NannyML Cloud
CtrlK
HomeBlogNannyML OSS Docs
  • ☂️Introduction
  • Model Monitoring
    • Quickstart
    • Data Preparation
    • Tutorials
    • How it works
  • Product tour
    • Navigation
    • Adding a model
    • Model overview
    • Model side panel
    • Account settings
  • Deployment
    • Azure
    • AWS
    • Application setup
  • NannyML Cloud SDK
    • Getting Started
    • API Reference
  • Probabilistic Model Evaluation
    • 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
  • Experiments Module
    • Introduction
    • Tutorials
    • How it works
  • miscellaneous
    • Engineering
    • Usage logging in NannyNL
Powered by GitBook
On this page
  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)

Last updated 1 year ago