Transaction Outcome Prediction Using Taxonomy Classifications
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional systems fail to accurately predict entity outcomes from transaction data, particularly in identifying credit risks and fraudulent transactions, as they rely on income, cash on hand, and credit scores without analyzing transaction patterns.
Innovation Solution
A method involving the classification of transaction data using taxonomy classifications, where processors obtain and structure data, determine similarity to predetermined categories, generate an input data structure, and provide it to a predictive algorithm to estimate entity outcomes such as probability of default or fraudulent transactions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional systems use income, cash on hand, and credit scores to assess entity outcomes, then the assessment process is simple and fast, but the accuracy in identifying credit risks and fraudulent transactions is insufficient
Solution Approach 1:
The patent segments transaction data into multiple categorical dimensions (e.g., merchant category, transaction type, time patterns, location) and analyzes each segment separately. This allows the system to process complex transaction patterns while maintaining manageable complexity in each analysis module, ultimately improving prediction accuracy without overwhelming system complexity.
Solution Approach 2:
The patent introduces additional analytical dimensions by classifying transactions across multiple categorical axes simultaneously (merchant category codes, transaction timing, geographic patterns, etc.). This multi-dimensional analysis transforms the problem from simple credit score evaluation to comprehensive transaction pattern recognition, significantly improving accuracy in identifying credit risks and fraud.
2Reliability
If systems analyze detailed transaction patterns using taxonomy classifications, then the ability to identify credit risks and fraud improves, but the processing time and computational resources increase
Solution Approach 1:
The patent performs preliminary classification of transactions into categorical groups (merchant categories, transaction types, time patterns) before detailed fraud analysis. This pre-grouping allows the system to quickly eliminate normal transaction patterns and focus computational resources only on suspicious patterns, reducing processing time while maintaining high detection reliability.
Solution Approach 2:
The patent applies different levels of analysis intensity to different transaction categories. High-risk categories receive more detailed scrutiny while low-risk categories undergo faster processing. This localized quality adjustment optimizes the balance between detection reliability and processing speed by allocating computational resources efficiently across different transaction types.
Data Source
AI summary
Methods, systems, and computer programs, for predicting a likely outcome for an entity. A method includes obtaining a first data structure that includes data that represents a transaction, determining a similarity level of the transaction to each of a plurality of categories, determining a transaction category based on the determined similarity level, generating an input data structure that includes data representing (i) at least a portion of the data representing the transaction, and (ii) data describing the determined category, providing the input data structure to a predictive algorithm trained to determine a value that represents a likely outcome for an entity that initiated a transaction, obtaining output generated by the predictive algorithm based on the predictive algorithm's processing of the input data structure, the output including a value that represents a likely outcome for the entity, and determining a likely outcome for the entity based on the obtained output.