A COMPARISON OF FUZZY TIME SERIES CHENG AND CHEN-HSU IN FORECASTING TOTAL AIRPLANE PASSENGERS OF SOEKARNO-HATTA AIRPORT

Abstract

In some cases, the demand for flights has increased or decreased unexpectedly. Based on this airport, as a service provider, balance the availability of the service and the needs in the field. To balance all the provided services, the airport needs to predict the total number of passengers that would visit the airport on consecutive days. Thus, a form of time-series forecast is used in this research. We applied fuzzy time series (FTS) to forecast total airplane passengers, where there are several logics in FTS, including FTS Cheng’s Logic and FTS Chen-Hsu’s Logic. To determine the accuracy of the forecast, use three criteria, namely Root Mean Squared Error (RMSE), Mean Absolute Deviation (MAD), and Mean Absolute Percentage Error (MAPE). In terms of modeling and forecasting data, FTS Chen-Hsu’s Logic is better than FTS Cheng’s Logic. This is shown in the value of three accuracy criteria of FTS Chen-Hsu’s Logic, which are smaller than those of FTS Cheng’s Logic. In conclusion, the FTS Chen-Hsu method can be used as a forecasting model for the total number of passenger airplanes at Soekarno-Hatta International Airport.