Sürdürülebilir Kalkınma Amaçları
Yazarlar
Yayınlar
- MakaleAçık Erişim2022The Dynamics Affecting the Export-Import Ratio in Turkey: A Hybrid Model Proposal with Econometrics and Machine Learning Approach
Özden, Erdemalp
The indicators related to foreign trade are conventionally measured in a currency or as the ratio of the country's gross domestic products. The ratio of exports to imports, alternatively, provides more useful results when comparing the foreign trade performance of economies both over time and with other countries as a unit-free indicator. In this study, the macroeconomics and financial determinants affecting this ratio are examined both econometrically and using the machine learning method. In this context, the autoregressive distributed lag model method was first used to investigate the relationship between normalized gross domestic products, exchange rate, consumer price index, producer price index, crude oil and Turkey's ratio of exports to imports rate between 2010-2021, monthly. Long-term analysis showed that the 1% depreciation of the Turkish Liras against the US dollar increased the ratio of exports to imports rate by 0.7 points. In addition, a 1% increase in consumer price index will increase ratio of exports to imports by 1.9 points, while a 1% increase in producer price index will cause a -0.8 point decrease on the ratio of exports to imports. Then, the pattern between the variables was analyzed with quadratic support vector machine, a machine learning method. Finally, the novel ARDL-SVM hybrid method was developed, and the pattern between the variables was examined. The findings revealed that although the econometric method provided a broader scope for interpreting the relationships between variables, the developed ARDL-SVM method successfully captured patterns between variables.
AtıfWoS1OpenAlex5TR Dizin1
İncele - MakaleYalnız künye2022Scopus SJRQ2Optimized Machine Learning Algorithms for Investigating the Relationship Between Economic Development and Human Capital
Ozden, Erdemalp; Guleryuz, Didem
In Economic Development, human capital was previously seen as production factors but gradually evolved into endogenous growth theories. Most of the previous studies have examined the relationships between economic development and human capital via econometric models. Since this relationship is usually nonlinear and machine learning (ML) models can resolve it better, this study investigates the relationships by employing ML methods to provide a new perspective. For this purpose, the optimized ML methods, namely Bayesian Tuned Support Vector Machine and Bayesian Tuned Gaussian Process Regression (BT-GPR), were performed to develop the prediction model for economic development. The hyperparameters have been optimized with the Bayes method by using different kernel functions to increase SVM and GPR methods' predictive performance. The Multiple Linear Regression model has been employed to make a comparison as an econometric model. The performance of the models is evaluated using three statistical metrics, namely, the root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2). The BT-GPR with the exponential kernel model has superior prediction ability with the highest accuracy (R2: 0.9727, RMSE: 0.4022, MAE: 0.3728 in the testing phase). The study shows that the BT-GPR model increases the accuracy of R2 6.4%, RMSE 10.7%, and MAE 1% compared with other developed models.
AtıfScopus27WoS18OpenAlex30
İncele