AIS-data & Machine Learning - A Quantitative Approach to Predicting Freight Rates - Master thesis

Aug 4, 2026

Upload by Maeve

The thesis investigates how Automatic Identification System (AIS) data can improve route-specific freight rate prediction within maritime shipping. With the rise of real-time tracking and extensive AIS availability, the study positions AIS-derived variables as a potential decision-support input for researchers and practitioners. Using machine learning models alongside additional non-AIS variables expected to affect freight rates, the work evaluates predictive performance and compares contributions. Results show AIS-derived data can add some incremental value, though the additional contributory effect is negligible in the examined case.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages67

Reading Time2 h 49 min

AccessFree to download

Maritime Economics and Tanker Shipping

Literature Review

Data

Methodology

Norwegian School of Economics Bergen, Autumn 2023 AIS-data & Machine Learning A Quantitative Approach to Predicting Freight Rates Ole Fredrik Odfjell & Magnus Haugland Supervisor: Jonas Andersson Master thesis, Economics and Business Administration Business Analytics NORWEGIAN SCHOOL OF ECONOMICS This thesis was written as a part of the Master of Science in Economics and Business Administration at NHH. Please note that neither the institution nor the examiners are responsible – through the approval of this thesis – for the theories and methods used, or results and conclusions drawn in this work. Acknowledgements This thesis is written as a part of our Master of Science degree in Economics and Business Administration within our major in Business Analytics at Norwegian School of Economics. This thesis summarizes our ﬁve years attending Norwegian School of Economics, and weare grateful for the excellent opportunity to meet remarkable people and learn from some of the best professors in the conﬁnes of the economic ﬁeld. During these ﬁve years, we have gained insight and aspiration through past courses to explore the shipping industry further and thus contribute to research embedded in this ﬁeld. We sincerely thank our supervisor, Professor Jonas Andersson, for encouraging us to write within the shipping ﬁeld and for his guidance and constructive feedback throughout the semester. His advice has given us valuable insight and motivation for a seamless realization of this thesis. Additionally, we thank Assistant Professor Gabriel Moises Fuentes from the Department of Business and Management Science for providing the AIS data used in this thesis. Norwegian School of Economics Bergen, December 2023 Ole Fredrik Odfjell Magnus Haugland Abstract The emerging availability of data and the development of real-time tracking systems, also known as AIS, have engaged a new ﬁeld of study within the shipping segment. AIS data has a pivotal role in enhancing safety at sea. Moreover, the accessibility of real-time data over the majority of merchant vessels around the world has instigated researchers to investigate how to adopt this information to create further value in the decision-making process. Together with machine learning methodologies and data processing capability, this thesis aspires to contribute to further investigate the deployment of AIS-derived data. More speciﬁcally, we will examine the predictive ability of AIS data on a route-speciﬁc freight rate. In addition to AIS variables, we have included other data expected to inﬂuence freight rate, and the results from a series of machine learning models have been thoroughly examined. Our results indicate that AIS-derived data oﬀer some additional value when predicting the freight rate. However, in this exact case, the additional contributory value is negligible. Keywords – Business Analytics, NHH, Machine Learning, Shipping, AIS, Master thesis, Maritime Economics Contents 1 Maritime Economics and Tanker Shipping 1 1. 1 Maritime Economics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.1.1 Shipping Segments .......................... 2 1.1.2 Four Shipping Markets ........................ 2 1.1.3 Stakeholders . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 1.1.4 The Shipping Market Model 3 1.1.5 Freight Rate Mechanism . . . . . . . . . . . . . . . . . . . . . . . 4 1.1.6 Supply and Demand Curves 5 1.2 Global Tanker Trade . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 1.2. 1 Tanker Supply 7 1.2.2 Tanker Demand . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 1.2.3 Freight Contract Agreement 9 1.2.4 Worldscale . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 2 Literature Review 12 2. 1 Literature review . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 2.1.1 Freight rate dynamics . . . . . . . . . . . . . . . . . . . . . . . . 12 2.1.2 S

FAQs

What is the main objective of the thesis?

To assess the predictive ability of AIS data for a route-specific freight rate using machine learning models.

Which data sources are used for freight rate prediction?

AIS-derived variables are combined with other non-AIS data expected to influence freight rates.

Do AIS-derived variables significantly improve prediction results?

AIS-derived data provides some additional value, but in the specific case studied the incremental contribution is negligible.

Aug 4, 2026

Upload by Maeve