Project Completion Announcement
PROJECT COMPLETED: Network-Based Credit Risk Models in P2P Lending Markets
I am delighted to announce the successful completion of the SNSF-funded research project (Grant 205487) on network-based credit risk models in peer-to-peer lending markets.
What we achieved: Over three years (Oct 2022 - Aug 2025), the project developed novel machine learning methodologies that leverage network topology to assess credit risk in P2P lending. The supervised network-based approach fundamentally advances how we understand borrower relationships and default prediction.
Key outcomes: 12 open-access Zenodo deposits | 2 PhD researchers trained | CHF 247,028 total funding | Publications in Expert Systems with Applications, Finance Research Letters, Quantitative Finance, Energy Economics
Core team: @Lennart John Baals | @Yiting Liu | @Branka Hadji Misheva | @Stefan Lyocsa
International collaborators: @Ali Hirsa (Columbia) | @Stephen Chan (AUS) | @Jeffrey Chu (Renmin) | @Yuanyuan Zhang (Manchester) | @Blanka Stadler (Masaryk)
Institutions: @BFH | @University of Twente | @SNSF | @COST Association
The research demonstrates that network position contains genuine predictive signal for default risk. A key finding: simple degree centrality often matches complex metrics like PageRank, offering practitioners an accessible entry point to network-based credit assessment.
#CreditRisk #P2PLending #MachineLearning #NetworkAnalysis #FinTech #OpenScience #SNSF #DigitalFinance #AI #XAI
Our Team
International cooperation between Bern Business School (Switzerland) and partner institutions
Principal Investigator
Prof. Dr. Joerg Osterrieder
Bern Business School, Switzerland
University of Twente, Netherlands
Professor of Finance and AI with 15+ years in quantitative finance. Chair of COST Action Fintech and AI in Finance. Coordinator of the MSCA Digital Finance doctoral network.
ORCID
Researcher
Lennart John Baals
Bern Business School, Switzerland
University of Twente, Netherlands
PhD researcher in Quantitative Finance focusing on credit risk assessment through graph-based models and network analysis in P2P lending markets.
Researcher
Prof. Dr. Branka Hadji Misheva
Bern Business School, Switzerland
Professor of Applied Data Science and Finance. Expert in AI applications in finance, XAI methods, network models and fintech risk management.
Researcher
Dr. Yiting Liu
Bern Business School, Switzerland
University of Twente, Netherlands
PhD researcher specializing in P2P lending risk modelling using graph-based approaches. Research interests include credit risk, digital finance, and network theory.
Research Project
Background
Peer-to-peer (P2P) lending has become an increasingly popular alternative to traditional bank lending, allowing individuals and businesses to borrow money directly from investors through online platforms without involving banks. While this method offers advantages such as higher returns for investors and greater access to credit for borrowers, it also brings unique risks. The decentralized nature of P2P lending means that loans are funded entirely by investors, without the safeguards of bank intermediation.Rationale
The growing presence of P2P lending markets, especially during economic crises, exposes these platforms to significant risks, including adverse selection and moral hazard. Unlike traditional banks that use long-term relationships and extensive data to evaluate borrowers, P2P platforms have less detailed information and face higher levels of uncertainty. There is a critical need for robust credit risk models that can accurately assess the creditworthiness of borrowers in these markets.Objectives
This project aims to develop advanced, interpretable credit risk models tailored specifically to the needs of P2P lending markets. These models will address the unique challenges of P2P lending, such as: - Higher information asymmetry - Less regulation compared to traditional banking - Increased risk during economic downturns The ultimate goal is to enhance trust between investors and P2P platforms by providing accurate tools for evaluating and mitigating credit risk.Methods
The project develops credit risk models using network-based approaches, analyzing the connections between borrowers and lenders to identify patterns that indicate heightened risk. These models incorporate: - Static factors: Established risk indicators - Dynamic factors: Real-time data for adaptive risk assessment - Network topology: Graph-based features capturing borrower-lender relationshipsExpected Impact
By providing more reliable credit risk models, this project will strengthen the P2P lending market, making it a more secure and viable alternative to traditional bank lending. The results will be valuable to: - P2P platforms and investors - Policymakers and regulators - Financial institutions - Academic researchersOpen Access Research Outputs (Zenodo)
12 Open-Access Deposits | All research materials freely available under CC-BY or MIT license
Working Papers & Journal Articles:
- Leveraging Network Topology for Credit Risk Assessment in P2P Lending - Expert Systems with Applications code/data [DOI]
- Network Evidence on Credit-Risk Pricing in P2P Lending - PhD Chapter 4 [DOI]
- State-Dependent Pricing in FinTech Credit: Evidence from P2P Lending - PhD Chapter 5 [DOI]
Reproducible Code & Data (Yiting Liu):
- Code: Network centrality and credit risk (Finance Research Letters) [DOI]
- Code: Leveraging network topology (Expert Systems with Applications) [DOI]
- Code: Credit Risk via GNN with Homophily-Guided Graph Construction [DOI]
- Code: Tree-based Interpretation Framework for R2-RD Models [DOI]
Conference Presentations (Lennart John Baals):
- COST FinAI Meets Istanbul Conference (May 2024) [DOI]
- 4th Int'l Symposium on Big Data and AI, Hong Kong (Dec 2024) - SLR on Graph-Based Credit Models [DOI]
- Bern Conference 2023 - Network Topology for Credit Risk [DOI]
- BFH Doctoral Seminar (Nov 2023) - Identifying Mispriced Loans [DOI]
Academic Records:
- PhD Qualifier Report and Presentation - University of Twente [DOI]
Project Timeline
Project Launch
SNSF CHF 207k
Training School
Enschede
COST Conference
Bern
Summer School
Delft
ERCIM/CFE
Berlin
Mobility Grants
CHF 40k
PhD School
Treviso
AI Finance
Istanbul
Big Data & AI
Hong Kong
PROJECT COMPLETE
12 Zenodo deposits
Datasets & Code
Research materials and code repositories from the projectP2P Network Analysis Code
Python implementation of network feature extraction and credit risk modeling
Bondora P2P Dataset (LoanData)
European P2P lending platform data (2009-2023) with loan performance metrics. Curated by Liu Yiting.
Network Centrality Toolkit
Implementation of degree, betweenness, and eigenvector centrality for credit scoring
LendingClub Dataset
US P2P lending data for comparative analysis and model validation
Project Documentation
Wiki with detailed methodology, results, and supplementary materials
News & Updates
View All News (30+ items) → | RSS
Successfully concluded the 3-year SNSF-funded research on network-based credit risk models. 12 Zenodo deposits, 2 PhD...
A related paper 'Leveraging network topology for credit risk assessment in P2P lending' has been published in Expert ...
A related paper 'Network centrality and credit risk: A comprehensive analysis of peer-to-peer lending dynamics' has b...
See all news, publications, conferences, and Zenodo releases →
Academic Events
The team has received invitations to numerous international conferences, serving roles as keynote speakers, session chairs, or organizing events.Conference Presentations
| Event | Date | Location | Contribution |
|---|---|---|---|
| AI Finance Insights: Pioneering the Future of Fintech | Sep 2024 | Istanbul, Turkey | Network-Based Prediction of Loan Default Risk |
| COST FinAI PhD School 2024 | May 2024 | Treviso, Italy | Workshop Organization |
| COST FinAI Brussels | May 2024 | Brussels, Belgium | Conference Organization |
| 16th ERCIM WG / 17th CFE Conference | Dec 2023 | Berlin, Germany | Leveraging network topology for credit risk |
| 8th European COST Conference on AI in Finance | Sep 2023 | Bern, Switzerland | Predicting Loan Default in P2P Lending |
| European Summer School in Financial Mathematics | Sep 2023 | Delft, Netherlands | Poster Presentation |
| COST Action Training School | Jun 2023 | Enschede, Netherlands | Workshop Organization |
Knowledge Transfer Events
| Event | Date | Location | Type |
|---|---|---|---|
| Expert Day Workshop | May 2024 | FHNW Campus Brugg-Windisch, Switzerland | Workshop |
| International Week, Shenzhen Technology University | Sep 2023 | Shenzhen, China | Talk |
Public Communication
| Activity | Year | Type | Reach |
|---|---|---|---|
| Shenzhen Technology University - International Week | 2024 | Talks/Events | International |
| MSCA Digital Finance | 2024 | Webpage, New Media | International |
| Shenzhen Technology University - International Week | 2023 | Talks/Events | International |
Use-Inspired Outputs
| Activity | Year | Sector | Description |
|---|---|---|---|
| REA Expert Reviewer | 2023 | European Commission | Expert reviewer for EISMEA programme |
| EIC Accelerator Expert | 2022 | European Commission | EIC Work Programme evaluator |
Collaborations
| Institution | Contact | Activities |
|---|---|---|
| Columbia University, USA | Prof. Ali Hirsa | Constructive exchanges, Publications, Personnel exchange |
| American University of Sharjah, UAE | Prof. Dr. Stephen Chan | Constructive exchanges, Publications, Personnel exchange |
| Renmin University, China | Prof. Dr. Jeffrey Chu | Constructive exchanges, Publications, Personnel exchange |
| University of Manchester, UK | Dr. Yuanyuan Zhang | Constructive exchanges, Publications |
| Masaryk University, Czech Republic | Dr. Blanka Stadler | Constructive exchanges, Publications |
Research Networks
COST Action CA19130 - Fintech and Artificial Intelligence in Finance - Action Chair: Joerg Osterrieder - In-depth constructive exchanges on approaches, methods, and results - Joint publications and personnel exchange MSCA Industrial Doctoral Network on Digital Finance - Coordinator: Joerg Osterrieder - Cross-institutional research collaboration - Doctoral training and knowledge transferThird-Party Funds
The team has acquired research funds from national and international organizations, including the Swiss National Science Foundation and Horizon Europe.SNSF Project Funding - Network-based Credit Risk Models (Main Grant)
207,028 CHF- Grant Number
- 205487
- Funding Scheme
- Weave/Lead Agency
- Grant Period
- 1 October 2022 - 31 August 2025
- Institution
- Bern University of Applied Sciences (BFH)
- Title
- Network-based credit risk models in P2P lending markets
- Team
- Joerg Osterrieder (PI); Lennart Baals, Yiting Liu (Researchers)
SNSF Mobility Grant 2024 / 1
20,000 CHF- Proposal Number
- 100018E_205487 / 3
- Grant Period
- 1 February 2024 - 31 August 2024
- Title
- Network-based credit risk models in P2P lending markets
- Team
- Lennart John Baals (PI); Joerg Osterrieder (Co-PI)
SNSF Mobility Grant 2024 / 2
20,000 CHF- Proposal Number
- 100018E_205487 / 2
- Grant Period
- 1 February 2024 - 31 August 2024
- Title
- Network-based credit risk models in P2P lending markets
- Team
- Yiting Liu (PI); Joerg Osterrieder (Co-PI)
Total Funding Secured: 247,028 CHF
Contact Us
Principal Investigator: Prof. Dr. Joerg Osterrieder
Institution: Bern University of Applied Sciences (BFH), Department of Business
Address: Bruckenstrasse 73, 3005 Bern, Switzerland