A Simulated Annealing Approach to Designing Optimal Decision Trees for Classification, Prescriptive, and Survival Analysis
A binary decision tree is a highly interpretable machine learning model, as humans can easily understand how a prediction is made by answering a series of binary questions. Earlier work has provided a powerful framework for constructing optimal decision trees by utilizing multiple random warm starts...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Published: |
Massachusetts Institute of Technology
2024
|
| Online Access: | https://hdl.handle.net/1721.1/153845 https://orcid.org/0000-0002-6564-9316 |