Funded Projects
UKFin+ Funded Projects
UKFin+ opened for funding applications September 2023, below is a list of projects which have since been funded by the network. To apply for our funding, please visit our funding pages.
An Agile Proposal for a Feasibility Study on a Gifted Account Information Service Provider (AISP) for Research Data
This is a feasibility study for a large-scale financial database and research resource, containing anonymised bank records and financial information gifted by UK individuals. The proposed database will gather this information using an api that makes use of open banking protocols. The study will assess the data privacy, charitable and legal aspects of what would become an important academic resource.
This project is led by Professor Daniel Broby
Pilot Project: UnFed: Selective Forgetting in Federated Financial Applications
Consider a system for predicting default risk used by Buy-now-pay-later (BNPL) lenders. An accurate predictor reduces the lenders’ risk and safeguards customer interests. Developing this predictor requires a large pool of customer profiles and their default records. However, sharing such data across corporations is impossible due to privacy agreements and business interests. This proposal aims to address this by building a distributed machine learning solution, training a predictor while keeping customer data local to the source institute ensuring privacy.
Now, think of a scenario where a child clicks on an advertisement and unknowingly ends up applying for a BNPL credit unknowingly, or when you return an item and don’t want the BNPL lender to retain your personal details. In these cases, among many others, financial institutes need the crucial ability to remove customers from their knowledge base and modify models, such as the above default risk predictor. Machine unlearning algorithms enable an already trained model to forget a selective subset of training samples. While existing methods lack research in applying unlearning to distributed learning, vital for this application, our project will build a distributed learning system with unlearning capabilities for default risk prediction.
This project is led by Dr Abhirup Ghosh
Agile Project: Fintech entrepreneurship and innovation in online black markets.
In online black markets (OBMs) many sell and buy cyber vulnerabilities and cybercrime services. Other actors can resell, repackage, or use such vulnerabilities for hacking or to develop information security solutions. How OBMs work and maintain the fragile balance of ethics, entrepreneurship and innovation, raises a wicked problem for law enforcement, regulators, businesses and researchers. While the primary consideration is for the potential harm, the value created for fintech services and society deserves more attention.
The purpose of this project is to paint a broader picture around OBMs creating an entrepreneurial and innovative environment from which fintech regulators and businesses can learn from. The project challenges the taken-for-granted ethical relationship between entrepreneurship and innovation. In an environment where members create and follow their own rules, doing harm or good is equally possible under conditions of limited accountability and control. We explore the underlying principles of entrepreneurship and innovation value creation in OBMs by looking at the activity of sellers and buyers there, and how traded cyber vulnerabilities and cybercrime services can impact fintech services.
This project is led by Dr Endrit Kromidha