NannyML Cloud
⌘Ctrlk
HomeBlogNannyML OSS Docs
NannyML Cloud
  • ☂️Introduction
    • Quickstart
    • Data Preparation
    • Tutorials
    • How it works
    • Custom Metrics
    • Navigation
    • Adding a model
    • Model overview
    • Deleting a model
    • Model side panel
    • Account settings
    • Azure
    • AWS
    • Application setup
    • Getting Started
    • API Reference
    • Introduction
    • Tutorials
    • How it works
      • HDI+ROPE (with minimum precision)
      • Getting Probability Distribution of a Performance Metric with targets
      • Getting Probability Distribution of Performance Metric without targets
      • Getting Probability Distribution of Performance Metric when some observations have labels
      • Defaults for ROPE and estimation precision
    • Introduction
    • Tutorials
    • How it works
    • Engineering
    • Usage logging in NannyNL
    • Versions
Powered by GitBook
  1. Probabilistic Model Evaluation

How it works

This section describes the core algorithms of Probabilistic Model Evaluation that is the way the probability distributions for performance metrics are estimated.

HDI+ROPE (with minimum precision)Getting Probability Distribution of a Performance Metric with targetsGetting Probability Distribution of Performance Metric without targetsGetting Probability Distribution of Performance Metric when some observations have labelsDefaults for ROPE and estimation precision
PreviousData PreparationNextHDI+ROPE (with minimum precision)