Credit Scoring and Risk Management

Every participant in the Webtransfer network has a social credit rating determined based on their history of interactions, credit activity, ratings, and reviews from other users within their social connections and trust chain.

This rating plays a crucial role in issuing unsecured loans and setting the limits, interest rates, and required levels of collateral to minimize risks.

Webtransfer is committed to developing and implementing an advanced credit scoring model based on a comprehensive analysis of users’ social, financial, and behavioral data. The system will utilize multifactorial scoring models with artificial intelligence and machine learning to assess creditworthiness in real-time.

Innovations in a historical context:

Webtransfer was the first in the world to implement theVisual DNA method to assess borrowers’ personality traits, using a test based on the“Big Five” model. This allowed a deeper understanding of users’ motivations and preferences, improving their reliability assessment as borrowers.

Key aspects of scoring:

• Social credit rating: each user will have an individual rating formed based on their interactions in the network, credit history, reviews, and ratings from other users.
  
• Comprehensive data analysis: analysis algorithms will consider a wide range of factors, including financial flows, social connections, online behavior, as well as macroeconomic and demographic data.
  
• Adaptive lending conditions: lending conditions will automatically adjust based on changes in credit rating and borrowers’ financial situations.

An additional credit scoring parameter – Guarantor Rating

Parameter description:

An additional creditworthiness assessment parameter is the number of guarantors within the participant’s credit union or partner network. This indicator reflects the level of trust the participant enjoys among other system participants and their ability to attract guarantors.

Integration mechanism into the credit score model:

1. Quantitative assessment of guarantors: each guarantor adds a certain number of points to the credit rating, depending on their own credit history and rating. The rating also includes consideration of loans issued, allowing for the activity of guarantors in the credit network.
   
2. Verification of guarantors: an automated system checks the status and credit background of each guarantor to ensure their suitability and relevance. It’s crucial that active loans of a guarantor do not exceed the term of the guaranty and serve as collateral.
   
3. Limits and restrictions:setting a maximum number of guarantors that can influence the scoring to prevent data distortion.
   
4. Dynamic rating update: regular updates of the rating based on changes in the composition of guarantors and their credit ratings. If a guarantor has repaid issued loans and withdrawn money from the credit pool, the borrower’s rating should change. During the guaranty period, the guarantor cannot withdraw the amount equivalent to the guaranty collateral.

The introduction of guaranty strengthens mutual trust and fosters the creation of a more stable credit environment, enhancing creditworthiness and access to better lending conditions. However, there is a risk of collusion and abuse, which requires strict audit and control procedures to maintain the integrity of the credit system.

Continuous improvement:

Active implementation of artificial intelligence methods on the Webtransfer platform enhances credit scoring systems. Using feedback and analyzing user behavior will help improve the accuracy and fairness of lending conditions, reducing financial risks and strengthening trust and loyalty among users.

This approach not only increases the efficiency of the credit system but also reinforces the principles of trust and mutual aid within the decentralized Webtransfer credit network, promoting the creation of fairer and safer financial conditions for all participants.