Network Data Output
Algorithms
The initial BlockScore® Protocol credit scoring algorithm will prioritize a specific set of risk parameters, a standardized set of global parameters for the network. The algorithm uses mathematical and statistical models using the input data to calculate the users BlockScore®. By storing the blocks of compiled data represented by cryptographic hashes on the data ledger, this data can then be used as the building blocks to train and increase the accuracy of the credit scoring algorithms on the network.
Score Factors
Calculating A Users BlockScore
Methodology – BlockScore put the most significant factors in detecting loan default as the priority by combing traditional scoring models with social, economic, and blockchain data to create a fair and inclusive risk protocol.
_________________________
Level 1 – Financial Score (40-45%) – The ability to provide collateral and down-payments through multiple streams is crucial when building a credit history and financial identity in today’s economy. The financial factors influence the size of the loan and loan terms.
Financial Data
Digital Assets – Cryptocurrencies, NFTs, Metaverse, IoT Devices
Assets – Traditional Investments
Liquidity – Cash Reserve
_________________________
Level 2 – Reliability Score (45-55%) – A study conducted at Stanford University shows consumers would care more about their credit score if it was not tied so heavily to personal income. Simply put, just because someone makes more income does not mean they are more responsible or trustworthy. Reliability is measured by past behavior, such as historical data that shows patterns of consistent financial decisions.
Payment History
Loan Activity
Total Debt
Verified Public Records
Blockchain Activity
_________________________
Level 3 – Social Score (15%) – According to a study conducted by Carnegie Mellon, social metrics detect default with higher accuracy than credit scores. The study shows that consumers naturally put more weight on social situations good credit offers than the actual credit score itself. Further research done by Stanford University indicates that social data performs on the same level as traditional credit scoring methods and even outperforms in detecting loan defaults in many situations.
Social KYC – Public Identity
Facebook Verified
Twitter Verified
Linkedin Verified
Digital Footprint
_________________________
Score Range
