Crypto-based company is creating and incentivizing on-chain credit scores

66
2
Crypto-based company is creating and incentivizing on-chain credit scores

We are creating and incentivizing a network of modelers, creators, users and validators using proof-of-stake mechanics. The concept - similar to Chainlink and The Graph's models - is to create a decentralized marketplace with a built-in feedback mechanism that ferrets out and discourages bad actors.

Our Multi-asset credit risk oracle score is a machine learning model that weighs approximately 100 on-chain signals to generate a three-digit score predicting a wallet's likelihood of liquidation on an on-chain loan. The score is similar to the FICO score, which ranges from 300 to 850, representing a very low risk. It's very similar to what you'd get from a traditional credit report, but instead ofrelying on Experian, Transunion and Equifax to keep tabs on your spending, you opt-in with your wallet.

The promise of on-chain credit score is that it's opt-in, completely transparent, and ultimately, production of the algorithm generating the scores can be decentralized by incentivizing a competitive marketplace. Netflix pioneered the idea in the 2000s when they offered a million-dollar bounty to a team of data scientists who improved their advice algorithm by 10%.

The traditional structure of a validator network is to provide rewards to a validator node for creating blocks and validating rewards, and punishing nodes by taking away their stake by slashing, which is called slashing, by taking away their stake when they misbehave, which is known as failing to maintain the node, behaving maliciously or other blockchain misfeasance. Validation is a useful tool for incentivizing a contest. A network can be divided into modelers and creators, who create data science challenges for the modelers to tackle, in this case an accurate credit score generated from on-chain information.

We also have validators who vet the models for quality, and after the contest ends, we have users who pay to use scores generated from the winning models. The idea is to use crypto to support a thriving ecosystem that grows extremely accurate machine learning models as a result.

When it works, Cryptoeconomics creates a hothouse environment, where ideas are enticed by people worldwide. By building on a blockchain, smart contracts can build off-chain processing on the system, so nearly any data set may be encrypted and worked on given enough processing power and time - whether it's tumor hunting, medical records inferences, insurance payouts, bail calculations, or training robotic operating systems to serve hamburgers.