Data Clustering System for Risky Trading Investigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Analysts face challenges in efficiently selecting and prioritizing relevant data items within large electronic collections for investigations, such as risky trading, due to the difficulty in processing and analyzing vast amounts of data, and existing systems require manual repetition of searches, leading to time-consuming and resource-intensive investigations.
Innovation Solution
A data analysis system that automatically generates memory-efficient clustered data structures, analyzes them, and provides an interactive user interface for efficient evaluation, allowing analysts to dynamically re-group and filter data clusters based on automated scoring and prioritization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If analysts manually search and process large electronic collections of data items, then they can identify relevant data for investigations, but the processing time and resource consumption increase significantly
Solution Approach 1:
The patent segments the large electronic collection of data items into multiple clusters, where each cluster contains a subset of related data items. This segmentation allows analysts to navigate and evaluate data in smaller, more manageable groups rather than processing the entire collection at once, thereby reducing the time and resources required while maintaining the ability to identify relevant data through systematic cluster evaluation.
2Quantity of substance
If all data items are stored in electronic memory for analysis, then complete data availability is achieved, but memory consumption becomes excessive
Solution Approach 1:
The patent divides the large set of data items into multiple smaller clusters that are stored and processed separately in electronic memory. Each cluster contains a manageable subset of data items that can be loaded into memory for analysis. This segmentation enables the system to work with complete data availability on a cluster-by-cluster basis rather than requiring all data to be simultaneously present in memory, thereby significantly reducing peak memory consumption while maintaining data accessibility.
3Ease of operation
If clusters of data items are created for organization, then data navigation becomes easier, but the number of clusters to evaluate increases the complexity of analysis
Solution Approach 1:
The patent extracts and applies multiple evaluation criteria to each data cluster to generate scores that indicate the likelihood of risky activity. By taking out the complex evaluation task and automating it through systematic scoring based on predefined criteria (such as trading patterns, data item relationships, and risk indicators), the system reduces the manual complexity of evaluating numerous clusters. Analysts can then prioritize clusters based on these automated scores rather than manually assessing each cluster, thereby maintaining ease of navigation while reducing evaluation complexity.
4Adaptability or versatility
If manual searching and analysis methods are used, then flexibility in investigation approach is maintained, but productivity and efficiency decrease
Solution Approach 1:
The patent implements a dynamic system where data clusters are automatically evaluated using multiple criteria that can be adjusted and refined. The scoring mechanism allows for dynamic prioritization of clusters based on risk indicators and evaluation results. This dynamic approach maintains flexibility in investigation strategies while significantly improving productivity through automated cluster evaluation and prioritization, enabling analysts to quickly identify high-risk clusters without sacrificing investigative adaptability.
Data Source
AI summary
Embodiments of the present disclosure relate to a data analysis system that may automatically generate memory-efficient clustered data structures, automatically analyze those clustered data structures, automatically tag and group those clustered data structures, and provide results of the automated analysis and grouping in an optimized way to an analyst. The automated analysis of the clustered data structures (also referred to herein as data clusters) may include an automated application of various criteria, rules, indicators, or scenarios so as to generate scores, reports, alerts, or conclusions that the analyst may quickly and efficiently use to evaluate the groups of data clusters. In particular, the groups of data clusters may be dynamically re-grouped and/or filtered in an interactive user interface so as to enable an analyst to quickly navigate among information associated with various groups of data clusters and efficiently evaluate those data clusters in the context of, for example, a risky trading investigation.