Decision Tree Classification Handling Missing Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing decision-tree systems are ineffective in handling missing data, which can lower the quality of results produced in data classification tasks.
Innovation Solution
A decision-tree system and method that incorporates a tree-generation module and a distinction module capable of handling both real-value and set-value data, allowing for quantitative and qualitative comparisons, and accounting for missing data during the generation and training of the decision tree to improve predictive power.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a typical computerized decision-tree analysis is used, then the classification process is simple, but the quality of results deteriorates when missing data is present
Solution Approach 1:
The distinction module is divided into specialized sub-modules: a real-value comparison module for quantitative data and a set-value determination module for qualitative data. This segmentation allows each module to handle specific data types optimally, improving classification reliability while maintaining manageable complexity through modular design.
Solution Approach 2:
The decision-tree system is designed with a universal distinction module that can handle multiple data types (real values and set values) through a unified interface. The module adapts its processing method based on the data type encountered, enabling the system to process diverse data formats without requiring separate specialized systems for each data type.
2Measurement precision
If missing data is handled by typical decision-tree systems, then the processing speed is maintained, but the measurement precision deteriorates
Solution Approach 1:
The system performs preliminary determination of data types (real value or set value) and prepares appropriate processing paths before actual classification. This preliminary action includes identifying missing data patterns and selecting the appropriate comparison or determination method in advance, ensuring precise handling of each data type while maintaining efficient processing throughput.
Solution Approach 2:
The distinction module dynamically changes its processing parameters based on the data type encountered. For real-value data, it uses quantitative comparison operations; for set-value data, it uses qualitative determination operations. This parameter adaptation allows the system to maintain high measurement precision for each data type while avoiding the time penalty of using a single rigid processing method for all data.
Data Source
AI summary
Systems and methods are disclosed for classifying records by sorting records based on both quantitative and qualitative information at a node in a decision tree. Technologies are also disclosed for determining whether records are linked together by applying quantitative and qualitative information at the same nodes in a decision tree. Furthermore, improvements to decision trees are disclosed in terms of the generation and/or training of decision trees that harnesses additional information in the quantitative and qualitative aspects that a unit of data relevant to a single node, and/or the relationships between these aspects, may provide a machine learning algorithm.