Reference interest rates or often referred to as BI 7-Day Repo Rate is a policy interest rate that describes the establishment or view of monetary policy whose determination is made by Bank Indonesia which is then notified to the public.. BI 7-Day Repo Rate has an influence on economic activities, such as investment, inflation and currency changes. Investors and market players in making economic decisions will refer to the fluctuation of interest rates set by the central bank. Therefore, the prediction of the benchmark interest rate (BI 7-Day Repo Rate) is important. The purpose of the BI 7-Day Repo Rate prediction is to facilitate and assist investors and market players to make estimates of the decisions to be taken according to the prediction of the benchmark interest rate. This study uses the Extreme Learning Machine (ELM) method to predict the reference interest rate (BI 7-Day Repo Rate). The process of the first ELM algorithm is to normalize, then initialize the input and bias weights, then continue to carry out the training process and proceed with the testing process, then do the normalization to obtain the actual value. Based on the Extreme Learning Machine (ELM) algorithm that has been conducted, it produces the best Mean Absolute Percentage Error (MAPE) of 1,1% and the fastest processing time is 0.125 seconds using 50 hidden neurons, sigmoid activation function and 96 data counts.
Copyrights © 2019