Hybrid Predictive Modelling for Cargo Traffic Forecasting at Major and Non-Major Ports

Baghel, Pintoo Ramkis (2025) Hybrid Predictive Modelling for Cargo Traffic Forecasting at Major and Non-Major Ports. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (916kB) | Preview
Preview	PDF (Configuration Manual) Download (400kB) | Preview

Abstract

Precise forecasting and prediction of cargo traffic is essential for improving operational efficiency and long-term strategic planning at maritime ports (UNCTAD, 2023). In India, both major and non-major ports manage considerable volumes of cargo each month, making accurate prediction insights important for infrastructure, logistics optimization and management. This study introduces a hybrid forecasting model that integrates statistical, machine learning, and deep learning techniques which are ARIMA, XGBoost, and LSTM this is to improve and boost the accuracy of monthly cargo traffic predictions. The research uses publicly available datasets which covers monthly port-level cargo data across Indian states. Each forecasting model is trained and is validated using standard metrics such as and including RMSE, MAE, and MAPE. These individual predictions are then merged through a weighted ensemble method to generate the final output. The hybrid model is designed and tailored to account for linear trends, complex non-linear interactions, and temporal dynamics, addressing the limitations and shortcomings of individual models. This report outlines the design, conceptualization, development, and implementation of the proposed hybrid approach. The results demonstrate that the hybrid model consistently outperforms standalone/individual models in terms of predictive accuracy and robustness, particularly in capturing patterns exhibited across major and non-major ports. These improvements demonstrate that the hybrid model significantly improves forecasting accuracy across both major and non-major ports, offering valuable insights for stakeholders such as port authorities and logistics managers.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Basilio, Jorge UNSPECIFIED
Subjects:	Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning H Social Sciences > HE Transportation and Communications > Water Transportation > Shipping H Social Sciences > HD Industries. Land use. Labor > Business Logistics > Supply Chain Management H Social Sciences > HD Industries. Land use. Labor > Business Logistics > Transportation of Goods and Trade Logistics
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	30 Jun 2026 16:54
Last Modified:	30 Jun 2026 16:54
URI:	https://norma.ncirl.ie/id/eprint/9409

Actions (login required)

View Item