Tarımsal ve sosyo-ekonomik göstergelerle tarım kredileri tahmini: makine öğrenmesi ve istatistiksel modellerin karşılaştırılması
Küçük Resim Yok
Tarih
2025
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Bayburt Üniversitesi
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
Tarımsal üretim, ekonomik büyüme ve kırsal kalkınma açısından stratejik öneme sahiptir. Bu çalışmada, Türkiye'de 2000-2022 yıllarını kapsayan verilerle tarımsal kredilerin tahmininde makine öğrenmesi ve istatistiksel modellerin performansları karşılaştırılmıştır. Analizde tarım arazileri, sulama oranları, tatlı su çekimi, kentsel nüfus oranı ve tarımsal katma değer gibi değişkenler bağımsız değişken olarak kullanılmıştır. Analiz sürecinde Gauss Süreç Regresyonu, Destek Vektör Regresyonu, Topluluk Öğrenmeleri, Yapay Sinir Ağları, Karar Ağaçları ve Çoklu Doğrusal Regresyon yöntemleri değerlendirilmiştir. Elde edilen bulgular, GPR modelinin test aşamasında en yüksek tahmin doğruluğunu sağladığını ve doğrusal olmayan karmaşık ilişkileri modelleme kapasitesinin üstün olduğunu göstermiştir. GPR modelini Topluluk Öğrenmeleri yöntemi takip ederken, SVR modeli de dikkate değer bir performans sergilemiştir. Bununla birlikte, YSA ve Karar Ağaçları modellerinin genelleme kapasitelerinin sınırlı olduğu gözlemlenmiştir. Çalışmada, çoklu doğrusal bağımlılık probleminin çözümü için Ana Bileşen Analizi (PCA) uygulanmış ve temel bileşenler yardımıyla veri boyutu düşürülerek model performanslarının artırıldığı tespit edilmiştir. Sonuç olarak, bu tezde makine öğrenmesi yöntemlerinin tarımsal kredilerin tahmininde istatistiksel yöntemlere göre daha yüksek doğruluk sunduğu tespit edilmiştir. Elde edilen bulgular, makine öğrenmesi modellerinin tarımsal kredi politikalarının geliştirilmesi ve kırsal kalkınmanın desteklenmesinde etkili bir araç olabileceğini göstermektedir. Gelecekte, daha geniş veri setleri ve hibrit yaklaşımların kullanımı önerilmektedir.
Agricultural production is strategically important in terms of economic growth and rural development. In this study, the performances of machine learning and statistical models were compared to estimate agricultural credits with data covering the years 2000-2022 in Turkey. Variables such as agricultural lands, irrigation rates, freshwater withdrawal, urban population rate and agricultural added value were used as independent variables in the analysis. Gaussian Process Regression, Support Vector Regression, Ensemble Learning, Artificial Neural Networks, Decision Trees and Multiple Linear Regression methods were evaluated in the analysis process. The findings showed that the GPR model provided the highest estimation accuracy in the test phase, and its capacity to model nonlinear complex relationships was superior. While the GPR model was followed by the Ensemble Learning method, the SVR model also exhibited a remarkable performance. However, it was observed that the generalization capacities of ANN and Decision Tree models were limited. In the study, Principal Component Analysis (PCA) was applied to solve the multicollinearity problem. It was determined that the model performances were increased by reducing the data size with the help of principal components. As a result, this thesis has defined machine learning methods as providing higher accuracy in estimating agricultural credits than statistical methods. The findings show that machine learning models can be an effective tool in developing agricultural credit policies and supporting rural development. Using more extensive data sets and hybrid approaches is recommended in the future.
Agricultural production is strategically important in terms of economic growth and rural development. In this study, the performances of machine learning and statistical models were compared to estimate agricultural credits with data covering the years 2000-2022 in Turkey. Variables such as agricultural lands, irrigation rates, freshwater withdrawal, urban population rate and agricultural added value were used as independent variables in the analysis. Gaussian Process Regression, Support Vector Regression, Ensemble Learning, Artificial Neural Networks, Decision Trees and Multiple Linear Regression methods were evaluated in the analysis process. The findings showed that the GPR model provided the highest estimation accuracy in the test phase, and its capacity to model nonlinear complex relationships was superior. While the GPR model was followed by the Ensemble Learning method, the SVR model also exhibited a remarkable performance. However, it was observed that the generalization capacities of ANN and Decision Tree models were limited. In the study, Principal Component Analysis (PCA) was applied to solve the multicollinearity problem. It was determined that the model performances were increased by reducing the data size with the help of principal components. As a result, this thesis has defined machine learning methods as providing higher accuracy in estimating agricultural credits than statistical methods. The findings show that machine learning models can be an effective tool in developing agricultural credit policies and supporting rural development. Using more extensive data sets and hybrid approaches is recommended in the future.
Açıklama
Anahtar Kelimeler
İstatistik, Statistics
