer Engineering and Computer Science and Control, Econometrics, Civil Engineering
Turkish CoHE Thesis Center URL
Fields of Science
Citation
WoS Q
Scopus Q
Source
Volume
Issue
Start Page
End Page
63
Collections
Google Scholar™
Sustainable Development Goals
2
ZERO HUNGER

4
QUALITY EDUCATION

6
CLEAN WATER AND SANITATION

8
DECENT WORK AND ECONOMIC GROWTH

9
INDUSTRY, INNOVATION AND INFRASTRUCTURE

11
SUSTAINABLE CITIES AND COMMUNITIES

12
RESPONSIBLE CONSUMPTION AND PRODUCTION

13
CLIMATE ACTION
