SISTEM PREDIKSI VOLUME PENUMPANG HARIAN KRL YOGYAKARTA-SOLO MENGGUNAKAN MODEL HYBRID SARIMAX-PROPHET

Muhammad Ilham 'Aziiz Alfarobi; Nurmalitasari; Ratna Puspita Indah

doi:10.46880/mtk.v12i2.5721

Authors

Muhammad Ilham 'Aziiz Alfarobi Universitas Duta Bangsa Surakarta
Nurmalitasari Universitas Duta Bangsa Surakarta
Ratna Puspita Indah Universitas Duta Bangsa Surakarta

DOI:

https://doi.org/10.46880/mtk.v12i2.5721

Keywords:

Hybrid Model, Passenger Volume Prediction, SARIMAX-Prophet, Yogyakarta-Solo Commuter Line

Abstract

The operation of the Yogyakarta-Solo Commuter Line (KRL) since 2021 has become the backbone of transportation in the Yogyakarta Special Region and Central Java. However, highly dynamic fluctuations in passenger volume pose challenges for operational optimization. This research aims to develop an accurate daily passenger volume prediction system with a 30 day forecasting horizon to mitigate overcrowding and fleet inefficiency. The methodology employed is CRISP-DM, proposing a layered hybrid architecture based on residual modeling. In this model, SARIMAX serves as the primary pattern modeler (Layer 1), while Facebook Prophet acts as a residual corrector (Layer 2), optimized with selective correction mechanisms and daily adaptive weights. The research data covers the period from January 2025 to January 2026, totaling 396 observations. The test results show that the hybrid model provides the best performance compared to single models, achieving a Mean Absolute Percentage Error (MAPE) of 9.66% and a Mean Absolute Error (MAE) of 2,739 passengers per day. Utilizing historical data from January 2025 to January 2026, the modeling results are integrated into an interactive Streamlit dashboard as a practical decision support tool for KAI Commuter's proactive operational planning

References

F. Fadhilah, M. Y. Hartiman, dan I. Prasetyo, “Analisis Rencana Pengoperasian KRL Lintas Yogyakarta-Kutoarjo Sebagai Pengganti KRDE Prameks”.

C. Noermartanto, H. Risnandar, N. Anggani, dan P. Hmp Uns, Analisis Peningkatan Komuter Di Perkotaan Solo -Yogya Menggunakan Commuter Line. 2024.

T. N. Arifin, S. Sodikin, dan T. Tantin, “ANALISA KINERJA OPERASIONAL KRL COMMUTER LINE JURUSAN YOGYAKARTA-SOLO,” Rang Tek. J., vol. 8, no. 2, hlm. 273–283, Jun 2025, doi: 10.31869/rtj.v8i2.6228.

“KAI Commuter.” Diakses: 19 Mei 2026. [Daring]. Tersedia pada: https://kci.id/informasi-publik/berita/capaian-membanggakan-volume-pengguna-commuter-line-wilayah-6-yogyakarta-tembus-10-juta-sepanjang-2025

R. M. Yunianto dan A. Muklason, “Penerapan Metode Hybrid LSTM dan Seasonal Decomposition untuk Peramalan Permintaan Tiket Harian PT KAI,” ILKOMNIKA, vol. 7, no. 2, hlm. 168–181, Agu 2025, doi: 10.28926/ilkomnika.v7i2.733.

“KAI Commuter.” Diakses: 19 Mei 2026. [Daring]. Tersedia pada: https://kci.id/informasi-publik/berita/masa-libur-sekolah-volume-pengguna-krl-yogyakarta-solo-naik-17

S. S. S. Sidabutar, S. T. Sitohang, M. J. Samosir, Y. A. Simatupang, dan J. T. Hardinata, “Perbandingan Metode Regresi Linier dan Artificial Neural Network dalam Memprediksi Jumlah Penumpang Kereta Api Nasional,” J. Komput. Teknol. Inf. Sist. Komput. JUKTISI, vol. 4, no. 3, hlm. 2125–2132, Jan 2026, doi: 10.62712/juktisi.v4i3.822.

A. C. Damar, D. Safitri, dan S. Sujarwo, “Analisis Dampak Kepadatan Penumpang KRL Terhadap Tingkat Stress Masyarakat Jabodetabek,” J. Ilm. Penelit. Mhs., vol. 3, no. 2, hlm. 226–235, Apr 2025, doi: 10.61722/jipm.v3i2.815.

R. Wati, R. Estriana, R. Praptiwi, B. S. Ilmi, N. R. Oktavian, dan T. Zakiyudin, “Analisis Perbandingan XGBoost, Random Forest, dan LSTM untuk Prediksi Jumlah Penumpang Bus,” J. Inform. Interact. Technol., vol. 2, no. 3, hlm. 405–413, Des 2025, doi: 10.63547/jiite.v2i3.73.

L. D. Jayanti, R. Lestari, F. A. D. Suparno, dan F. Fachruzzaki, “Prediksi Harga Emas Tahun 2024-2025 dengan Metode Autoregressive Integrated Moving Average (ARIMA) pada Aplikasi RStudio,” MARAS J. Penelit. Multidisiplin, vol. 3, no. 4, hlm. 1275–1289, Okt 2025, doi: 10.60126/maras.v3i4.1253.

I. K. Chisan dan A. W. Wijayanto, “Forecasting Jumlah Penumpang Pesawat Yogyakarta International Airport dengan Big Data Google Trends dan Variabel Makroekonomi untuk Mendukung Official Statistics,” Semin. Nas. Off. Stat., vol. 2024, no. 1, hlm. 615–624, Nov 2024, doi: 10.34123/semnasoffstat.v2024i1.2123.

L. L. Ibrahim dan E. Kurniati, “Peramalan Jumlah Penumpang Kereta Api Eksekutif di Pulau Jawa Menggunakan Model SARIMA,” J. Ris. Mat., hlm. 73–82, Jul 2023, doi: 10.29313/jrm.v3i1.1747.

Q. Cao, Z. Sun, dan H. Li, “Comparative Analysis of SARIMA, Prophet, and a Diagnostic Decomposition–Correction Hybrid for Long-Horizon Lottery Sales Forecasting,” Entropy, vol. 28, no. 3, hlm. 286, Mar 2026, doi: 10.3390/e28030286.

H. N. Azalia, Hannie, dan A. A. Ridha, “ANALISIS TREN DAN FORECASTING KUNJUNGAN PASIEN BERBASIS FACEBOOK PROPHET UNTUK OPTIMALISASI MANAJEMEN LAYANAN KESEHATAN,” J. Inform. Dan Tek. Elektro Terap., vol. 14, no. 2, Apr 2026, doi: 10.23960/jitet.v14i2.9290.

F. B. Prakoso, G. Darmawan, dan A. Bachrudin, “PENERAPAN METODE FACEBOOK PROPHET UNTUK MERAMALKAN JUMLAH PENUMPANG TRANS METRO BANDUNG KORIDOR 1,” ARMADA J. Penelit. Multidisiplin, vol. 1, no. 3, hlm. 133–147, Mar 2023, doi: 10.55681/armada.v1i3.416.

M. R. Yudistira, “Nowcasting Jumlah Penumpang Udara di Kabupaten Berau Menggunakan Indeks Google Trends,” BESTARI BPS Kalimantan Timur, vol. 5, no. 1, Jun 2025, Diakses: 20 Mei 2026. [Daring]. Tersedia pada: https://bestari.bpskaltim.com/index.php/bestari-bpskaltim/article/view/68

V. Ripatti, “Forecasting Prescription Medication Utilization: A Comparative Study of SARIMA, Prophet, XGBoost and LSTM Models”.

M. G. S. Kenyi dan K. Yamamoto, “A hybrid SARIMA-Prophet model for predicting historical streamflow time-series of the Sobat River in South Sudan,” Discov. Appl. Sci., vol. 6, no. 9, hlm. 457, Agu 2024, doi: 10.1007/s42452-024-06083-x.

G. Saqware dan I. Beary, “Hybrid SARIMA-Facebook Prophet Model for Prediction and Forecasting of the Staple Food Prices in Tanzania,” Int. J. Oper. Res., vol. 20, hlm. 1–11, Agu 2023, doi: 10.6886/IJOR.202308_20.0001.

A. Lisnawati, S. Alam, dan I. Kurniawan, “APLIKASI PREDIKSI KEDATANGAN WISATAWAN MANCANEGARA KE INDONESIA DENGAN ALGORITMA LONG SHORT-TERM MEMORY (LSTM),” JATI J. Mhs. Tek. Inform., vol. 9, no. 5, hlm. 8343–8349, Jul 2025, doi: 10.36040/jati.v9i5.15055.

D. J. Putnarubun, C. F. Palembang, J. E. T. Radjabaycolle, dan E. M. C. Wattimena, “Sistem Prediksi Waktu Keberangkatan Pesawat Berbasis Machine Learning,” J. Inform. Dan Tek. Elektro Terap., vol. 14, no. 2, Apr 2026, doi: 10.23960/jitet.v14i2.9320.

W. S. Kesuma, “Prediksi Analisis Time Series Nilai Tukar Rupiah terhadap Dolar Amerika dengan ARIMA dan SARIMA melalui CRISP-DM,” Pros. Semin. Nas. Univ. Ma Chung Inform. Sist. Inf. Bhs. Dan Seni Farm., vol. 4, hlm. 190–203, Sep 2024.

“KIP PT. Kereta Commuter Indonesia.” Diakses: 16 Mei 2026. [Daring]. Tersedia pada: https://kip.kci.id/info-berkala

S. Pangestu, A. Febrian, dan Y. Cahyan, “PENERAPAN MODEL PROPHET UNTUK PERAMALAN JUMLAH DOKTER UMUM DI KOTA BANDUNG,” JATI J. Mhs. Tek. Inform., vol. 10, no. 1, hlm. 435–440, Jan 2026, doi: 10.36040/jati.v10i1.16619.

S. J. Taylor dan B. Letham, “Forecasting at scale,” 27 September 2017, PeerJ Preprints. doi: 10.7287/peerj.preprints.3190v2.

A. A. Maulana dan H. Rosalina, “IMPLEMENTASI METODE SARIMAX UNTUK PREDIKSI CURAH HUJAN JANGKA PENDEK DI PAGERAGEUNG, TASIKMALAYA,” J. SUMBER DAYA AIR, vol. 20, no. 1, hlm. 39–50, Mei 2024, doi: 10.32679/jsda.v20i1.874.

A. S. S. Ayuningrum, N. C. A. P. Sari, N. F. Ihsan, dan Nasrudin -, “Peramalan Jumlah Wisatawan Mancanegara yang Datang ke Bali Tahun 2025 Menggunakan SARIMAX dan Data Google Trends,” Semin. Nas. Off. Stat., vol. 2025, no. 1, hlm. 287–296, Des 2025, doi: 10.34123/semnasoffstat.v2025i1.2472.

M. G. S. Kenyi dan K. Yamamoto, “A hybrid SARIMA-Prophet model for predicting historical streamflow time-series of the Sobat River in South Sudan,” Discov. Appl. Sci., vol. 6, no. 9, hlm. 457, Agu 2024, doi: 10.1007/s42452-024-06083-x.

R. Achmad Zahra dan D. H. Fudholi, “Prediksi Pencapaian Target Kerja untuk Optimasi Manajemen Proyek Menggunakan Metode Long Short Term Memory dan Random Forest,” J. Sains Dan Teknol. J. Keilmuan Dan Apl. Teknol. Ind., vol. 25, no. 2, hlm. 208–222, 2025, doi: 10.36275/8m9pg216.

K. Arunika dan L. J. E. Dewi, “PERBANDINGAN MODEL SARIMA, EXPONENTIAL SMOOTHING, DAN XGBOOST UNTUK PREDIKSI PENJUALAN SUPER STORE,” J. Inform. Dan Tek. Elektro Terap., vol. 13, no. 3S1, Okt 2025, doi: 10.23960/jitet.v13i3S1.8173.