Scoring Aave Accounts for Creditworthiness

07/14/2022
by   Will Wolf, et al.
0

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.

READ FULL TEXT
research
08/12/2021

Bagging Supervised Autoencoder Classifier for Credit Scoring

Credit scoring models, which are among the most potent risk management t...
research
02/29/2020

A Quadratic Programming Solution to the FICO Credit Scoring Problem

After decades of experience in developing credit scores, the FICO corpor...
research
10/26/2020

A Novel Classification Approach for Credit Scoring based on Gaussian Mixture Models

Credit scoring is a rapidly expanding analytical technique used by banks...
research
05/21/2022

Deep Learning vs. Gradient Boosting: Benchmarking state-of-the-art machine learning algorithms for credit scoring

Artificial intelligence (AI) and machine learning (ML) have become vital...
research
11/05/2021

Disentangling Decentralized Finance (DeFi) Compositions

We present the first study on compositions of Decentralized Finance (DeF...
research
07/13/2015

Supervised Hierarchical Classification for Student Answer Scoring

This paper describes a hierarchical system that predicts one label at a ...
research
10/02/2017

HUMOR: A Crowd-Annotated Spanish Corpus for Humor Analysis

Computational Humor, as the name implies, studies humor from a computati...

Please sign up or login with your details

Forgot password? Click here to reset