Anomaly Detection in Online Forms Using Statistical Tree Cohorts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current online form filling processes face challenges in detecting anomalous data fields, leading to high error rates and manual corrections, which are inefficient and time-consuming, particularly in tax preparation and other form filing processes.
Innovation Solution
A machine learning-based anomaly detection system using statistical tree structures is implemented to predict and flag anomalous data fields by organizing users into cohorts based on data features, determining confidence scores, and providing explanations for flagged items, with dynamically set thresholds for improved accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual evaluation of online forms is used, then data accuracy and quality can be ensured, but time consumption and operational costs increase significantly
Solution Approach 1:
The patent replaces manual evaluation processes with an automated machine learning-based anomaly detection system. The system uses statistical tree structures to automatically identify anomalous data fields in online forms, substituting the mechanical manual review process with an automated computational system that achieves both speed and accuracy.
Solution Approach 2:
The system enables self-service anomaly detection by automatically evaluating form data fields against learned statistical patterns. The machine learning model autonomously identifies anomalies without requiring human intervention for each evaluation, allowing the system to serve itself in the detection process.
2Loss of time
If automated anomaly detection is implemented, then time consumption is reduced, but prediction accuracy may deteriorate without proper threshold calibration
Solution Approach 1:
The patent dynamically adjusts threshold parameters in the statistical tree structures based on the specific data distribution and form types. By adapting threshold values to match the statistical characteristics of different datasets, the system maintains high prediction accuracy while operating automatically at scale.
Solution Approach 2:
The system incorporates feedback mechanisms where predicted anomalies are reviewed and used to refine the statistical models. This continuous feedback loop allows the machine learning algorithms to improve their detection accuracy over time while maintaining automated operation.
3Productivity
If statistical tree structures are used for anomaly detection, then processing speed increases, but model complexity increases
Solution Approach 1:
The patent divides the anomaly detection task into separate statistical tree structures, with each tree specialized for detecting anomalies in specific data fields or form types. This segmentation allows the system to maintain high processing speed through specialized models while managing overall complexity by organizing detection functions into modular, independent units.
Data Source
AI summary
A computer-implemented system and method for predicting and flagging an anomaly entered in a digital form. A server computing device classifies a plurality of data fields of the digital form to identify a set of non-zero value data fields; and obtains an anomaly detection model comprising a statistical tree structure associated with the data field of the digital form. The server computing device receives datasets including a target value of a data field and values of a set of cohorting data features; traverses a statistical tree structure of the anomaly detection model with the target dataset to form a set of target cohorts to determine a target statistic value for the data field; flags the data field value of the target dataset as an anomaly item; and generates one or more confidence scores for a runtime prediction based on one or more variance changes for the data field.