Intelligent Data-Driven Methods for Demand and Price Prediction in the Shipping Industry

Ubaid, Ayesha

Intelligent Data-Driven Methods for Demand and Price Prediction in the Shipping Industry

Ubaid, Ayesha

Permalink

Publication Type:: Thesis
Issue Date:: 2021

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download contents and abstractAdobe PDF (814.02 kB)

Adobe PDF

Download thesisAdobe PDF (5.43 MB)

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Ubaid, Ayesha
dc.date.accessioned	2022-01-13T23:53:06Z
dc.date.available	2022-01-13T23:53:06Z
dc.date.issued	2021
dc.identifier.uri	http://hdl.handle.net/10453/153082
dc.description	University of Technology Sydney. Faculty of Engineering and Information Technology.	en_US.UTF-8
dc.description.abstract	Machine Learning has found its applications in many industrial and commercial domains. However, there are few ignorant industries that still lack digitization and require fusion of AI into their processes. Once such industry is the container-shipping industry. The global supply chain is complex, with cargo volumes that are highly seasonal driven by events, consumer related, Christmas and Chinese New Year, agriculture harvests further impacted by extreme weather occurrences and changes to the Geo, Political regulatory environment affecting trade. In contrast, supply, the shipping capacity is fixed in the short run; this results in periods of mismatched supply and demand and therefore shipping price volatility. The Shipping lines are trapped by the current spot market pricing practice of using date validity and not the vessel voyage. This causes a disconnect between price, demand and supply, a problem that is compounded by the shipping line’s enterprise systems. Entrenched operational silos within the lines are resulting in missed revenue opportunities through a lack of real time visibility into the availability of equipment and vessel space which are key inputs to price decisions. Forty percent of all shipping containers moved around the world are purchased on the short-term spot market; their commercial terms are set manually with emails and phone calls. Spot market price should be a product of supply and demand. However, the industry as a whole has little visibility into the state of the market in real time, and carriers are making sub optimal pricing decisions and their customer procurement decisions because of this. Australian Linear Shipping industry is lacking digitization hence the visibility into the industry statistics is missing. Without real time visibility of the market as a whole, future spot pricing decisions are based mainly on a carrier's internal assessment of current and future booking build up and net contribution targets. This can, and usually does, present a different and misleading picture of market conditions. With the limited market wide information and inability to use vessel voyage specific price as a lever to steer the cargo opportunity to the optimum vessel sailing, opportunity cost materializes. In this research, we want to empower Australian Container Shipping Industry with machine learning capabilities to provide a market wide view of current and future demand (both for short-term and long-term), optimal spot pricing model and machine learning based prices prediction model that can predict spot pricing based on current demand and available capacity (supply).	en_US.UTF-8
dc.format	Thesis (PhD)
dc.language.iso	en_US	en_US.UTF-8
dc.relation	https://opus.lib.uts.edu.au/bitstream/10453/153082/2/02whole.pdf
dc.rights	info:eu-repo/semantics/openAccess
dc.rights	The author owns the copyright in this thesis including all reproduction and reuse rights for the work. The work may not be altered without the permission of the copyright owner. Attribution is essential when quoting or paraphrasing from this thesis.
dc.rights	au.edu.uts.lib/ppc
dc.title	Intelligent Data-Driven Methods for Demand and Price Prediction in the Shipping Industry	en_US.UTF-8
dc.type	Thesis
utslib.copyright.status	open_access	*

Abstract:

Machine Learning has found its applications in many industrial and commercial domains. However, there are few ignorant industries that still lack digitization and require fusion of AI into their processes. Once such industry is the container-shipping industry. The global supply chain is complex, with cargo volumes that are highly seasonal driven by events, consumer related, Christmas and Chinese New Year, agriculture harvests further impacted by extreme weather occurrences and changes to the Geo, Political regulatory environment affecting trade. In contrast, supply, the shipping capacity is fixed in the short run; this results in periods of mismatched supply and demand and therefore shipping price volatility. The Shipping lines are trapped by the current spot market pricing practice of using date validity and not the vessel voyage. This causes a disconnect between price, demand and supply, a problem that is compounded by the shipping line’s enterprise systems. Entrenched operational silos within the lines are resulting in missed revenue opportunities through a lack of real time visibility into the availability of equipment and vessel space which are key inputs to price decisions. Forty percent of all shipping containers moved around the world are purchased on the short-term spot market; their commercial terms are set manually with emails and phone calls. Spot market price should be a product of supply and demand. However, the industry as a whole has little visibility into the state of the market in real time, and carriers are making sub optimal pricing decisions and their customer procurement decisions because of this. Australian Linear Shipping industry is lacking digitization hence the visibility into the industry statistics is missing. Without real time visibility of the market as a whole, future spot pricing decisions are based mainly on a carrier's internal assessment of current and future booking build up and net contribution targets. This can, and usually does, present a different and misleading picture of market conditions. With the limited market wide information and inability to use vessel voyage specific price as a lever to steer the cargo opportunity to the optimum vessel sailing, opportunity cost materializes. In this research, we want to empower Australian Container Shipping Industry with machine learning capabilities to provide a market wide view of current and future demand (both for short-term and long-term), optimal spot pricing model and machine learning based prices prediction model that can predict spot pricing based on current demand and available capacity (supply).

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/153082