AI Utilization

Enhances security, efficiency, and user experience. AI algorithms analyze transaction patterns for risk management, optimize smart contracts, and provide predictive analytics for informed decisions. AI-driven chatbots improve customer support, while data analysis extracts valuable insights for continuous improvement. This integration ensures Iron Chain remains efficient, secure, and user-friendly in the decentralized finance (DeFi) space.

πŸ’―AI-Based Credit Scoring

Introduction

Our platform leverages the power of artificial intelligence to revolutionize the way lenders and borrowers are evaluated, streamlining the transaction process and ensuring greater trustworthiness. πŸ€–πŸ’³

Your Credit Score

With AI-Based Credit Scoring, we utilize advanced algorithms to analyze various factors such as transaction history, repayment behavior, and financial stability to assess the creditworthiness of users. By automating this process, we eliminate the need for manual credit checks, saving time and reducing the risk of human error.

For lenders, AI-Based Credit Scoring provides invaluable insights into the risk associated with potential borrowers, allowing them to make more informed decisions and mitigate potential losses. On the other hand, borrowers benefit from faster approvals and access to capital, as our AI algorithms accurately assess their creditworthiness and determine suitable lending options.

By incorporating AI-Based Credit Scoring into our platform, Iron Chain Bank is at the forefront of innovation in decentralized finance, paving the way for faster, more efficient, and trustworthy transactions. Join us as we harness the power of artificial intelligence to revolutionize the lending and borrowing experience! πŸš€πŸ”—

How does it work?

Step 1: We verify the user's ownership of the crypto wallet through Non-Fungible Credit Scoring (NFCS)

Step 2: Through NFCS, we crawl data of users' financial behaviors on the blockchain networks

Step 3: The data then being processed by the Credit Scoring ML Model and the users get scoring

AI-Based Credit Scoring Process

Non-Fungible Credit Scoring Explained

A non-Fungible Credit Scoring token is a solution to verify ownership of the addresses to receive credit scoring.

  1. Credit Risk Rating Process: Users interested in borrowing from Iron Chain Bank must undergo a credit risk rating process. This process will assess their creditworthiness based on their on-chain behavior and financial history.

  2. Non-fungible Credit Score (NFCS) Token: To receive a credit risk rating, users must mint their Non-fungible Credit Score (NFCS) token. This will be a BRC-20 token minted on the Iron Chain Bank blockchain.

  3. Ownership Verification: The NFCS token serves as proof of ownership for the addresses associated with the user's on-chain behavior. By owning the NFCS token, users verify their ownership of the addresses for which the credit risk score has been generated.

  4. Credit Score Classification: The NFCS token categorizes users' on-chain behavior into a numerical scale from 1 to 10. A score of 1 indicates the highest creditworthiness, while a score of 10 indicates the lowest.

  5. Aggregated Transaction History: Users can bundle multiple addresses to their NFCS token. This allows the credit risk score to be determined based on the aggregate transaction history from these addresses. Once generated, the NFCS is immutable and cannot be altered.

  6. User Control and Ownership: Similar to credit bureaus like FICO, the NFCS belongs to the user, but the user does not have direct control over it. However, they can use it to demonstrate their creditworthiness when seeking borrowing opportunities within the Iron Chain Bank ecosystem.

By implementing NFCS, Iron Chain Bank can effectively assess the credit risk of users and provide them with appropriate borrowing opportunities based on their creditworthiness. This system enhances trust and transparency within our platform, promoting responsible borrowing and lending practices.

Built-in Limitations of NFTCS

  1. Non-Reusability of Addresses: Addresses/accounts already included in an NFCS bundle cannot be utilized in another NFCS bundle. This measure prevents duplication of addresses within the system, reducing the risk of fraudulent activity and ensuring the uniqueness of each NFCS bundle.

  2. Address Ownership Confirmation: Users must confirm ownership of each address added to the NFCS bundle through a nonce signature. This authentication process adds layer of security, verifying the legitimacy of addresses included in the bundle and minimizing the potential for unauthorized access.

  3. Single NFCS Per Wallet: Users are restricted to possessing only one NFCS in their wallet. This limitation prevents the proliferation of NFCS instances within a single wallet, streamlining the credit evaluation process and enhancing overall system efficiency.

  4. Access Restriction to Primary Address: Credit access is granted exclusively from the 'Primary' address within the NFCS bundle. This restriction ensures that credit utilization is centralized and controlled, reducing the complexity of credit management and minimizing potential misuse.

  5. Non-Transferability of NFCS: NFCS tokens are non-transferable, meaning they cannot be transferred or exchanged between users or wallets. This safeguard prevents unauthorized transfer of NFCS tokens and maintains the integrity of the credit scoring system.

  6. Address Addition, No Removal: In subsequent versions of NFCS, users have the capability to add new addresses to the bundle, but they are unable to remove existing addresses. This feature promotes continuity and stability within the NFCS framework, preventing manipulation or tampering with address inclusion/exclusion.

By adhering to these established limitations, Iron Chain Bank ensures the reliability, security, and fairness of the NFCS system, fostering trust among users and stakeholders alike. These measures uphold the integrity of credit scoring processes and contribute to a robust and sustainable financial ecosystem within Iron Chain Bank.

The Data used for ML Models

Data utilized for the machine learning (ML) model encompasses a comprehensive range of sources and factors to ensure robust analysis and predictive accuracy. This includes:

  1. Full transaction histories from prominent lending protocols such as Aave, Compound, Cream, RociFi Labs, Venus, MakerDAO, GMX, and Radiant. This extensive dataset provides insights into borrowers' behavior across various lending platforms.

  2. Transaction histories spanning seven blockchain networks, including Ethereum, Arbitrum, Fantom, Polygon, Optimism, BSC, and Avalanche. This multi-chain approach enables a holistic understanding of users' activities across different ecosystems.

  3. Historical token prices are incorporated to facilitate conversion to USDT, allowing for standardized valuation and comparison of assets across different timeframes.

  4. Wallet transactions related to decentralized finance (DeFi) lending are analyzed to identify patterns and trends in borrowing and lending activities.

  5. Liquidation events are monitored, with their frequency serving as a potential indicator of risk appetite and exposure to speculative behavior.

  6. Collateralization ratios are assessed, with higher ratios indicating lower susceptibility to speculative risk for borrowers.

  7. The first DeFi interaction date is considered as an indicator of user experience and familiarity with decentralized finance platforms.

  8. Overall wallet history is evaluated to gain insights into users' broader financial activities and behavior.

  9. Market context, including borrowing behavior during periods of high volatility and uncertainty, is factored in to understand users' risk management strategies.

  10. Combinations of lending protocols within a wallet's history are analyzed to identify diversification strategies and assess risk exposure across different platforms.

By integrating these diverse datasets and factors, the ML model can generate comprehensive credit risk assessments, enabling Iron Chain Bank to make informed lending decisions and mitigate potential risks effectively.

Credit Scoring Engine

There are four components in Iron Chain Bank's credit scoring engine

Credit Scoring Engine

  1. Fraud Database Scan: Borrower addresses will be scanned through Iron Chain Bank's database of known fraudulent actors, encompassing various types of fraudulent activities such as phishing, hacks, and scams. This database comprises hundreds of thousands of entries compiled from historical data and ongoing monitoring efforts.

  2. Fraud Score Analytics: Each borrower address will be assigned a fraud score, representing the probability or likelihood that it is associated with fraudulent activity. The fraud score ranges from 1 to 10, with 1 indicating the lowest risk and 10 indicating the highest risk. This score is derived from advanced analytics and machine learning algorithms that analyze patterns and behaviors indicative of fraudulent activity.

  3. DID/Web3 Score: Borrower addresses will undergo evaluation based on their reputation and monetary value within the Iron Chain Bank ecosystem. This evaluation results in the assignment of a Rep Score to each address, with 1 representing the highest reputation and value, and 10 representing the lowest. The Rep Score is determined through a combination of decentralized identity (DID) verification and analysis of transactional data.

  4. Credit Score Analytics: Borrower addresses will be assessed for creditworthiness, specifically the probability or likelihood that they will default on the loan. Similar to the fraud score, the credit score ranges from 1 to 10, with 1 indicating the lowest default risk and 10 indicating the highest. This assessment leverages sophisticated analytics and predictive modeling techniques to evaluate factors such as repayment history, debt-to-income ratio, and financial stability.

This comprehensive approach to credit scoring enables Iron Chain Bank to mitigate fraud, assess borrower risk accurately, and make informed lending decisions that promote financial stability and sustainability.

Last updated