Forecasting Monthly Inflation Rate in Denpasar Using Long Short-Term Memory

Abstract

One of indicators of economic stability of a country is controlled inflation. In general, inflation provides information about the rise of goods and services in a region within certain period which has strongly related with people’s ability to purchase. The Covid-19 pandemic has affected almost any sectors especially the consumer price in-dex. Bali, as a major tourist destination in Indonesia, has severely affected by the pandemic. Information about future inflation rate plays important role in determining the correct decision regarding economic policy. The aim of this research is to fore-cast inflation rate in Denpasar using deep learning method for time series. Deep learning, a part of machine learning, consists of layers of neurons that are designed to learn complex patterns and is able to make forecasting. In this research we de-ployed a special type of recurrent neural networks called long-short term memory (LSTM) that is suitable for use in time series analysis. We stacked the networks into two, three, and four layers to add capacity and to build deep networks for inflation rate series. A grid search for each layer is conducted to obtain optimal hyperparame-ters setting. We conclude that the optimum architecture for setting for this deep net-work is stacked two LSTM layers. The monthly inflation rate forecasts suggest the in-flation for 2022 fluctuates, but below one percent.