Performance of ensemble forecasting tools for analysis turkish consumer price index

---

Tezin Türü: Yüksek Lisans

Tezin Yürütüldüğü Kurum: Orta Doğu Teknik Üniversitesi, Fen Edebiyat Fakültesi, İstatistik Bölümü, Türkiye

Tezin Onay Tarihi: 2018

Öğrenci: PETEK AYDEMİR

Danışman: CEYLAN YOZGATLIGİL

Özet:

Major challenge in time series analysis is to get reasonably accurate forecasts of the future data from the analysis of the previous records. Accurate forecasting of inflation has great importance in the market economies, the policymakers and the monetary system since the inflation rate determines the cost and standard of living. Also, it affects the decision on investments. In Turkey, the inflation rate is measured by the consumer price index (CPI). There exist many methods to predict the future values of the CPI. In this study, six individual models were applied to forecast the Turkish CPI. Those are Seasonal Autoregressive Integrated Moving Average Model with Exogeneous variables (SARIMAX), Holt-Winters Exponential Smoothing, Trigonometric Exponential Smoothing State Space model with Box-Cox transformation, ARMA errors, Trend and Seasonal Components (TBATS) model, Artificial Neural Network (ANN), Theta Model, Seasonal Trend Decomposition with Loess (STL). Then, ensemble model was constructed to improve the forecast performance. Ensemble model is the combination of several forecasting models to improve the performance of the forecast. The forecast accuracy of all models is evaluated by the Root Mean Square Error and Mean Absolute Percentage Error. Our findings show that SARIMAX(4,1,4)(2,0,1)x12 and ensemble model composed of auto.arima and neural network produce the best forecasts for 12 month Turkish CPI.