T-Digest Percentile Scoring for Adaptive Digital Threat Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies fail to accurately and timely detect digital fraud and abuse over the Internet, lacking the ability to adapt to new threats and evolve in response.
Innovation Solution
A computer-implemented method using T-Digest data structures and percentile-based threat scoring to assess digital events, involving threat scoring machine learning models, automated disposal decisions, and automated decisioning workflows to mitigate digital threats.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing technology implementations are used to detect digital fraud and digital abuse, then detection capabilities are provided, but detection accuracy and real-time response are insufficient
Solution Approach 1:
The system dynamically adapts to new threats by continuously learning from emerging patterns and evolving threat landscapes. The threat detection model is updated in real-time to incorporate new fraud patterns, ensuring both high detection accuracy and current relevance without requiring complete system reconfiguration.
Solution Approach 2:
The system implements feedback loops where detection results, false positives, and emerging threat patterns are continuously fed back into the model. This allows the system to learn from its performance and automatically adjust detection parameters, improving accuracy over time while maintaining real-time operational capabilities.
2Adaptability or versatility
If existing technology implementations are used to detect digital threats, then basic detection is provided, but the ability to detect new and never-before-encountered threats is lacking
Solution Approach 1:
The system performs preliminary analysis of emerging threat patterns and prepares detection rules in advance. By proactively identifying and preparing for potential new threats before they fully manifest, the system can rapidly respond to novel attack vectors without requiring complex ad-hoc analysis when threats occur.
Solution Approach 2:
The threat detection system automatically evolves and updates itself through self-learning mechanisms. It autonomously identifies new threat patterns, adjusts detection parameters, and incorporates emerging fraud techniques without requiring manual intervention, thereby improving adaptability while managing complexity through automation.
3Measurement precision
If traditional threat detection methods are used, then processing is provided, but false positives and negatives cannot be sufficiently reduced
Solution Approach 1:
The system dynamically adjusts detection parameters, thresholds, and weighting factors based on emerging threat patterns and performance metrics. By continuously optimizing these parameters rather than using fixed values, the system improves scoring accuracy and reduces both false positives and negatives as threat landscapes evolve.
Data Source
AI summary
A system and method for quantile-based assessment and handling of digital events in a digital threat mitigation platform includes receiving, via an application programming interface (API), a request from a subscriber to assess a threat of a digital event, computing, using one or more threat scoring machine learning models, a digital threat inference based on one or more corpora of feature vectors associated with the digital event, wherein the digital threat inference includes an uncalibrated digital threat score, retrieving, from a database, a T-Digest data structure of historical digital threat scores of the subscriber, computing, using the T-Digest data structure of historical digital threat scores, a percentile-based threat score based on the uncalibrated digital threat score computed for the digital event, and executing an automated disposal decision computed for the digital event based on at least the percentile-based threat score satisfying automated decisioning instructions of the digital threat mitigation platform.