Branka Hadji Misheva
Prof. Dr. Branka Hadji Misheva Professor of Applied Data Science and Finance Bern Business School Institute of Applied Data Science & Finance Brückenstrasse 73, 3005 Bern, Switzerland E-mail: branka.hadjimisheva@bfh.ch
About
Prof. Dr. Branka Hadji Misheva is a Professor in Applied Data Science and Finance at BFH, working on AI applications in finance, XAI methods, network models and fintech risk management. She holds a PhD in Economics and Management of Technology with a specific focus on network models as they apply to the operation and performance of P2P lending platforms, from the University of Pavia, Italy. She leads/co-leads many research and innovation projects among which the notable examples are:
Two larger EU funded projects: Fintech-ho2020: A FINancial supervision and TECHnology compliance training programme and COST Action Finance & Artificial Intelligence for Finance. The budget that was associated for these projects was 2.5 mil CHF and 1 mil CHF, respectively.
Two Innosuisse projects: (lead) Towards Explainable Artificial Intelligence and Machine Learning in Credit Risk Management [5], and (project partner) DataInc - Intelligent Data Integration and Cleaning. Both project jointly had a budget of 850,000 CHF. Both projects aim to provide state-of-art AI-based solutions to persisting problems in financial risk management (i.e. accurate and trustworthy assessment of credit risk and high level of data quality).
An SNF Weave project on Network-based scoring models for P2P systems. The budget associated with this project is 350,000 CHF.
She has furthermore participated in the acquisition of over 20 SNF, Innosuisse and EU projects and published a variety of papers related within the different research proposals Prof. Hadji Misheva is also research author of over 25 papers in the field of credit risk modeling, graph theory, predictive performance of scoring models, lead behavior in crypto markets and explainable AI models for credit risk management.
Key Achievements and Outputs
Within the last 5 years, I have lead/co-lead many research and innovation projects among which the notable examples are: - Two larger EU funded projects: Fintech-ho2020: A FINancial supervision and TECHnology compliance training programme; and COST Action Finance & Artificial Intelligence for Finance. The budget that was associated for these projects was 2.5 mil CHF and 1 mil CHF, respectively.
- Two Innosuisse projects: (lead) Towards Explainable Artificial Intelligence and Machine Learning in Credit Risk Management [5], and (project partner) DataInc
- Intelligent Data Integration and Cleaning. Both project jointly had a budget of 850,000 CHF. Both projects aim to provide state-of-art AI-based solutions to persisting problems in financial risk management (i.e. accurate and trustworthy assessment of credit risk and high level of data quality).
- An SNF Weave project on Network-based scoring models for P2P systems. The budget associated with this project is 350,000 CHF.
I currently hold the role of Scientific Grant Holder of the COST Action: Fintech and Artificial Intelligence for Finance. As part of my role, I have been co-leading a research network of over 370 researchers from 51 countries and managing a budget of 1 mil CHF distributed over a period of 4 years.
Within this project, the network has produced over 140 research works within the last three years and has organised over 300 workshops, conferences and events around Europe (attended jointly by over 6000 participants). As part of my role in this project, I have played a key role in setting up research objectives focusing on using state-of-art AI tools for financial risk management. I have furthermore organised and co-organised many research conferences and workshops across Europe that have been instrumental in fostering international collaboration in the domain of Fintech.
Research Interests
My research interests are centered around leveraging machine learning (ML) techniques for enhancing credit risk assessment, with a specific focus on developing network-based scoring models. This innovative approach utilizes the interconnectivity of financial entities to generate more accurate and robust credit scores, potentially overcoming the limitations of traditional scoring methods. In addition, my research also focuses on identifying the limitations of classic XAI methods as they apply to financial data and use cases. Specifically, I am also interested in researching and proposing novel XAI methods that are suited for AI models applied to financial time series forecasting.