A COMPARISON OF SUPERVISED LEARNING METHODS FOR FORECASTING TIME SERIES IN OUTSIDE PATIENT VISITS

Abstract

Data is something important because it can be used to help make a decision or policy in an organization. One form of output from the use of data is to produce forecasts in the future. One of the organizations that need forecasting is the hospital. Data that can be used for forecasting is patient visit data. The purpose of this study is to compare several supervised learning methods in the case of forecasting outpatient visit data, by producing a model result from the experimental process of KNN, SVR, Decision Tree, Random Forest and Linear Regression methods. From the Plot Time Series data for outpatient visits, autocorrelation results using the ACF method have a significance level, namely at lag 1 = 0.797, lag 2 = 0.6, and lag 3 = 0.579. So that the formation of the dataset is found that the current data 15Yt">  has an influence on the data one month earlier 15Xt-1"> , the previous two months 15Xt-2"> , and the previous three months 15Xt-3"> . The results of the forecasting model carried out resulted that the random forest method had the best model with an evaluation value of the RMSE model of 204.43 and the MAPE value of 12%. Based on the criteria for the MAPE value, the model that has been made has a good category.