User Score Model Training Using Social Network Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The FICO credit score model faces difficulties in accurately calculating a user's credit score when their personal information is missing or incorrect, as it relies on specific data that is not readily available in such cases.
Innovation Solution
A credit score model training method that utilizes social networking information to generate user scores by training a model based on the scores of sampled users with social relations, allowing for the calculation of a target credit score even when personal information is incomplete or incorrect.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the FICO credit score model is used to calculate credit scores based on personal information, then the calculation can be performed with available data, but the accuracy deteriorates when personal information is missing or incorrect
Solution Approach 1:
The patent introduces social networking information as an intermediary to bridge the gap between unavailable personal information and the credit score calculation. By using social relations as a mediator, the system can infer creditworthiness through network effects when direct personal data is missing or incorrect, thus maintaining both reliability and precision.
2Adaptability or versatility
If personal information is required for credit score calculation, then the model can use direct user data, but the coverage is limited when users lack or provide incorrect information
Solution Approach 1:
The patent makes the credit score model universal by enabling it to function with multiple data sources. The model can process both traditional personal information and social networking information, allowing it to adapt to various data availability scenarios. This multi-functionality expands data coverage quantity while maintaining model versatility.
3Measurement precision
If social networking information is incorporated into the credit score model, then the coverage and accuracy improve, but the device complexity increases
Solution Approach 1:
The patent segments the credit score calculation into distinct modules: personal information processing, social networking information processing, and integration. By dividing the complex task into separate segments, the system can manage complexity through modular architecture while still achieving improved precision through the combined effect of multiple data sources.
Data Source
AI summary
A method, apparatus, and server for generating a user score based on social networking information is provided. In the disclosed method, by processing circuitry of an information processing apparatus, default annotation information of a plurality of sampled users, an ith user score and an ith relative user score for each of the sampled users are obtained. A user score model is trained according to the ith user score of the respective sampled user, the ith relative user score of the respective sampled user, and the default annotation information of the respective sampled user. An (i+1)th user score of the respective sampled user is subsequently calculated and a trained user score model, for each of the sampled users, is obtained when the (i+1)th user score for the respective sampled user satisfies a training termination condition, The method provides a solution to evaluate the user score for a use when personal information of the user is missing or incorrect.