Future Forecasting of Turkey’s Chemical Imports: Performance Analysis of Machine Learning and Ensemble Learning Methods

Kamil Abdullah Eşidir

Makale detayları

Future Forecasting of Turkey’s Chemical Imports: Performance Analysis of Machine Learning and Ensemble Learning Methods

Yazarlar:

Kamil Abdullah Eşidir

Yayıncı:

Fırat University

Ana Başlıklar:

Yapay Zeka (Diğer)

Dergi:

Fırat Üniversitesi Sosyal Bilimler Dergisi Vol.35 Issue 1, pp.261-278

Belge Tipi:

Makale

Yayın Tarihi:

1/2025

Belge Dili:

Türkçe

Document ID (Org No.):

2001338757

pISSN:

1300-9702

Anahtar kelimeler:

Özet:

 This study evaluates the performance of machine learning and ensemble learning methods to predict the future values of Turkeys chemical imports. Linear Regression, Random Forest, Rational Quadratic Regression, Support Vector Machine and XGBoost models are used. Data are obtained from reliable sources such as TurkStat and CBRT. Macroeconomic variables include Turkeys Imports, Chemicals and Chemical Products Production Index, Monthly Average Dollar Exchange Rate, Manufacturing Industry Production Index, Oil Barrel Prices and Chemicals Exports. According to the analysis results, the XGBoost model has the highest accuracy and generalization ability. The model performed well in the training, test and cross-validation sets with the lowest error rates and the highest R² values. SHAP analysis reveals that Turkey Imports and Chemicals Production Index variables have the highest impact. The projections made with the XGBoost model provide important insights into the future course of Turkeys chemical imports and are critical for economic planning and trade strategies. The models capability facilitates strategic decisions for policymakers and the business community.

 This study evaluates the performance of machine learning and ensemble learning methods to predict the future values of Turkeys chemical imports. Linear Regression, Random Forest, Rational Quadratic Regression, Support Vector Machine and XGBoost models are used. Data are obtained from reliable sources such as TurkStat and CBRT. Macroeconomic variables include Turkeys Imports, Chemicals and Chemical Products Production Index, Monthly Average Dollar Exchange Rate, Manufacturing Industry Production Index, Oil Barrel Prices and Chemicals Exports. According to the analysis results, the XGBoost model has the highest accuracy and generalization ability. The model performed well in the training, test and cross-validation sets with the lowest error rates and the highest R² values. SHAP analysis reveals that Turkey Imports and Chemicals Production Index variables have the highest impact. The projections made with the XGBoost model provide important insights into the future course of Turkeys chemical imports and are critical for economic planning and trade strategies. The models capability facilitates strategic decisions for policymakers and the business community.

 This study evaluates the performance of machine learning and ensemble learning methods to predict the future values of Turkeys chemical imports. Linear Regression, Random Forest, Rational Quadratic Regression, Support Vector Machine and XGBoost models are used. Data are obtained from reliable sources such as TurkStat and CBRT. Macroeconomic variables include Turkeys Imports, Chemicals and Chemical Products Production Index, Monthly Average Dollar Exchange Rate, Manufacturing Industry Production Index, Oil Barrel Prices and Chemicals Exports. According to the analysis results, the XGBoost model has the highest accuracy and generalization ability. The model performed well in the training, test and cross-validation sets with the lowest error rates and the highest R² values. SHAP analysis reveals that Turkey Imports and Chemicals Production Index variables have the highest impact. The projections made with the XGBoost model provide important insights into the future course of Turkeys chemical imports and are critical for economic planning and trade strategies. The models capability facilitates strategic decisions for policymakers and the business community.

 Bu çalışma, Türkiyenin kimyasal madde ithalatının gelecekteki değerlerini tahmin etmek amacıyla makine öğrenmesi ve topluluk öğrenme yöntemlerinin performansını değerlendirmektedir. Doğrusal Regresyon, Rastgele Orman, Rasyonel Kuadratik Regresyon, Destek Vektör Makinesi ve XGBoost modelleri kullanılmıştır. Veriler, TÜİK ve TCMB gibi güvenilir kaynaklardan elde edilmiştir. Makroekonomik değişkenler arasında Türkiye İthalatı, Kimyasallar ve Kimyasal Ürünler Üretim Endeksi, Aylık Ortalama Dolar Kuru, İmalat Sanayi Üretim Endeksi, Petrol Varil Fiyatları ve Kimyasal Madde İhracatı yer almaktadır. Analiz sonuçlarına göre, XGBoost modeli en yüksek doğruluk ve genelleme yeteneğine sahiptir. Model, eğitim, test ve çapraz doğrulama setlerinde en düşük hata oranları ve en yüksek R² değerleri ile başarılı performans göstermiştir. SHAP analizi, Türkiye İthalatı ve Kimyasallar Üretim Endeksi değişkenlerinin en yüksek etkiye sahip olduğunu ortaya koymuştur. XGBoost modeli ile yapılan projeksiyonlar, Türkiyenin kimyasal madde ithalatının gelecekteki seyrine dair önemli bilgiler sunmakta, ekonomik planlama ve ticari stratejiler için kritik öneme sahiptir. Modelin yeteneği, politika yapıcılar ve iş dünyası için stratejik kararları kolaylaştırmaktadır.

Makale detayları

Future Forecasting of Turkey’s Chemical Imports: Performance Analysis of Machine Learning and Ensemble Learning Methods

Yazarlar:

Kamil Abdullah Eşidir

Yayıncı:

Fırat University

Ana Başlıklar:

Yapay Zeka (Diğer)

Dergi:

Fırat Üniversitesi Sosyal Bilimler Dergisi Vol.35 Issue 1, pp.261-278

Belge Tipi:

Makale

Yayın Tarihi:

1/2025

Belge Dili:

Türkçe

Document ID (Org No.):

2001338757

pISSN:

1300-9702

Chemicals Imports

Machine Learning

Ensemble Learning

Economic Forecasting

XGBoostKimyasal Madde İthalatı

Makine Öğrenmesi

Topluluk Öğrenme

Ekonomik Tahmin

XGBoost

Sayı

Makale detayları

Yazarlar: Kamil Abdullah Eşidir

Yayıncı: Fırat University

Ana Başlıklar: Yapay Zeka (Diğer)

Dergi: Fırat Üniversitesi Sosyal Bilimler Dergisi Vol.35 Issue 1, pp.261-278

Belge Tipi: Makale

Yayın Tarihi: 1/2025

Belge Dili: Türkçe

Document ID (Org No.): 2001338757

pISSN: 1300-9702

Sayı

Yazarlar:

Kamil Abdullah Eşidir

Yayıncı:

Fırat University

Ana Başlıklar:

Yapay Zeka (Diğer)

Dergi:

Fırat Üniversitesi Sosyal Bilimler Dergisi Vol.35 Issue 1, pp.261-278

Belge Tipi:

Makale

Yayın Tarihi:

1/2025

Belge Dili:

Türkçe

Document ID (Org No.):

2001338757

pISSN:

1300-9702