Forecasting Indonesia Inflation Using Long Short Term Memory Method

The case of inflation can influence monetary policy. Therefore, in assisting policy decision-making, inflation forecasts can be made. Inflation forecasting is a connecting bridge to determine the value of inflation for the coming period. Running inflation allows it to change from time to time, resulting in a nonlinear model that will provide a more accurate forecast of inflation. The neural network is a general function approach capable of mapping any nonlinear function. One part of the neural network method used in forecasting is the Long Short Term Memory (LSTM) method. This method has the advantage of storing information for a more extended period. However, the efficiency of the neural network method depends on the network structure of the number of hidden neurons and epochs in converging conditions. This study aims to obtain the best inflation forecasting model in Indonesia using the LSTM method. This method is a development network of the Recurrent Neural Network, which is composed of forget gate, input gate, cell state, and output gate. Based on the research results, the best LSTM model in predicting inflation in Indonesia has more than one hidden neuron with the optimum number of epochs. However, too many hidden neurons are used, and the use of epochs that are not optimized will make the root mean square error value and mean absolute error based on the sample out worse. This indicates that too many hidden neurons and epochs will lead to overfitting in Indonesia's inflation forecasting.