Use of ARIMA Method to Predict the Number of Train Passenger in Malang City

Closed

Triyanna Widiyaningtyas, Muladi, Adiba Qonita

2019 Proceeding - 2019 International Conference of Artificial Intelligence and Information Technology, ICAIIT 2019 Conference paper Cited by 4 Quartile

Abstract

Today, trains have become one of the most popular public transportation for medium and long distance travel. During the holidays, the number of train passengers is difficult to predict. The increase in the number of train passengers causes Indonesian Railway Company (IRC) needs to take action by adding train departures. The purpose of this study is to predict the number of train passengers with the Autoregressive Integrated Moving Average (ARIMA) method. The stages used in the study include: (1) datasets preparation, (2) preprocessing data, (3) experimental and method testing, and (4) accuracy testing. To test the accuracy of the algorithm used Mean Absolute Error (MAE). The MAE result is 1.37409 for the number of train passenger from Malang and 2.48417 for the number of train passenger to Malang. So, the ARIMA method used in predicting passenger was accurate. © 2019 IEEE.

Affiliations

Electrical Engineering Department, Universitas Negeri Malang, Malang, Indonesia