Machines in markets: The impacts of technology on stock valuation and trading

Do, Bao Linh

Machines in markets: The impacts of technology on stock valuation and trading

Do, Bao Linh

Permalink

Publication Type:: Thesis
Issue Date:: 2023

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download thesisAdobe PDF (4.87 MB)

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Do, Bao Linh
dc.date.accessioned	2024-04-16T00:54:04Z
dc.date.available	2024-04-16T00:54:04Z
dc.date.issued	2023
dc.identifier.uri	http://hdl.handle.net/10453/177933
dc.description	University of Technology Sydney. Faculty of Business.	en_US.UTF-8
dc.description.abstract	This thesis examines the implications and applications of technology in finance, specifically in the areas of fundamental valuation of stocks, market efficiency, and market manipulation. The first chapter discusses the application of machine learning in company valuation. The chapter uses a tree-based model to demonstrate that interactions among firm fundamentals play a large role in predicted value. Certain interactions are important in accurately valuing companies and have a sound conceptual basis. The second chapter explores a new dimension of market efficiency. We propose non-linear market efficiency as an orthogonal dimension to the original Efficient Markets Hypothesis (EMH) – for a given information set, how well do stock prices incorporate increasingly complex combinations of the information. We attribute the increase in non-linear market efficiency to improvements in technology. The third chapter examines layering and spoofing, which refers to the use of non-bona-fide orders in a market to cause a better execution price on a bona-fide order from the same trader. Using a global sample of hand-collected data from prosecuted cases, we develop empirical metrics to detect layering and spoofing and test their accuracy using out-of-sample cross-validation. Overall, this thesis contributes to the literature by using advances in data science techniques to shed new light on core topics in finance – revealing nonlinearity in company valuation, developing a new market efficiency dimension, and building a detection model for a new, algorithmic type of market manipulation.	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/10453/177933/1/thesis.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	© 2023 Bao Linh Do
dc.rights	au.edu.uts.lib/cph
dc.title	Machines in markets: The impacts of technology on stock valuation and trading	en_US.UTF-8
dc.type	Thesis
utslib.copyright.status	open_access	*

Abstract:

This thesis examines the implications and applications of technology in finance, specifically in the areas of fundamental valuation of stocks, market efficiency, and market manipulation. The first chapter discusses the application of machine learning in company valuation. The chapter uses a tree-based model to demonstrate that interactions among firm fundamentals play a large role in predicted value. Certain interactions are important in accurately valuing companies and have a sound conceptual basis. The second chapter explores a new dimension of market efficiency. We propose non-linear market efficiency as an orthogonal dimension to the original Efficient Markets Hypothesis (EMH) – for a given information set, how well do stock prices incorporate increasingly complex combinations of the information. We attribute the increase in non-linear market efficiency to improvements in technology. The third chapter examines layering and spoofing, which refers to the use of non-bona-fide orders in a market to cause a better execution price on a bona-fide order from the same trader. Using a global sample of hand-collected data from prosecuted cases, we develop empirical metrics to detect layering and spoofing and test their accuracy using out-of-sample cross-validation. Overall, this thesis contributes to the literature by using advances in data science techniques to shed new light on core topics in finance – revealing nonlinearity in company valuation, developing a new market efficiency dimension, and building a detection model for a new, algorithmic type of market manipulation.

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

http://hdl.handle.net/10453/177933