Analisis Prediksi Data Kasus Covid-19 di Provinsi Lampung Menggunakan Recurrent Neural Network (RNN)

Abstract

This study aims to examine the architectural performance of the Recurrent Neural Network (RNN) model in predicting Covid-19 cases in Lampung Province. The RNN method is part of Deep Learning which will be used to model data on Covid-19 cases in Lampung Province from March 26, 2020 to March 28, 2021. The RNN model was chosen because the Covid-19 data is in the form of a time series and the advantages of RNN are that it can capture information on the data time series using multiple network layers which allow better modeling and resulting in high prediction accuracy. The data is divided into 3, namely active cases, recovered cases, and dead cases. After preparing the data, the 368 data were divided into 294 initial latih data and 74 test data. After latih on the data for each data, then a test is carried out on the data for each data as a reference for predicting the latest data. The most optimal results show the cumulative active case model with RMSE=0.0022; for cumulative recovery cases obtained RMSE = 0.0007; while the cumulative death cases obtained RMSE = 0.0012. Based on the modeling error, then make predictions on the three cases which results in RMSE = 0.001 for cumulative active cases; RMSE=0.0027 for cumulative recovery cases; and RMSE=0.001 for cumulative death cases.

Multivariat Predict Sales Data Using the Recurrent Neural Network (RNN) Method

“…Prediction is a crucial element in decision-making because whether a decision is effective or not generally depends on several factors that we cannot see when the decision is made, which is based on existing and past data [7]. To be able to predict sales data, time series data from the past is needed, which can be analyzed so that patterns can be formed that can predict future conditions [8].…”