Decoding the Game: A Quantitative Analysis of Market Manipulation and Machine-Human Interactions

Deng, Xinyi

Decoding the Game: A Quantitative Analysis of Market Manipulation and Machine-Human Interactions

Deng, Xinyi

Permalink

Publication Type:: Thesis
Issue Date:: 2024

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download thesisAdobe PDF (1.97 MB)

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Deng, Xinyi
dc.date.accessioned	2024-06-20T03:43:43Z
dc.date.available	2024-06-20T03:43:43Z
dc.date.issued	2024
dc.identifier.uri	http://hdl.handle.net/10453/179591
dc.description	University of Technology Sydney. Faculty of Business.	en_US.UTF-8
dc.description.abstract	The financial markets have experienced a technology revolution, resulting in innovations such as the advent of limit order books, increased social media use in investment decisions, and expanded FinTech services. This dissertation investigates market manipulation and machine-human interactions within this modern finance landscape. Chapter 2 introduces Q-learning, a novel machine learning technique, to explore its impact on strategic trading behavior in a dynamic limit order market. In equilibrium, informed traders learn to manipulate the market by using market buys (resp. sells) to trigger uninformed market buys (resp. sells) to enhance profitability of later informed limit sells (resp. buys). Chapter 3 analyses meme investing, a retail buying frenzy coordinated through social media, and its effect on investment efficiency. Modeling the frenzy as short-sale frictions reveals that small costs on short sellers can improve investment efficiency, while higher costs or bans harm it. Chapter 4 investigates the impact of growth in quantitative investing on price efficiency. Quants tend to trade more (resp. less) aggressively due to greater information processing (resp. weaker flexibility to adapt to market conditions) than discretionary traders. Consequently, the price efficiency is non-monotonic with respect to the level of quant trading.	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/10453/179591/1/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	© 2024 Xinyi Deng
dc.rights	au.edu.uts.lib/cph
dc.title	Decoding the Game: A Quantitative Analysis of Market Manipulation and Machine-Human Interactions	en_US.UTF-8
dc.type	Thesis
utslib.copyright.status	open_access	*

Abstract:

The financial markets have experienced a technology revolution, resulting in innovations such as the advent of limit order books, increased social media use in investment decisions, and expanded FinTech services. This dissertation investigates market manipulation and machine-human interactions within this modern finance landscape. Chapter 2 introduces Q-learning, a novel machine learning technique, to explore its impact on strategic trading behavior in a dynamic limit order market. In equilibrium, informed traders learn to manipulate the market by using market buys (resp. sells) to trigger uninformed market buys (resp. sells) to enhance profitability of later informed limit sells (resp. buys). Chapter 3 analyses meme investing, a retail buying frenzy coordinated through social media, and its effect on investment efficiency. Modeling the frenzy as short-sale frictions reveals that small costs on short sellers can improve investment efficiency, while higher costs or bans harm it. Chapter 4 investigates the impact of growth in quantitative investing on price efficiency. Quants tend to trade more (resp. less) aggressively due to greater information processing (resp. weaker flexibility to adapt to market conditions) than discretionary traders. Consequently, the price efficiency is non-monotonic with respect to the level of quant trading.

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

http://hdl.handle.net/10453/179591