Get Started
Research questionHow can extracted rules from tree ensembles retain calibrated probabilities while simplifying predictions?Rule extraction makes tree-ensemble decisions easier to inspect, but compact rulesets can distort the probabilities attached to those decisions. This matters when users need trustworthy confidence estimates rather than class labels alone.
Machine Learning
Statistical Machine Learning
Latest papersRecent research connected to this question, newest first.RCProb: Probabilistic rule extraction from classification tree ensemblesThe evidence concerns random-forest and gradient-boosting classification ensembles evaluated on 18 binary and 5 multiclass datasets. It reports effects on log loss, rule count, macro-F1, and calibration, including a controlled experiment using dedicated calibration data.research paper · Sep 3, 2026
Related questions
How can ensemble classifiers retain accuracy and generalization with far fewer base learners?How can multiclass post-hoc calibration improve confidence without changing top-1 predictions?How can we explain interacting reasons behind classifier predictions fast enough for repeated local use?How can teams estimate whether multiclass accuracy gains reduce optimization regret before building a model?
Home
Topics
Search
Library