Yuanyuan Zhang
Research Associate in Criminology
What are your research interest?
My research interests are in the general area of statistical modelling, extreme value theory and distribution theory with applications to finance. I am particularly interested in the applications to blockchain, decentralized finance (DeFi) and digital assets. My primary research has centered on the development of new statistical models and the applications of these models to address a diverse range of real-world challenges, especially those stemming from financial crimes.
What is the focus of your current research?
Currently at the CDTS, my main research project is to investigate the behaviours of anomalies and fraud in blockchain-based networks. We are currently developing new and improved methods for both static and dynamic anomaly detection that can be used alongside blockchain-based systems for real time fraud detection. The final product can also assist fraud agencies through an anomaly detection system with the ability to link anomalous activities on the blockchain to different types of crimes, which will benefit agencies in predicting and managing crime in the blockchain. This is a cross-disciplinary project in collaboration with the Digital Technologies and Crime, and the Advanced Mathematics research clusters.
What are some projects or breakthroughs you wish to highlight?
U.S Army - One of my research projects focused on investigating the statistical problem of “Bias reduction in the size estimation of big data”, and looked at improving the accuracy of estimators for the size of large datasets or hard to reach populations, respectively, where the true size is not known. This is an interesting and relevant problem in areas such as hidden databases, retail (size of a market), advertising (size of social networks or certain demographic groups), and networks (optimising network traffic). It has potential applications in the military, where the analysis of very large or small hidden populations is common but is not straightforward because of limited access to data due to restrictions on cost, time, and safety. We proposed four new population size estimators and their performances are compared in terms of bias with two existing methods in the big data literature. The results show improvements over recent estimators in the literature, especially when only small samples of data are available. The results are particularly beneficial in the context of time-critical decisions or actions. This research is published in the journal Computational Statistics & Data Analysis, and the general results could be used as input for other analysis in the military but also in the areas mentioned above. The research was part of the project supported by the U.S. Army Research Laboratory and the U.S. Army Research Office.
Blockchain - Bitcoin (whilst being built and based upon blockchain technology) can be treated as a technology (or technology firm) in itself. We investigated Bitcoin in finance but from the perspective of technology. We implemented a quantile-on-quantile regression approach to examine the relationship between both Bitcoin returns and technology stock returns, and stock market returns at varying quantiles. Evidence showed that Bitcoin may not be seen as a technology or technology stock, hence Bitcoin acts as a diversifier and a safe haven against technology stocks (published in Physica A: Statistical Mechanics and Its Applications).
What memberships and awards do you hold/have held in the past?
Memberships: Member of American Statistical Association (ASA), Institute of Mathematical Statistics (IMS) and International Chinese Statistical Association (ICSA).
Awards:
- Centre for Digital Trust and Society’s seed corn funding competition.
- Selected by the Scientific Review Board of the Council of the Hong Kong Laureate forum and the Government of the Hong Kong Special Administrative Region to present at the 2023 Young Scientist Forum on my research blockchain project.
- University of Manchester Global Scholars Fund 2023-2024.
- Institute of Mathematical Statistics (IMS) New Researcher Award.
- Henry Lester Trust Ltd Research Grant.
What is the biggest challenge in Digital Trust and Security now?
A significant challenge in the area of Digital Trust and Security is the emerging cybersecurity threats targeting Blockchain Technology (cryptocurrencies, non-fungible tokens (NFTs) and Decentralized Finance (DeFi)). The landscape of these threats is increasingly sophisticated, with perpetrators employing cutting-edge tactics in their attacks.
What real world challenges do you see Digital Trust and security meeting in the next 25 years?
I think the beginning of quantum computing could have massive potential disruption to encryption methods, challenging the very foundation of digital security. Quantum computers have the potential to break the cryptographic algorithms that currently secure data, the blockchain and communications.