Publication: Hanehalkı Tüketim Harcamalarının Mikroekonometrik Analizi:_x000D_
LAD-LASSO Yöntemi
Loading...
Files
Date
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Bu çalışmanın amacı, denetimli makine öğrenmesi yöntemlerinin aşırı değer ve uzun kuyruklu hatalara sahip HanehalkıBütçe Anketi Hane veri setinin ilgili değişkenlerini seçmemize nasıl yardımcı olduğunu incelemek ve Türkiye’nin HanehalkıTüketimHarcamaları’nın tahmininde en iyitahmin ve öngörü performansına sahip olanmodelin belirlenmesinisağlamaktır.Bu amaçla, 2018 yılı Türkiye’nin Hanehalkı Bütçe Anketi Hane veri seti klasik regresyon yönteminin yanı sıra En KüçükMutlak Sapma (LAD), En Küçük Mutlak Küçültme ve Seçim Operatörü (LASSO) ve LAD-LASSO yöntemleri kullanılarakincelenmiş ve yöntemlerin tahmin ve öngörü performansları karşılaştırılmıştır. Analiz sonuçlarına göre; uzun kuyrukluhataların varlığında dayanıklı tahminciler elde edilirken aynı zamanda değişken seçimine olanak sağlayan LAD-LASSOmakine öğrenmesi yönteminin tahmin performansı ve öngörü açıklığı açısından en başarılı yöntem olduğu sonucunaulaşılmıştır. Ayrıca gelir, tasarruf ve hane halkı büyüklüğü gibi bazı temel değişkenler tüm modeller için hanehalkı tüketimharcamalarını artırmaktadır. Bu değişkenlere ek olarak odanın yapısı, mutfak, banyo zeminleri, ısıtma, klima tercihleri,kullanılan enerji kaynakları, müstakil ev, apartman, yazlık, bağ sahipliği ve yatırım tercihleri, kredi kartı kullanımı, internetalışveriş alışkanlıkları gibi çeşitli değişkenler LAD-LASSO modelinde hane halkı tüketim harcamalarının belirleyicileriolarak seçilmiştir. Çalışma sonuçlarından, makine öğrenme algoritmalarının mikroekonometrik modellerin oluşturulmasısırasında gerekli değişkenlerin seçiminde kullanılabileceğine dair bulgular elde edilmiştir. Bu çalışma doktora tezindenüretilmiştir.
This study examined how supervised machine learning methods help us select the relevant variables of a Household_x000D_ Budget Survey Consumption Expenditures dataset with outliers in order to achieve better performance in the predicting_x000D_ and forecasting of the Household Consumption Expenditures Model. To achieve this, the Household Budget Survey_x000D_ Consumption Expenditures dataset of Turkey for 2018 was examined using the Least Absolute Deviation (LAD), Least_x000D_ Absolute Shrinkage and Selection Operator (LASSO) and LAD-LASSO methods. In addition, the classical regression method_x000D_ and the prediction and forecasting performances of the methods were compared. According to the analyzed results, it was concluded that the LAD-LASSO machine learning method, which enables the selection of variables_x000D_ while obtaining robust predictors in the presence of long-tailed errors, was the most successful method in_x000D_ prediction performance and forecasting accuracy. Additionally, several fundamental variables such as income,_x000D_ saving, and household size increase the household consumption expenditures for all models. In addition to_x000D_ these variables, other variables including the structure of a room, the kitchen, bathroom floors, heating, air_x000D_ conditioning preferences, energy sources used, detached house, apartment, cottage, vineyard ownership,_x000D_ investment preferences, credit card usage, and internet shopping habits were selected as determinants of_x000D_ household consumption expendituresin the LAD-LASSO model. From the results of the study, it wasfound that_x000D_ machine learning algorithms can be used in the selection of the most appropriate variablesin the course of the_x000D_ construction of microeconometric models.
This study examined how supervised machine learning methods help us select the relevant variables of a Household_x000D_ Budget Survey Consumption Expenditures dataset with outliers in order to achieve better performance in the predicting_x000D_ and forecasting of the Household Consumption Expenditures Model. To achieve this, the Household Budget Survey_x000D_ Consumption Expenditures dataset of Turkey for 2018 was examined using the Least Absolute Deviation (LAD), Least_x000D_ Absolute Shrinkage and Selection Operator (LASSO) and LAD-LASSO methods. In addition, the classical regression method_x000D_ and the prediction and forecasting performances of the methods were compared. According to the analyzed results, it was concluded that the LAD-LASSO machine learning method, which enables the selection of variables_x000D_ while obtaining robust predictors in the presence of long-tailed errors, was the most successful method in_x000D_ prediction performance and forecasting accuracy. Additionally, several fundamental variables such as income,_x000D_ saving, and household size increase the household consumption expenditures for all models. In addition to_x000D_ these variables, other variables including the structure of a room, the kitchen, bathroom floors, heating, air_x000D_ conditioning preferences, energy sources used, detached house, apartment, cottage, vineyard ownership,_x000D_ investment preferences, credit card usage, and internet shopping habits were selected as determinants of_x000D_ household consumption expendituresin the LAD-LASSO model. From the results of the study, it wasfound that_x000D_ machine learning algorithms can be used in the selection of the most appropriate variablesin the course of the_x000D_ construction of microeconometric models.