-->

Lecture 6 - Shipping data, statistical analysis and machine learning

Welcome

This lecture centers around two main practical exercises.

For the first part, we will discuss where to obtain shipping data, what potential it offers for analytics, and the limitations you should be aware of when using it. We will explore real-world examples understand how data analytics could be used to address various challenges in the shipping industry. The practical exercise will focus on how to detect and handle outliers that could affect the quality of the data, as well as methods for aggregating and segregating data for analysis.

In the second part, we will introduce the basic concepts of machine learning and explain how these can be applied to shipping data. The practical exercise for this part will involve comparing the performance of traditional statistical models with machine learning models, helping you understand their respective pros and cons.

What you’ll learn from this lecture

  • Segregation, aggregation, and interpretation of the shipping data
  • Intro to Machine Learning
  • Shipping research/apps implementation
  • Outliers detection for shipping data
  • The fundamentals of shipping data (sources, potential, limitations, etc.)
  • Machine learning vs statistics

Learning Outcomes

Skills
  • Finds, synthesizes, and presents information on the international shipping
  • Can communicate with industry practitioners using correct terminology
Competency
  • Translates statistics into managerial insight
  • Exchanges opinions and experiences with others with a background in the field
Knowledge
  • Is familiar with recent development in data-driven analysis applied to the freight markets and ship operation
  • Is conversant on technical aspects of shipping digital platforms
  • Understand the main results in recent research within shipping economics and analytics

Yang, Wu, L., Wang, S., Jia, H., & Li, K. X. (2019). How big data enriches maritime research - a critical review of Automatic Identification System (AIS) data applications. Transport Reviews, 39(6), 755–773. https://doi.org/10.1080/01441647.2019.1649315

Adland. R. (2021). Shipping Economics and Analytics. In Artikis, A., & Zissis, D. (Eds.), Guide to Maritime Informatics (pp. 319–333). Springer International Publishing

Pensum

Generating Bunkering Statistics from AIS data