Predictive Analitycs Menggunakan Machine Learning Untuk Memprediksi Waktu Keterlambatan Berdasarkan Penyebab Keterlambatan Pada PT. Kereta Api Indonesia
Abstract
Abstract - PT. Kereta Api Indonesia (KAI) is a company that regulates trains in Indonesia. Railways in Indonesia still often experience delays, especially in the Cibatu Purwakarta lane which will be the object of research in this study. This research is intended as an initial stage of applying machine learning to overcome the problem of tardiness by providing the best model for predicting tardiness and what things are causing the tardiness pattern. Machine learning models considered are decision tree regression, support vector machine regression, random forest regression, ensemble learning, and gradient boosting regression. From the best machine learning techniques, a model will be made to predict the delay based on the cause of the delay.
Keywords – KAI, machine learning, predict the delay, cause of delay, Cibatu Purwakarta lane
Downloads
References
Robert N, Kim H, “Predictions of train delays using machine learning”, 2018
Ramashish G, Biplav S, “Estimating Train Delays in a Large Rail Network Using Zero Shot Markov Model, 2018
Pu W, Qing-peng Z,”Train delay analysis and prediction based on big data fusion”, 2019
William A R, Gary E, “The Team Data Science Process lifecycle”, 2020, diambil dari https://docs.microsoft.com/en-us/azure/machine-learning/team-data-science-process/lifecycle pada tanggal 2 Maret 2020 Pukul 15.31
T.Chai, R.R. Draxler, “Root mean square error (RMSE) or mean absolute error (MAE)? – Arguments against avoiding RMSE in the literature”, 2014
Aurelien G, “Hands On Machine learning With Scikit-Learn & Tensorflow”, 2017
Olsson NOE, Haugland H. Influencing factors on train punctuality—results from some Norwegian studies. Transp Policy 2004;11:387–397.
