17899534. OPTIMAL CONSTRAINED MULTIWAY SPLIT CLASSIFICATION TREE simplified abstract (International Business Machines Corporation)
Contents
OPTIMAL CONSTRAINED MULTIWAY SPLIT CLASSIFICATION TREE
Organization Name
International Business Machines Corporation
Inventor(s)
Shivaram Subramanian of Frisco TX (US)
Markus Ettl of Yorktown Heights NY (US)
OPTIMAL CONSTRAINED MULTIWAY SPLIT CLASSIFICATION TREE - A simplified explanation of the abstract
This abstract first appeared for US patent application 17899534 titled 'OPTIMAL CONSTRAINED MULTIWAY SPLIT CLASSIFICATION TREE
Simplified Explanation
The computer-implemented machine learning method involves accessing a decision tree associated with a path-based machine learning model, splitting the decision tree into multiple multiway decision trees in a path-based formulation, and solving a problem using one or more of these decision trees through a mixed-integer program (MIPS).
- Each decision tree in the plurality has an attribute that does not repeat within the tree.
- The decision rules of the decision tree are mapped using a mixed-integer program (MIPS).
---
- Potential Applications
- Predictive analytics
- Fraud detection
- Recommendation systems
- Problems Solved
- Efficiently solving problems associated with machine learning models
- Handling decision trees with unique attributes in a path-based formulation
- Benefits
- Improved accuracy in solving machine learning problems
- Better performance in decision-making processes
- Enhanced scalability and efficiency in handling decision trees
Original Abstract Submitted
A computer-implemented machine learning method includes accessing a decision tree associated with a path-based machine learning model. The decision tree is split into a plurality of multiway decision trees in a path-based formulation, each of the plurality of decision trees having an attribute not occurring more than once in each of the plurality of decision trees. A problem associated with the machine learning model is solved using one or more of the plurality of decision trees in which one or more decision rules of the decision tree are mapped using a mixed-integer program (MIPS).