Decentralized Credit Scoring: Black Box 3.0

Abstract

Decentralized credit scores usher in a new era of consumer credit. Much like traditional credit scoring, decentralized credit scoring calculates a borrower's creditworthiness, but the fully automated process is executed on the blockchain by Decentralized Finance (DeFi) platforms. But while DeFi emerged as an alternative to the centralized traditional finance (TradFi) system, decentralized credit scoring combines–beyond DeFi data–much of the same off-chain data that has been used in traditional credit schemes to gauge individuals’ creditworthiness. The off-chain data integration includes a wide range of information sources, from traditional credit reports to social media information.

This Article presents the first legal analysis of hybrid decentralized credit scores. Despite their fairness-oriented narrative, an examination of protocols and entities operating in this space and an investigation of their business models reveal that these hybrid scores are subject to the same algorithmic distortions that have been observed in traditional and alternative credit scoring models. Moreover, decentralized credit scores present their own distinctive set of fairness issues, which this Article refers to as black box 3.0. These challenges are associated with using smart contracts to enforce preset rules in the scoring process. Both upgrades to smart contracts and their reliance on external algorithms, known as oracles, to feed outside data introduce heightened potential for error and bias in the credit scoring process. These black box 3.0 issues, which have been virtually overlooked by legal commentary, can result in opaque automation of biased processes and perpetuate social injustices. The Article reviews these problems and the regulatory void in which they thrive, and advocates for strengthening linkage points between DeFi and TradFi through regulatory intervention in order to better protect consumers from the black box 3.0 consequences of decentralized credit scores. 

Keywords: credit scores, creditworthiness, fairness, smart contracts, discrimination, black box, bias, social justice, algorithms, finance, decentralization, blockchain, tech policy, automation