Scoring Aave Accounts for Creditworthiness

TL;DR

This paper introduces a credit scoring system for Aave DeFi accounts using a tree-based classifier to predict delinquency, providing a novel approach to assess DeFi account creditworthiness.

Contribution

The paper presents a new credit scoring method specifically designed for DeFi accounts interacting with Aave, including the model, results, and dataset.

Findings

The classifier effectively predicts account delinquency.

The system offers a practical tool for DeFi credit assessment.

Results demonstrate the model's potential for real-world application.

Abstract

Scoring the creditworthiness of accounts that interact with decentralized financial (DeFi) protocols remains an important yet unsolved problem. In this paper, we propose a credit scoring system for those accounts that have interacted with the Aave v2 liquidity protocol. The key component of this system is a tree-based binary classifier that predicts "position delinquency." To the community, we provide our method, results, and the (abridged) dataset on which this system is built.