Comment on page
The answers to all your questions, at least the main ones!
Cred Protocol uses on-chain analytics to quantify lending risk at scale. We correlate transaction history with the account owners ability to fulfil obligations, specifically, repay loans.
Our machine learning credit score model is comprised of a set of features that have been selected to capture the holistic view of an account's on-chain risk. When combined, they create a predictive score that quantifies the creditworthiness of an account.
As the web3 ecosystem continues to grow and mature, we are always looking to add features that inform the model and improve the score. This process of continuous development is driven by our search for new data sources as they emerge, including new lending protocols, chains, and broader web3 projects.
Revealing the individual features that contribute to the score would potentially lead to people being able to 'game' the score, and improve their score without improving their underlying fundamental behaviours. In order to preserve the score's integrity but also provide transparency, the features are grouped into high-level 'Credit Factors'.
A table of the Credit Factors, alongside a more detailed breakdown of each factor is listed below:
The easiest way to improve your score is to use lending protocols, take out loans and then repay them successfully, this demonstrates strong creditworthiness that will be reflected in a higher credit score.
However there are ways to improve your credit score beyond interacting with lending protocols. The Credit Factors represent groups of features that contribute to the score, improving behaviour in any of these areas would have a positive impact on your score.
We are able to score any account with on-chain Ethereum mainnet transactions, if your account does not have any Ethereum mainnet transactions then it will not be given a score. Once your account has transactions it will be possible to score it.
Similarly, rather than giving a brand new account with no transactions a score of 0, we will return 'Unscorable' as there are insufficient transactions to generate a score.
We are able to provide a score to a single account on the basis of its transaction history. Similarly if you have a number of accounts, we are able to amalgamate their combined transaction history to produce a single score for the entire group.
Our score is designed so that creditworthiness is informed by legitimate account activity. We have layers of on-chain analysis, fraud mitigation techniques and a suite of Accountability APIs that surface consequence for bad actors. We don't publish exact details of our scoring algorithm to mitigate manipulation.
Using on-chain analytics, we’re able to track transactions which pass between different accounts and back to the same account helping to mitigate “self dealing” which may inflate transaction volumes and aspects of the score. Other aspects of the score are focused on Trust and evaluate multiple “proofs of humanity” ranging from verified credentials to fully KYC’d identities which make it more difficult for an account to be abandoned or transferred.
The short answer, is: where appropriate we verify identity. We use proprietary on-chain analytics to mitigate fraud and partner with leading identity verification and attestation protocols to support the credit decisioning process. In addition, we’re actively exploring privacy-preserving identity attestation approaches which combine security and pseudonymity. Learn more.