In this study, the relationship between Türkiye’s real gross domestic product, CO2 emission and renewable energy consumption is modelled using machine learning techniques. The data between 2003-2020, the period when renewable energy production and consumption have accelerated, are included in the modelling. First of all, it was tested whether there is a causal relationship between the real gross domestic product, CO2 emission and renewable energy consumption data. Afterwards, a deep learning model was developed in Python programming language by considering the real gross domestic product as the dependent variable while CO2 emission and renewable energy consumption are considered as independent variables. The developed deep learning model has two input nodes, three hidden layers consisting of 100 neurons each, and an output node. In addition, the rectified unit functions are used as nonlinear activation functions in the deep learning network. Based on the standard usage, seventy percent of the data was used as the training data and the remaining thirty percent were employed as the test data. The results of the developed deep learning network and actual gross domestic product data were compared, and it is shown that the developed deep learning network successfully models the relationship between the real gross domestic product, CO2 emission and the renewable energy consumption. The coefficient of determination of the developed model was calculated in Python environment as R2=0.986. This parameter value also indicates that the developed deep learning network model has a good performance for the modelling of the real gross domestic product dependent on the CO2 emission and renewable energy consumption.

The increase in the producer prices limits the activities of the companies and leads to the deterioration of the national product, employment and consumer prices. In this study, the relations between the oil price, exchange rate, interest rate, wages and the producer prices for the period of 2002Q01-2022Q03 in Türkiye were examined using autoregressive moving averages (ARIMA) and artificial neural network (ANN) methods. The employed ANN structure consists of an input layer, a hidden layer with 100 neurons and an output layer. The ANN is trained and then the modelling and forecasting performances of the traditional ARIMA and nonlinear ANN methods are compared. RMSE, MAE, MAPE and R2 criteria were used to evaluate the predictive power of the ARIMA and ANN models. As a result of automatic ARIMA model estimation, it has been determined that the producer prices can be modelled using an ARMA(4.4) model, which is a subset of the ARIMA modelling. MAE, RMSE, MAPE and R2 values of ARIMA and ANN models show that the ARMA(4,4) model has slightly better accuracy compared to the ANN model. In addition, according to the ARMA(4.4) model, it is shown that the interest rate, exchange rate, oil prices and wages affect producer prices. In this context, our policy recommendations are to follow a low interest policy and to encourage the use and production of electric vehicles to reduce the use of fossil fuels in order to reduce producer prices. Keywords: Producer price index, artificial neural network ARIMA, economic modelling.

Energy is an important input of the economic growth and the energy policies of countries are crucial for reaching their economic targets. In this study, the economic growth of Türkiye for the period of 1990-2021 is modelled dependent on the sectoral energy consumption, labour force and the capital formation. The dependent and independent data are taken from the respective sources and then the pairwise Granger causality test is applied on these data. As the next step, the economic growth of Türkiye is taken as the dependent variable and modelled as a function of the other variables. Considering the low number of samples available and the nonlinearity of the data, machine learning methods are utilized for the modelling. Specifically, deep learning multilayer perceptron networks which are coded in Python programming language are employed for the modelling of the economic growth. The 70% of the available data are used as the training data while 30% of the data are utilized as the test data. The training and test data are split using special classes of the Python programming language to provide objectivity. Then, the actual economic growth and the deep learning model results are graphed which show a high degree of overlap indicating the accuracy of the developed model. In addition, the performance metrics of the developed model namely the coefficient of determination, mean absolute error, mean absolute percentage error and the root mean square error are computed which also indicate the high accuracy of the developed model. The approach used for the modelling of the economic growth is considered to be useful for modelling the other econometric data related to the growth hypothesis.

The gross domestic product of countries plays a key role in the development and wealth of nations. There are several components of the gross domestic product, such as industrial revenue, revenue from services, and tourism revenue. Türkiye is located in Anatolia, which is very rich from a historical viewpoint. Therefore, Türkiye attracts tourists from all over the world, making its tourism revenue an important contributor to its gross domestic product. This study aimed to model the tourism revenue of Türkiye using machine learning methods. In this study, the tourism revenue of Türkiye, dependent on the number of tourists, oil prices, and the exchange rate, are modelled for the period of 2008-2022. The data of these variables were taken from official sources, and then the causality analyses were carried out. As the next step, the tourism revenue is modelled as a function of the number of tourists, oil prices, and the exchange rate. A deep learning network is developed using the Python programming language for modelling the tourism revenue. The developed deep learning network is then trained using a portion of the data. The performance of the developed deep learning network is then evaluated using the performance metrics such as the coefficient of determination, mean absolute error, root means square error, and the mean absolute percentage error. These metrics show that the developed deep learning network successfully models the tourism revenue dependent on the number of tourists, oil prices, and the exchange rate.