Automated Transaction Feature Generation Model
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In machine learning, feature generation for transaction data is inefficient due to reliance on artificial experience and requires significant prior knowledge and time for verification.
Innovation Solution
A method and apparatus for training a transaction feature generation model that combines original features using various methods to create new feature vectors, which are then input into a trained model to predict and select features meeting specific conditions, thereby automating feature generation and improving efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If artificial experience summary is used for feature generation, then feature quality can be ensured, but feature generation efficiency is low and significant time is consumed
Solution Approach 1:
The system enables automated feature generation through machine learning models that self-learn from transaction data without requiring manual feature engineering. The model automatically identifies important features and generates feature representations, eliminating the need for technicians to manually summarize features based on artificial experience while maintaining or improving feature quality.
Solution Approach 2:
The patent replaces the manual mechanical process of feature engineering with an automated machine learning system. Instead of technicians manually creating and verifying features, the system uses trained models to automatically generate features from raw transaction data, substituting human cognitive work with computational processes that are faster and more scalable.
2Reliability
If technicians manually generate features based on prior knowledge, then feature relevance can be ensured, but significant time needs to be consumed for verification
Solution Approach 1:
The system performs preliminary feature generation and verification through automated machine learning pipelines. Features are pre-generated by the model and pre-verified through automated evaluation metrics and validation processes, eliminating the need for time-consuming manual verification while ensuring feature relevance through the model's learned understanding of important patterns.
Data Source
AI summary
The present specification discloses a method and an apparatus for training a transaction feature generation model, and a method and an apparatus for generating a transaction feature. The method for generating a transaction feature can include the following: obtaining a target dataset, where the target dataset includes some pieces of transaction data; obtaining some original features of the transaction data and determining one or more combination methods for the original features; determining a feature vector of a new feature that is obtained by combining the original features based on each combination method; inputting the feature vector into a trained transaction feature generation model, and outputting a prediction result of the new feature; and selecting some new features whose prediction results meet a specified condition as transaction features generated for the target dataset.