Federated Learning for Credit Risk Assessment

in Proceedings of the 56th Hawaii International Conference on System Sciences (2023, January 03)

Credit risk assessment is a standard procedure for financial institutions (FIs) when estimating their credit risk exposure. It involves the gathering and processing quantitative and qualitative datasets ... [more ▼]

Credit risk assessment is a standard procedure for financial institutions (FIs) when estimating their credit risk exposure. It involves the gathering and processing quantitative and qualitative datasets to estimate whether an individual or entity will be able to make future required payments. To ensure effective processing of this data, FIs increasingly use machine learning methods. Large FIs often have more powerful models as they can access larger datasets. In this paper, we present a Federated Learning prototype that allows smaller FIs to compete by training in a cooperative fashion a machine learning model which combines key data derived from several smaller datasets. We test our prototype on an historical mortgage dataset and empirically demonstrate the benefits of Federated Learning for smaller FIs. We conclude that smaller FIs can expect a significant performance increase in their credit risk assessment models by using collaborative machine learning. [less ▲]

Opportunities and challenges of using blockchain technology in public administration – Insights from the FLORA project of Germany’s Federal Office for Migration and Refugees

Report (2022)

Chapter 8: Tokenization and Regulatory Compliance for Art and Collectible Markets: From Regulators' Demands for Transparency to Investors' Demands for Privacy

in Lacity, Mary; Treiblmaier, Horst (Eds.) Blockchains and the Token Economy: Studies in Theory and Practice (2022)

Art and collectibles markets tend to involve lower liquidity and higher fees than public equity markets. Distributed ledger technology can tokenize artworks and collectibles, so that claims to these ... [more ▼]

Art and collectibles markets tend to involve lower liquidity and higher fees than public equity markets. Distributed ledger technology can tokenize artworks and collectibles, so that claims to these assets can be exchanged digitally without intermediaries. Tokenization offers investors access to a global market plus a digitized paper trail, as well as new options for the fractional ownership of artworks, art-collateralized loans, and yield-bearing art assets. The main challenge for tokenization researchers and platform developers is to simultaneously satisfy regulators’ demands for transparency and auditability as well as art investors’ demands for privacy. New technological solutions are required that enable market participants to disclose the absolute minimum amount of information that is required by regulators. We explore new concepts from distributed ledger technology, cryptography, and digital identity management that can help address this challenge. [less ▲]