Yudhani, Nidya Putri (2024) Peramalan Jumlah Penumpang Kereta Api Indonesia Menggunakan Analisis Intervensi Berbasis Gaussian Autoregressive dan Poisson Autoregressive. Other thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 5003201179-Undergraduate_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
5003201179-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2026. Download (3MB) | Request a copy |
Abstract
Kereta api merupakan salah satu moda transportasi publik yang banyak digunakan oleh masyarakat Indonesia. Perusahaan BUMN yang mengelola dan menjalankan operasi kereta api di Indonesia adalah PT Kereta Api Indonesia (KAI). Data jumlah penumpang kereta api adalah data count time series yang berisi nilai diskrit. Jumlah penumpang kereta api dipengaruhi oleh serangkaian input yang disebut intervensi, seperti penerapan tarif progresif dan pandemi Covid-19. Penelitian ini bertujuan untuk menganalisis dampak intervensi terhadap jumlah penumpang Kereta Api Indonesia di Pulau Jawa dan Pulau Sumatra serta melakukan peramalan berdasarkan model terbaik antara Gaussian Autoregressive (AR) dengan Poisson Autoregressive (AR). Evaluasi kebaikan model dilakukan dengan membandingkan nilai RMSE dan MAPE pada masing-masing kandidat model. Model dengan nilai RMSE dan MAPE terkecil merupakan model terbaik. Hasil penelitian menunjukkan bahwa model intervensi Gaussian-AR merupakan model terbaik untuk meramalkan jumlah penumpang Kereta Api Indonesia. Model terbaik dengan Gaussian-AR untuk Pulau Jawa adalah model ARIMA (0,1,1)(0,1,1)^12 dengan (b1=1,s1=0,r1=0), (b2=0,s2=2,r2=2), dan (b3=0,s3=0,r3=1) sedangkan untuk Pulau Sumatra adalah model ARIMA ([1,34,35],1,1)(1,1,1)^12 dengan (b1=0,s1=3,r1=1) dan (b2=0,s2=2,r2=0) dimana kedua model tersebut sudah memenuhi asumsi residual berdistribusi normal. Hasil peramalan dengan menggunakan model intervensi Gaussian-AR pada data jumlah penumpang Kereta Api Indonesia di Pulau Jawa menunjukkan akan terjadi peningkatan jumlah penumpang pada akhir tahun 2023 sebesar 34.586.592 penumpang dan awal tahun 2024 sebesar 33.445.101 penumpang, sedangkan pada Pulau Sumatra menunjukkan akan terjadi peningkatan jumlah penumpang pada akhir tahun 2023 sebesar 638.020 penumpang dan awal tahun 2024 sebesar 630.426 penumpang.
=================================================================================================================================
Trains are one of the modes of public transportation that are widely used by the people of Indonesia. The state-owned company that manages and runs train operations in Indonesia is PT Kereta Api Indonesia (KAI). Train passenger count data is count time series data that contains discrete values. The number of train passengers is affected by a series of inputs called interventions, such as the implementation of progressive tariffs and the Covid-19 pandemic. This study aims to analyze the impact of interventions on the number of Indonesian Railways passengers on Java Island and Sumatra Island and conduct forecasting based on the best model between Gaussian Autoregressive (AR) and Poisson Autoregressive (AR). Evaluation of model goodness is done by comparing the RMSE and MAPE values of each candidate model. The model with the smallest RMSE and MAPE values is the best. The results show that the Gaussian-AR intervention model is the best model for forecasting the number of passengers of Indonesian Railways. The best model with Gaussian-AR for Java Island is the ARIMA model ARIMA (0,1,1)(0,1,1)^12 with (b1=1,s1=0,r1=0), (b2=0,s2=2,r2=2), and (b3=0,s3=0,r3=1) while for Sumatra Island is ARIMA model ([1,34,35],1,1)(1,1,1)^12 with (b1=0,s1=3,r1=1) and (b2=0,s2=2,r2=0) where both models have met the assumption of normally distributed residuals. The forecasting results using the Gaussian-AR intervention model on the data of the number of Indonesian Railway passengers on Java Island show that there will be an increase in the number of passengers at the end of 2023 of 34,586,592 passengers and the beginning of 2024 of 33,445,101 passengers, while on Sumatra Island it shows that there will be an increase in the number of passengers at the end of 2023 of 638,020 passengers and the beginning of 2024 of 630,426 passengers.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | Analisis Intervensi, Penumpang Kereta Api, Peramalan, Poisson Autoregressive, Forecasting, Gaussian Autoregressive, Intervention Analysis, Train Passengers. |
| Subjects: | Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry) Q Science > QA Mathematics > QA280 Box-Jenkins forecasting |
| Divisions: | Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis |
| Depositing User: | Nidya Putri Yudhani |
| Date Deposited: | 07 Feb 2024 03:50 |
| Last Modified: | 07 Feb 2024 03:50 |
| URI: | http://repository.its.ac.id/id/eprint/106328 |
Actions (login required)
 |
View Item |