Система будет остановлена для регулярного обслуживания. Пожалуйста, сохраните рабочие данные и выйдите из системы.
dc.contributor.author | Rakhymberdiyev, Alikhan![]() |
|
dc.contributor.author | Akbarov Alisher![]() |
|
dc.contributor.author | Sekerbayev, Amir![]() |
|
dc.contributor.author | Amantayev, Daniyar![]() |
|
dc.contributor.author | Kamaliyeva, Zhuldyz![]() |
|
dc.date.accessioned | 2024-05-19T11:12:16Z | |
dc.date.available | 2024-05-19T11:12:16Z | |
dc.date.issued | 2024-04-24 | |
dc.identifier.citation | Rakhymberdiyev, A., Akbarov A, Sekerbayev A., Amantayev D., Kamaliyeva Zh. (2024) Predicting expected time of arrival of freight wagons. Nazarbayev University School of Engineering and Digital Sciences | en_US |
dc.identifier.uri | http://nur.nu.edu.kz/handle/123456789/7678 | |
dc.description.abstract | The industry of freight transportation in Kazakhstan is one of great importance for both the economy and political status of the country. To improve the current situation in the industry and planning aspects of wagon management, digitalization changes can be introduced with the help of data mining and machine learning algorithms. A collaboration with the local Multicode company was established to help them improve wagon management. Multicode is a startup company that provides a platform for wagon owners to help them manage the service of wagons. The problem is that freight wagons frequently come to the stations with delays because the Expected Time of Arrival (ETA) is estimated inaccurately. The aim of the project is to build a precise model that predicts ETA based on the historical data and describe managerial implications for this model in the Multicode company. We managed to create a machine learning model based on the XGBoost regressor. The tuned version of XGBoost regressor decreased Mean Absolute Error of ETA from 147 hours to 5.7 hours. End-to-end product was created with the result of a functioning interface that returns ETA prediction to a request with specified wagon parameters. From a managerial perspective precise prediction of ETA helps to enhance decision-making for wagon owners, improves customer satisfaction for the customers that transport their goods, and provides efficient logistic management. | en_US |
dc.language.iso | en | en_US |
dc.publisher | Nazarbayev University School of Engineering and Digital Sciences | en_US |
dc.rights | Attribution-NonCommercial-NoDerivs 3.0 United States | * |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/3.0/us/ | * |
dc.subject | Type of access: Restricted | en_US |
dc.subject | Machine Learning | en_US |
dc.subject | Feature Engineering | en_US |
dc.subject | ETA Prediction | en_US |
dc.subject | Freight Wagons | en_US |
dc.subject | XGBoost | en_US |
dc.subject | Railway Logistics | en_US |
dc.subject | Data Analysis | en_US |
dc.title | PREDICTING EXPECTED TIME OF ARRIVAL OF FREIGHT WAGONS | en_US |
dc.type | Master's thesis | en_US |
workflow.import.source | science |
The following license files are associated with this item: