Cathy Yuen Yi Lee
Big data revolution is not about the quantity of data. It’s about now we can do something with the...
What qualification do you hold?
Master of Biostatistics, Bachelor of Advanced Mathematics (Honours Class I).
Supervisors:
Distinguished Professor Matt Wand and Distinguished Professor Louise Ryan
Research project title:
Machine learning approaches to longitudinal and multilevel data analysis.
Describe your research project
In today’s world, we are surrounded by data: from our digital interactions such as text messages and Facebook; from business transactions; and from government operations. Data are in different forms, come with different speed and uncertainty, and we refer them as “Big data”.
“Big data” is now a hot topic all around the world. These data have big benefits to our society, particularly in the fields of healthcare, scientific research and business development.
Big data revolution is not about the quantity of data. It’s about now we can do something with the data. With the fast growing in volume and complexity of these data, traditional methods are no longer adequate or too slow, and what we really need is improved statistical and computational methods, and not rely on storage growth or having a powerful computer, to make sure we make the most out of these data.
My thesis research focuses on developing efficient machine learning algorithms for analysing high volume/velocity data with complex structures that are often seen in the areas of public health, science and finance. My ultimate goal is to transform big data into big insight!
What is the aim of your project?
The aim of my thesis research is to develop sophisticated yet user-friendly machine learning algorithms for efficiently analysing large population-based administrative datasets, which typically have a complex grouped and hierarchical structure.
Why did you choose to pursue a research degree as opposed to going into the work force? Why this area of research?
Prior to my PhD, I have worked as a biostatistician for three years at the NSW Ministry of Health. While I really enjoyed the practical aspects of professional work I always knew I wanted to pursue a PhD one day, mainly for the following reasons:
- Curiosity - I wanted to explore my own boundaries and abilities in situations that are out of my comfort zone.
- Challenge - I enjoy problem solving, the harder, the better! Doing a PhD is a great way to challenge myself, push myself to new heights and achieve the impossible.
- Unpredictable - Unlike a day-to-day job, research is excitingly unpredictable. I face unexpected challenges every day!
What is your daily activity?
I am a very organised person and I like to set myself an agenda to accomplish at the end of everyday. I like reading literature and writing up thesis chapters in the morning when my mind is sharpest. I leave the things that I enjoy most in the afternoon, such as derivation of machine learning algorithms and coding/programming in R and Stan. At night, I like to work on small interesting side projects to further advance my analytical and coding skills.
What attracted you to research at UTS Science?
I have known my primary PhD supervisor, Professor Matt Wand, since 2010 when I did my Honours with him. I knew that he would be a great mentor for me to pursue my PhD goal. He is the one of the main reasons why I decided to do a PhD at UTS. My PhD co-supervisor, Professor Louise Ryan, is also a well-known statistician around the world. I strong believe working with both of them will help me grow as an independent researcher.
Moreover, the School of Mathematical and Physical Sciences within the Faculty of Science is a great supportive learning environment. We have discussion groups, workshops and seminars every week to discuss state-of-art statistical problems. This really helps me build a close bond with a lot of the academics and fellow students!
What is your future?
Through my research I have developed a passion for the analysis of large data and in particular, visualisation and translation. Upon completion of my PhD, I am seeking to advance my skills further through active collaboration and learning in a supportive and applied environment, perhaps a postdoctoral fellowship overseas!
