Blockchain Batch Transaction Detection With Feature Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for analyzing blockchain-based cryptocurrency transactions, particularly batched transactions, are cumbersome and computationally expensive, making real-time identification of batched and unbatched transactions impractical and inefficient.
Innovation Solution
A computer-implemented method using a machine learning process to detect batch transactions by obtaining and aggregating transaction data, applying a two-stage feature selection method to remove redundant and collinear features, and training a model with a reduced dataset to identify batched transactions efficiently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If individual transaction analysis is performed to obtain accurate analytical data, then measurement precision is improved, but computational cost and time consumption increase significantly
Solution Approach 1:
The patent segments the analysis process into two stages: (1) aggregate-level analysis using clustering algorithms to identify potential batch transactions, and (2) detailed individual transaction analysis only for suspected batch transactions. This segmentation allows most transactions to be processed efficiently at the aggregate level while maintaining high analytical precision for transactions requiring detailed examination.
Solution Approach 2:
The patent applies different levels of analysis quality to different transactions based on their characteristics. Aggregate-level clustering provides a screening mechanism that identifies suspicious patterns, while full individual transaction analysis is applied locally only to transactions flagged as potential batch transactions. This local quality approach optimizes computational resources while maintaining analytical accuracy where needed.
2Ease of operation
If heuristic methods are used to label transactions as batched by analyzing input and output addressees, then ease of operation is improved, but productivity decreases due to the large number of inputs and outputs requiring analysis
Solution Approach 1:
The patent replaces manual or simple heuristic analysis with automated machine learning models. The system uses trained models to automatically classify transactions as batched or unbatched based on aggregated features, eliminating the need for manual analysis of numerous inputs and outputs. This substitution enables real-time processing while maintaining ease of operation through automated decision-making.
Solution Approach 2:
The patent transforms the transaction analysis problem by changing parameters from examining individual input/output addressees to analyzing aggregated transaction characteristics. The system computes aggregate features such as total input count, total output count, and value distributions, then uses these transformed parameters for classification. This parameter transformation reduces computational complexity while preserving the ability to identify batch transactions.
3Measurement precision
If all features associated with inputs and outputs are used for transaction classification, then measurement precision is improved, but device complexity increases due to redundant and collinear features
Solution Approach 1:
The patent extracts only the most relevant features for batch transaction detection from the complete set of available features. The system identifies and removes redundant features that do not contribute to detection accuracy and eliminates collinear features that provide duplicate information. This extraction process reduces feature set complexity while preserving measurement precision by retaining only the most informative characteristics.
Solution Approach 2:
The patent performs preliminary feature selection and preprocessing before the main classification task. The system pre-identifies redundant and collinear features, removes them in advance, and prepares a streamlined feature set for model training and deployment. This preliminary action reduces computational complexity during real-time operation while maintaining the precision needed for accurate batch transaction detection.
Data Source
AI summary
A computer implemented method to obtain a batch transaction detection model that uses a machine learning process to detect that a transaction of a digital currency is a batch transaction is described. The method comprises obtaining transaction data from a block in a blockchain, wherein the transaction data comprises a plurality of items; generating an aggregated transaction data set of the transaction data and labelling the aggregated transaction data set according to whether the transaction is a batch transaction, using a feature selection method to remove from the aggregated transaction data redundant features and collinear features, to generate a reduced transaction data set having substantially independent features relevant to batch transaction detection. The method trains, tests and validates the batch transaction detection model using the reduced transaction data set; where the trained batch transaction detection model is adapted to determine whether a transaction is a batch transaction.