Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Brilliance: Research of Artificial Intelligence
Ramadhani, Jelang Fikri
Unknown Affiliation
Decision Sciences, Operations Research & Management Mathematics Other

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Predicting the Number of Passengers on Electric Rail Trains (KRL) in Jabodetabek Using the ARIMA Method Fajarianto, Gama Wisnu; Ramadhani, Jelang Fikri; Kusuma, Suleman Candra; Zarkasi, Mohammad
Brilliance: Research of Artificial Intelligence Vol. 5 No. 1 (2025): Brilliance: Research of Artificial Intelligence, Article Research May 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i1.6347

Abstract

The growing population of the Jabodetabek metropolitan area has significantly increased the number of public transportation users, placing immense pressure on the Electric Rail Train (KRL) as a backbone of urban mobility. This surge in KRL passengers frequently results in overcrowding, adversely impacting service quality and passenger satisfaction. Previous studies have consistently highlighted this dissatisfaction, emphasizing that an adequate supply of train carriages is critical to reducing congestion. To proactively manage this issue, accurate forecasting of future ridership is essential for strategic planning. This research employs the Autoregressive Integrated Moving Average (ARIMA) method to analyze and predict passenger volume based on historical time-series data. The methodology involved testing three distinct data-splitting scenarios to identify the most robust model configuration. The evaluation results demonstrate that the ARIMA (9,1,7) model, utilizing a 90% training and 10% testing data division, provides the most superior predictions compared to the other models. This is evidenced by its consistently low error metrics, with a Mean Absolute Percentage Error (MAPE) of 6.63%. The low MAPE value confirms the model's high predictive accuracy. It is concluded that this optimized ARIMA model is a reliable tool for stakeholders, enabling data-driven decisions to improve service quality and mitigate overcrowding in the Greater Jakarta area.
Co-Authors Gama Wisnu Fajarianto Kusuma, Suleman Candra Zarkasi, Mohammad