Results for "preference scoring"
Credit Scoring
Intermediate
Predicting borrower default risk.
RLHF
Intermediate
Reinforcement learning from human feedback: uses preference data to train a reward model and optimize the policy.
DPO
Intermediate
A preference-based training method optimizing policies directly from pairwise comparisons without explicit RL loops.
Brier Score
Intermediate
A proper scoring rule measuring squared error of predicted probabilities for binary outcomes.
Inverse Reinforcement Learning
Advanced
Inferring reward function from observed behavior.
Value Learning
Intermediate
Inferring and aligning with human preferences.
Explainability Requirement
Intermediate
Legal or policy requirement to explain AI decisions.
Risk Register
Intermediate
Central log of AI-related risks.
Batch Inference
Intermediate
Running predictions on large datasets periodically.
Explainable Credit Model
Intermediate
Credit models with interpretable logic.