ISO 20022 Message Generation Using ML Decision Trees
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Creating ISO 20022-compliant XML messages for financial transactions is complex and requires manual effort due to the need to validate thousands of mandatory and optional tags, making it challenging for testing and operational use.
Innovation Solution
An automated process using machine learning (ML) to generate ISO 20022 messages, incorporating a machine learning model with a decision tree algorithm to streamline message creation and validation, including a feature store for training and inferencing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual creation of ISO 20022 XML messages is performed, then message validity can be ensured through validation of thousands of tags, but the process requires excessive manual effort and time
Solution Approach 1:
The patent replaces the manual mechanical process of creating and validating ISO 20022 XML messages with an automated machine learning system. The ML model automatically generates compliant messages and validates thousands of tags without human intervention, substituting manual mechanical validation with automated intelligent processing.
Solution Approach 2:
The system enables self-service message generation where the ML model autonomously creates valid ISO 20022 messages without requiring manual input. The model self-validates the generated messages against the schema constraints, making the entire process self-sufficient and eliminating the need for manual creation and validation efforts.
2Manufacturing precision
If manual validation of thousands of tags is performed, then conformance to validity constraints can be ensured, but the complexity of the process increases
Solution Approach 1:
The complex manual validation process involving thousands of tags is replaced by an ML system that automatically checks conformance to validity constraints. The machine learning model inherently understands the ISO 20022 schema rules and validates messages without requiring complex manual validation procedures.
Solution Approach 2:
The ML model serves multiple functions simultaneously: it generates messages, validates tags, ensures conformance to constraints, and can adapt to different message types. This multi-functional approach simplifies the overall process complexity while maintaining high manufacturing precision for tag conformance.
3Productivity
If automated message generation is implemented using ML, then manual effort is reduced, but the initial system complexity increases
Solution Approach 1:
The patent replaces manual message creation mechanics with an ML-based automated system. Although the ML system introduces initial complexity, it dramatically improves productivity by automatically generating valid ISO 20022 messages without manual intervention, reducing the long-term operational complexity.
Data Source
AI summary
Apparatus is provided including computer memory configured to hold messages including data structures and configured data. The data structures may comprise a markup language and file format organized in accordance with a tree structure. The data structures may comprise an MX/ISO 20022 messaging format payment file for a sent or received payment. A machine learning (ML) processing circuit is provided that comprises a prediction data input and is configured to receive various messages at the prediction data input and to hold the various messages in the computer memory. The ML processing circuit comprises a message generator configured to generate messages for use in other systems, the generated messages being configured in accordance with the data structures. Per another embodiment, the machine learning processing circuit may be configured to create test messages based on the various messages held in the computer memory.