Unified Credit Data Structure for Risk Assessment

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current credit lending strategies face challenges in obtaining, organizing, and analyzing internal customer credit data and external consumer credit data effectively, leading to inefficiencies in risk assessment and decision-making.

Innovation Solution

A data gathering and analytical process that combines internal customer data with external CRA data to create a consumer credit market database and structure, enabling strategic planning and predictive analytics for risk/reward strategies by classifying data into Customer Attributes, Consumer Attributes, and Value Added Attributes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If lending institutions use only internal customer data, then data accessibility is improved, but market representation accuracy deteriorates

Engineering Contradiction:

Improvedata accessibilityVSAvoidmarket representation accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The patent combines internal customer data with external CRA data into a unified data structure. Internal data provides detailed customer relationships while external CRA data provides comprehensive market coverage, merging both sources to achieve both accessibility and accuracy simultaneously.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The unified data structure serves multiple functions: it represents the institution's own customers, the broader consumer credit market, and enables both internal strategic planning and external risk assessment, making the system universally applicable for various lending decisions.

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Adaptability or versatility

If lending institutions use only external CRA data, then market coverage is improved, but data detail and institutional relevance deteriorate

Engineering Contradiction:

Improvemarket coverageVSAvoiddata detail and institutional relevance

Core Design Contradiction:

Adaptability or versatilityVSLoss of information

Solution Approach 1:

The patent merges external CRA data with internal customer data, allowing the system to maintain broad market coverage from CRA data while preserving detailed institutional-specific information from internal data sources, thus preventing information loss.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The data structure maintains different levels of detail for different purposes: broad market-level aggregates from CRA data for coverage, and specific customer-level details from internal data for institutional relevance, allowing each data element to have the quality appropriate to its function.

Inventive Principle:

Principle #3Local quality

3Productivity

If comprehensive multi-source data is collected, then analytical capability is improved, but data organization complexity deteriorates

Engineering Contradiction:

Improveanalytical capabilityVSAvoiddata organization complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent segments the combined data into distinct categories: internal customer data, external CRA data, and derived attributes. This segmentation organizes the complexity by creating clear boundaries between data sources while enabling comprehensive analysis through the structured relationships between segments.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent adds a temporal dimension by tracking data over time periods, allowing the system to manage complexity through time-based organization while enhancing analytical capability through historical and forward-looking analyses enabled by the temporal structure.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

4Measurement precision

If detailed customer-level analysis is performed, then predictive accuracy is improved, but processing time deteriorates

Engineering Contradiction:

Improvepredictive accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary data organization and attribute derivation during data collection, pre-processing the data into the unified structure with calculated attributes. This preliminary action reduces processing time during actual analysis while maintaining the detailed predictive accuracy needed for individual customer assessments.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS8271364B2Method and apparatus for obtaining, organizing, and analyzing multi-source data

Publication Date: 2012.09.18 BANK OF AMERICA CORP

AI summary

The tool of the invention is a data gathering and analytical process that uses internal customer data and external CRA data to build a consumer credit market data base and data structure. The internal customer data is classified according to identified Customer Attributes, the CRA data is also classified according to identified Consumer Attributes and the combined data is further classified according to additional Value Added Attributes. The resulting data structure is organized at the individual level such that each individual has associated therewith values for each of the Customer Attributes, Consumer Attributes and Value Added Attributes. The resulting analysis can be used to set institutional strategies and/or to make predictive decisions on individual borrower credit requests.