<![CDATA[Inflation is a condition wherein the general level of prices for goods and services in an economy continually rises. Predicting inflation serves as a crucial link in establishing future inflation values. The dynamic nature of inflation allows for changes over time, forming a nonlinear model capable of providing more accurate inflation predictions. This research aims to examine and compare the effectiveness of GARCH/ARCH and LSTM models in predicting inflation data.The results of the study indicate that the LSTM model proves to be the superior choice for predicting inflation with higher accuracy when compared to the GARCH model. The GARCH model produces more accurate predictions of future inflation periods, as evidenced by the Mean Absolute Percentage Error (MAPE) value of 2.6814%. This value signifies the extent of the comparison between the actual and predicted model values. In contrast, the LSTM model yields a Mean Absolute Error (MAE) value of 0.00895358, demonstrating its superior accuracy.Therefore, the findings of this research can be considered a valuable reference for a country looking to predict inflation more effectively. Utilizing advanced time series models, such as LSTM, can enhance the accuracy of inflation predictions, providing policymakers with valuable insights for informed decision-making]]>
Copyrights © 2024
