AI System for Predicting Illicit Behavior via Search String Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for predicting and preventing illicit behavior through clickstream data analysis are inefficient and yield low-quality results, requiring significant processing resources and time, and often fail to identify users without a known ID.
Innovation Solution
An artificial intelligence-based system that analyzes live and historical internet data using machine learning models to identify suspicious users by preprocessing search strings for suspicious words and matching users with and without IDs, thereby reducing computational resources and improving accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If clickstream data is analyzed to identify suspicious users, then the ability to detect illicit behavior is improved, but the processing resources and time required increase significantly
Solution Approach 1:
The system segments the analysis process into multiple stages: first filtering search strings for suspicious keywords, then analyzing clickstream data only for users who triggered the filter. This hierarchical segmentation reduces the overall data volume requiring intensive analysis while maintaining detection accuracy.
Solution Approach 2:
The system performs preliminary filtering of search strings against a suspicious keyword database before conducting full clickstream analysis. This preliminary action eliminates the majority of benign users from further processing, reducing computational resources and time required for the main detection task.
2Reliability
If all user clickstream data is processed to ensure no suspicious users are missed, then detection completeness is improved, but processing time and computational resources increase
Solution Approach 1:
The system performs preliminary filtering of search strings against a suspicious keyword database before conducting full clickstream analysis. This preliminary action eliminates the majority of benign users from further processing, reducing computational resources and time required for the main detection task.
Solution Approach 2:
The system applies different levels of analysis intensity to different user groups: users with suspicious search keywords receive full clickstream analysis, while users without matching keywords receive minimal or no analysis. This local differentiation of quality maintains detection completeness for high-risk users while reducing overall processing time.
3Measurement precision
If the system analyzes detailed clickstream data to improve identification accuracy, then user identification precision is improved, but processing resources and computational power increase
Solution Approach 1:
The system segments users into high-priority and low-priority groups based on search keyword matching. Only high-priority users undergo detailed clickstream analysis, while low-priority users are processed with minimal resources. This segmentation maintains identification accuracy for suspicious users while dramatically reducing overall computational resource consumption.
Solution Approach 2:
The system applies full analysis intensity (excessive action) only to the subset of users who triggered suspicious keywords, rather than applying partial analysis to all users. This selective application of excessive action ensures high identification accuracy for the critical minority while avoiding wasteful resource consumption on the benign majority.
Data Source
AI summary
An artificial intelligence based system and method for predicting and preventing illicit behavior is disclosed. The system and method may include obtaining search strings used by multiple users, as well as the clickstream data of such users. The search terms included in the search strings may be preprocessed and analyzed for inclusion of suspicious words, e.g., words related to illicit behavior, provided in a corpus of suspicious words. Information associated with the search strings containing suspicious words may be analyzed to identify users associated with the same search strings. The clickstream of the identified users may be analyzed to determine whether the users are likely to engage in illicit behavior. Preventive measures may be taken to prevent such users from engaging in such illicit behavior.