I am a postgraduate researcher in the Management division, Leeds University Business School, University of Leeds. Before being a member of the University of Leeds, I received my M.S. degree in Applied Statistics from Syracuse University, USA, and worked as a senior data analyst for Tongdun Technology, a leading professional third-party risk management and decision-making service provider in China. I was focusing on applying machine learning algorithms and big data integration techniques to data management and feature engineering to produce data products aimed at boosting the power of credit risk management for our clients. As a result, I successfully provided a whole package of professional SaaS products containing hundreds of features for thousands of clients. Also, I planned, organized, and directed specific data analysis projects and R&D projects, as well as negotiated among different departments to make sure these projects were on time and within scope.
My research is primarily concerned with applying machine learning to credit risk management in order to better determine the creditworthiness of potential customers in financial institutions.
- Machine learning in credit risk management
University of Leeds
Doctor of Philosophy - Management (2021 – present)
Master of Science - Applied Statistics (2013 – 2015)
Senior Data Analyst (2019 – 2021)
Applying machine learning algorithms and big data integration techniques on data management and feature engineering to produce data products aiming at boosting the power of credit risk management for our clients. Successfully provides a whole package of professional SaaS products containing hundreds of features for thousands of clients.
Planning, organizing and directing specific data analysis projects and R&D projects as well as negotiate among different departments to make sure these projects are on time and within scope.
Data Analyst (2015 – 2019)
Architected credit risk evaluation models based on professional experience and machine learning algorithms to mine valuable information lying under large batches of raw data.
Responsible for the programming of the Data Testing System, which could efficiently simulate the SaaS service, speed up the data testing process requested by potential clients and provide testing results without slow down or damaging the operation of the production environment.
Completed the code transformation of the Data Testing System from Python to PySpark and optimised the searching performance from hour level speed to minute level speed.
Led a 3-member team to deliver the Data Testing Service to thousands of potential clients.