Yiting Liu (刘奕霆)

Yiting Liu, currently a Ph.D. researcher at the University of Twente, is delving into the intricacies of P2P lending risk modelling, a pivotal field at the intersection of finance and data analytics. With a comprehensive background in statistics and quantitative finance, he graduated with distinction from the Alliance Manchester Business School, University of Manchester, after completing his undergraduate studies at Fudan University’s School of Management.

During his academic career, Yiting has been actively engaged in research projects that demonstrate his analytical acumen. Notably, his work on optimizing e-shopping service systems via man-machine cooperation addressed key efficiency improvements in customer service operations. Additionally, his innovative approach to extending the Bradley-Terry model provided new insights into paired data analysis. These projects underscore his dedication to advancing quantitative methods and risk assessment in financial contexts.

Credit Risk Modeling; Graph Theory; P2P Lending

• Liu, Y., Osterrieder, J., Hadji Misheva, B., et al. (2023). Navigating the Environmental, Social, and Governance (ESG) landscape: Constructing a robust and reliable scoring engine - Insights into Data Source Selection, Indicator Determination, Weighting and Aggregation Techniques, and Validation Processes for Comprehensive ESG Scoring Systems. Open Research Europe, 3(119). https://doi.org/10.12688/openreseurope.16278.1
• Liu, Y., Baals, L. J., Liu, Y., Osterrieder, J., & Hadji-Misheva, B. (2023). Leveraging Network Topology for Credit Risk Assessment in P2P Lending: A Comparative Study under the Lens of Machine Learning. Manuscript submitted for publication to Expert Systems with Applications.
• Liu, Y., Baals, L. J., Liu, Y., Osterrieder, J., & Hadji-Misheva, B. (2023). Dual Centrality Measures in Network for Enhanced Default Prediction in P2P Lending. Manuscript to be submitted for publication to Finance Research Letters.
• Liu, Y., Baals, L. J., Liu, Y., Osterrieder, J., & Hadji-Misheva, B. (2023). Alpha Threshold Tuning: An Edge Pruning Approach to Network Simplification for Improved Default Prediction in P2P Lending. Manuscript to be submitted for publication to Finance Research Letters.

• Membership , MSCA Industrial Doctoral Network: Digital Finance, 2023 - 2027.
• Hired PhD student, Swiss National Science Foundation (SNSF) project: Network-based credit risk models in P2P lending markets. 2022 - 2025.
• Membership, COST Action CA19130 Fintech and AI in Finance, 2022 – 2025.

• Enschede, Netherlands: COST Action FinAI: FinTech and AI in Finance – Training School: Predicting Loan Default in P2P lending: A Comparative Analysis. June 12 - 16, 2023; Enschede, Netherlands.
• Shenzhen Technology University - International Week: Basic Concepts of Machine Learning. September 11 - 15, 2023; Shenzhen, China.
• COST 8th European COST Conference on Artificial Intelligence in Finance: Predicting Loan Default in P2P lending: A Comparative Analysis. September 27 - 29, 2023; Bern, Switzerland.
• 17th International Conference on Computational and Financial Econometrics (CFE 2023): Threshold Tuning: An Edge Pruning Approach to Network Simplification for Improved Default Prediction in P2P Lending. December 16 - 18, 2023; Berlin, Germany.

• COST FinAI Meets Brussels (May 15 - 16, 2023; Brussels, Belgium)

• European Summer School in Financial Mathematics (September 4 - 8, 2023; Delft, Netherlands)

November, 2022 - Now: PhD student at University of Twente.

September 2021-October 2022: Master of Science, Quantitative Finance. Alliance Manchester Business School, University of Manchester. Graduate with Distinction.

June 2017-June 2021: Bachelor of Science, Statistics. School of Management, Fudan University.