Audit Result Prediction via ML Classification Model
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current audit methods are inefficient in predicting audit results due to the subjective nature of human evaluation, discretion, and potential for human error, making it difficult for organizations to determine compliance deviations and their impact on audit outcomes.
Innovation Solution
A computer-implemented method using a machine learning model trained on historical audit data to predict audit results by identifying compliance deviations and classifying their severity, thereby generating a predicted audit outcome based on system inventory information and security requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If human evaluation and discretion are used in audit processes, then flexibility and adaptability are improved, but objectivity and consistency deteriorate due to subjective judgment and potential human error
Solution Approach 1:
The patent introduces an audit result classification model as an intermediary between the audit evidence and the final audit result. This model processes audit findings objectively while still allowing for flexible audit configurations and criteria. The model acts as a mediator that eliminates subjective human judgment while preserving the adaptability of the audit process through configurable parameters and evidence types.
2Measurement precision
If comprehensive audit of hundreds or thousands of audit points is performed, then measurement precision is improved, but productivity and efficiency deteriorate due to the time-consuming nature of manual review
Solution Approach 1:
The patent replaces the mechanical system of manual human review with an automated computer-based classification model. The model systematically processes hundreds or thousands of audit points through algorithmic evaluation rather than manual inspection. This substitution maintains comprehensive coverage of all audit points while dramatically improving processing speed and efficiency through automated computation.
Solution Approach 2:
The patent performs preliminary classification and filtering of audit evidence before final evaluation. The system pre-processes large volumes of audit data, organizing and categorizing evidence in advance of the final audit result determination. This preliminary action reduces the complexity of the main evaluation task, enabling faster processing of comprehensive audit points while maintaining accuracy.
3Measurement precision
If detailed compliance deviation analysis is conducted for each system, then measurement precision is improved, but device complexity and processing requirements increase
Solution Approach 1:
The patent segments the complex audit process into distinct modular components: evidence collection, classification, feature extraction, and result determination. Each component handles a specific aspect of the audit process independently. This segmentation allows detailed compliance analysis to be performed in discrete, manageable steps rather than as a monolithic complex process, reducing overall system complexity while maintaining precision.
Data Source
AI summary
Computer environment infrastructure compliance audit result prediction includes receiving system inventory information identifying systems of a computer environment and properties of those systems, loading security requirements applicable to systems, determining compliance deviations indicating deviations between current configurations of the systems and the security requirements, based at least on the determined compliance deviations, selecting audit features based on which a predicted audit result is to be generated, and generating a predicted audit result using the selected audit features as input to an audit result classification model trained on historical audit information to predict audit results based on input audit features, and the predicted audit result being a prediction of a result of an audit of the systems.