Blockchain Batch Transaction Detection Using Reduced Feature Sets
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 for efficient batch transaction detection.
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 use of energy and computational cost increase
Solution Approach 1:
The patent segments the transaction analysis process into two distinct phases: an offline training phase where a machine learning model is trained using historical transaction data, and an online detection phase where the trained model rapidly classifies new transactions. This segmentation allows computationally intensive operations to be performed once offline, while online operations require minimal computational resources, thus resolving the contradiction between analytical accuracy and computational cost.
Solution Approach 2:
The patent performs preliminary action by training the machine learning model offline using historical transaction data before actual transaction detection occurs. The model learns patterns and characteristics of batched transactions during this preliminary phase, so that when real transactions need to be analyzed, the heavy computational work has already been completed, enabling fast and accurate real-time detection with minimal energy consumption.
2Ease of operation
If heuristic methods are used to label transactions as batched or unbatched, then ease of operation is improved, but productivity deteriorates due to computational expense
Solution Approach 1:
The patent replaces the mechanical heuristic analysis method with a machine learning-based system. Instead of manually or algorithmically analyzing transaction features in real-time, a trained model automatically performs classification. This substitution maintains ease of operation while dramatically improving productivity, as the model can process transactions rapidly without the computational overhead of traditional heuristic methods.
3Device complexity
If feature selection is applied to remove redundant and collinear features, then device complexity is reduced, but loss of information may occur
Solution Approach 1:
The patent applies parameter changes by systematically evaluating and selecting features based on their predictive power for batched transaction detection. The feature selection process transforms the original feature set by removing redundant and collinear features while retaining those with highest predictive value. This parameter optimization reduces model complexity and computational requirements while preserving the essential information needed for accurate transaction classification.
Data Source
Figure 1
Figure 2
Figure 3
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, each item having a set of features and associated feature values. The method further comprises 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. The method then uses a feature selection method to remove from the aggregated transaction data redundant features and collinear features, in order to generate a reduced transaction data set having substantially independent features relevant to batch transaction detection. The redundant features are features determined not to be predictive for detecting batch transactions and wherein collinear features are features determined to be highly correlated with each other. The method then 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 on the basis of the values of the features determined to be relevant to batch transaction detection.