Dr Yu Liu

Biography

Yu (Jackie) Liu received B.S. and M.S. degrees from Civil Aviation University of China and South China University of Technology in 2007 and 2010. She joined the Department of Statistics in 2012 and graduated in 2016. Her PhD thesis is "Shaped restricted density estimation for financial data". She joined the Faculty of Education and Social Work, Woolf Fisher Research Centre in 2016 as a Data Analyst.

10/2016 – present        Data Analyst, the University of Auckland

06/2016 – 10/2016       Quantitative Analyst, Marathon Fund Management Limited

06/2016 – 10/2016       Data Analyst, Orix New Zealand Limited

06/2012 – 06/2016       Programmer/Graduate Teaching Assistant, the University of Auckland

02/2010 – 03/2011        Analyst, Bank of China

Research | Current

Liu, Y. and Wang, Y.(2017), A fast algorithm for log-concave density estimation. Aust. N. Z. J. Stat. 60(2), 2018, 258–275.

Liu, Y. and Wang, Y.(2015) R package "cnmlcd" to R CRAN, https://cran.r-project.org/web/packages/cnmlcd/index.html.

Liu, Y.(2015), A fast algorithm for log-concave density estimation. JSM conference, Seattle, USA

Liu, Y.(2014), Smooth density estimation under shape restrictions. Joint NZSA + ORSNZ conference, Hamilton, New Zealand.

Teaching | Current

Assistance for STATS 10X  and STATS 20X.

Responsibilities

Data Analyst in Woolf Fisher Research Centre, University of Auckland.

• Create database. e.g., data collection, data clean, database management.
• Create and design analysis plan to provide rationale and research decisions made.
• Coding and analysing data from a variety of instruments including surveys and observations as directed.
• Develope online assessment system for our clients to DIY their analysis reports.

Areas of expertise

Her research investigates the features of financial data, non-parametric density estimation with and without shape restrictions. A new algorithm for the log-concave density estimation has be proposed. It  is also extended to the heavy-tailed and high peaked density estimation. All the algorithms has been developed as packages for easy applications.

She is also an experienced data scientist with a solid background in statistics, math and financial engineering. Her skills in data analysis and knowledge of the financial market give her an edge in working on projects that require cross-disciplinary expertise. She has showcased her exceptional data analysis skills in a variety of projects across industries ranging from education, banking, retailing and financial investment. The skills include, but are not limited to:                                    

• Strong computational linguistics knowledge: many years' experience in R, SPSS, SAS, SQL, and Python.
• Statistics Background: Solid knowledge of statistic modeling, machine learning, classification, structure equation modeling, categorical/spatial data analysis and optimal algorithms.
• Financial Engineering Background: Profound knowledge in data mining/statistics, stochastic process, risk management, pricing convertible bonds with credit risk, and other issues related to the financial market.
• Commercial data analysis experience: Many years of experience in customer insight analysis and customer segmentation large companies.