Back to search

Rochester Institute of Technology

Optimizing Delivery Time Predictions Using Machine Learning: A Data-driven approach to Last-mile Logistics

Abstract

dc:description.abstract

This paper addresses how machine learning can be utilized to improve the prediction of delivery times during the last mile, specifically in Dubai urban logistics issues whereby the traffic congestion and weather circumstances usually contribute to unpredictable delivery times. The main goal was to evolve machine learning models that can predict properly delivery time depending on several parameters, i.e., speed of traffic, weather, length of delivery, and geography. The reason why three machine learning models were chosen [Random Forest, Gradient Boosting, and XGBoost] in this analysis is that they have the opportunity to work with non-linear relationships in the data. Models were trained and assessed based on the Metrics of the Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and the R-Squared (R 2 ). The findings indicated that Grade Boosting was more effective in comparison with the other models through the highest R2 of 0.6384. Geospatial analysis was also used in the research to examine how the location of delivery affected the delivery time. Through the geocoding of delivery points and mapping of their presence, which exposed the geographic regions in which the delivery was comparatively longer due to various factors, including, but not limited to traffic issues and weather pattern. The results show that the efficiency of last-mile delivery operations can be substantially increased by the real-time data integration, better feature engineering, and spatial optimization. The research adds to the body of knowledge focusing on data-based logistics and offers practical recommendations that the logistics firms could use to improve their finetuning delivery time estimations and efficiency of their operations.

Degree

thesis:*
Name thesis:degree_name
Professional Studies (MS)
Level thesis:degree_level
Thesis
Discipline thesis:degree_discipline
Graduate Programs & Research

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Burqaiba, Mohamed
Contributors dc:contributor
  • Parthasarathi Gopal

Subjects

dc:subject × 13

Identifiers

dc:identifier.*
Repository record dc:identifier
https://repository.rit.edu/theses/12473

Chain of custody

source
Harvested from
Rochester Institute of Technology
Base URL
repository.rit.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Burqaiba, Mohamed. Optimizing Delivery Time Predictions Using Machine Learning: A Data-driven approach to Last-mile Logistics. Thesis thesis, https://repository.rit.edu/theses/12473