IJEBM | Predicting Operating Train Delays into New York City using Random Forest Regression and XGBoost Regression Models

Indexing and Abstracting

Predicting Operating Train Delays into New York City using Random Forest Regression and XGBoost Regression Models

Thomas Wiese

International Journal of Engineering, Business And Management(IJEBM), Vol-7,Issue-1, January - February 2023, Pages 34-41 , 10.22161/ijebm.7.1.5

Download | Downloads : 3 | Total View : 557

Article Info: Received: 15 Jan 2023; Received in revised form: 11 Feb 2023; Accepted: 20 Feb 2023; Available online: 28 Feb 2023

Abstract:

The Long Island Railroad operates one of the largest commuter rail networks in the U.S.[1]. This study uses data which includes the location and arrival time of trains based on onboard GPS position and other internal sources. This paper analyzes the GPS position of the train to gain insight into potential gaps in on time performance and train operations. This was done by developing a Random Forest Re-gression model [2] and an XGBoost regression model [3[. Both models prove to be useful to make such predictions and should be used to help railroads to prepare and adjust their operations.

Keywords:

Random Forest Regression model, XGBoost Regression Model, Machine Learning, Operations Man-agement, Management, Business Analytics, Analytics, Industrial Internet, Industrial Internet of Things, Trains, Train Delays, Decision Tree

References:

[1] Hinsdale EB. History of the Long Island Railroad Company, 1834-1898. Evening Post Job Printing House; 1898.
[2] Segal MR. Machine learning benchmarks and random forest regression.
[3] Kankanamge KD, Witharanage YR, Withanage CS, Hansini M, Lakmal D, Thayasivam U. Taxi trip travel time prediction with isolated XGBoost regression. In2019 Moratuwa Engineering Research Conference (MERCon) 2019 Jul 3 (pp. 54-59). IEEE.
[4] Wang R, Work DB. Data driven approaches for passenger train delay estimation. In2015 IEEE 18th International Conference on Intelligent Transportation Systems 2015 Sep 15 (pp. 535-540). IEEE.
[5] Koshiishi I. Maintenance issues for railway facilities and future prospects in maintenance. JR East Technical Review. 2014;29.
[6] Sajan GV, Kumar P. Forecasting and Analysis of Train Delays and Impact of Weather Data using Machine Learning. In2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT) 2021 Jul 6 (pp. 1-8). IEEE.
[7] Nilsson R, Henning K. Predictions of train delays using machine learning.
[8] Henderson G, Darapanemi V. Managerial uses of causal models of subway on-time performance. Transportation Research Record. 1994(1451).
[9] Chai T, Draxler RR. Root mean square error (RMSE) or mean absolute error (MAE)?–Arguments against avoiding RMSE in the literature. Geoscientific model development. 2014 Jun 30;7(3):1247-50.
[10] Zaniolo C. Database relations with null values. InProceedings of the 1st ACM SIGACT-SIGMOD symposium on Principles of database systems 1982 Mar 29 (pp. 27-33).
[11] Abdulla PA, Atig MF, Chen YF, Diep BP, Dolby J, Janků P, Lin HH, Holík L, Wu WC. Efficient handling of string-number conversion. InProceedings of the 41st ACM SIGPLAN Conference on Programming Language Design and Implementation 2020 Jun 11 (pp. 943-957).
[12] Coulston JW, Blinn CE, Thomas VA, Wynne RH. Approximating prediction uncertainty for random forest regression models. Photogrammetric Engineering & Remote Sensing. 2016 Mar 1;82(3):189-97.
[13] De Ville B. Decision trees. Wiley Interdisciplinary Reviews: Computational Statistics. 2013 Nov;5(6):448-55.
[14] Lehmann A, Overton JM, Leathwick JR. GRASP: generalized regression analysis and spat ial prediction. Ecological modelling. 2002 Nov 30;157(2-3):189-207.
[15] Chicco D. Ten quick tips for machine learning in computational biology. BioData mining. 2017 Dec;10(1):1-7.
[16] Bardenet R, Brendel M, Kégl B, Sebag M. Collaborative hyperparameter tuning. InInternational conference on machine learning 2013 May 13 (pp. 199-207). PMLR.
[17] Jin W, Li ZJ, Wei LS, Zhen H. The improvements of BP neural network learning algorithm. InWCC 2000-ICSP 2000. 2000 5th international conference on signal processing proceedings. 16th world computer congress 2000 2000 Aug 21 (Vol. 3, pp. 1647-1649). IEEE.