Knowledge Hub
XAI Wikis
Explainable AI
AI Regulations in China
AI Regulations in the European Union (EU)
AI Regulations in the US
AI Regulations in India
Model safety
Synthetic & Generative AI
MLOps
Model Performance
ML Monitoring
Explainable AI
Explainable AI

LOCO

The LOCO method seeks to understand the significance of a particular feature for a model's prediction performance.

The Leave-One-Covariate-Out (LOCO) method seeks to understand the significance of a particular feature for a model's prediction performance. By calculating the mean change in accuracy for each variable throughout the entire data set, LOCO generates global variable importance measures and can provide confidence intervals.

Liked the content? you'll love our emails!

Thank you! We will send you newest issues straight to your inbox!
Oops! Something went wrong while submitting the form.

See how AryaXAI improves
ML Observability

Learn how to bring transparency & suitability to your AI Solutions, Explore relevant use cases for your team, and Get pricing information for XAI products.

Schedule a demo

Modern solution for ML Observability awaits

Schedule a demo
What is AryaXAI
Learn about our product →
Access Resources
Articles, Videos, Wikis and more →
Contact Us
Get to know us →

AryaXAI is a full stack ML Observability tool for mission-critical AI functions. Designed by Arya.ai, it is aimed to deliver much required common platform between stakeholders and deliver trust, transparency and auditability.

PRODUCTS
Explainable AI
ML Monitoring
ML Audit
Policy Control
Pricing
RESOURCES
Blog
Videos
Research
Wikis
All Resources
COMPANY
About Us
Contact Us
Careers
© Copyright 2024, Lithasa Technologies Pvt. Ltd.

By clicking “Accept All”, you agree to the storing of cookies on your device to enhance site navigation, analyze site usage, and assist in our marketing efforts. View our Privacy Policy for more information.

DenyAccept All
Internet Information Service Algorithm Recommendation Management Regulations
Generative AI Measures in China
Provisions on the Administration of Deep Synthesis of Internet-based Information Services
Artificial Intelligence and Algorithmic Fairness Initiative
The EU AI Act
Artificial Intelligence Risk Management Framework (AI RMF 1.0)
Federal Trade Commission (FTC)
President Biden's Executive Order on AI
Principles for Responsible AI
Digital India Act
Draft National Data Governance Framework Policy
National Strategy for Artificial Intelligence #AIFORALL: NITI Aayog
National Cybersecurity Reference Framework
Global Partnership on Artificial Intelligence (GPAI)
Top-k
Temperature
Low-Rank Adaptation (LoRA)
Quantization
Hallucination
Multi-modal models
Mixture of experts (MoEs)
Mamba
Opensource vs. Closed Source Models
Tokens
Diffusion Models
Transformers Models
Model safety
Vector database
Large Language Models (LLMs)
Foundation models
Synthetic AI
Generative AI
Z-Test
Chi-square test
Kolmogorov–Smirnov test (K–S test or KS test)
Wasserstein distance
Jensen-Shannon(JS) Divergence
Population Stability Index (PSI)
Kullback-Leibler (KL) divergence
ML Audit
Bias Monitoring
Data Monitoring
ML Observability
MLOps
Regression model
Classification model
Model confidence score
Model threshold
Surrogate models
What-if
Similar Cases
Feature Importance Store
LOCO
SHAP
LIME
Explainability
Fairness/Bias Monitoring
ML Monitoring
Accuracy
Data Processing
Precision
Recall/ Sensitivity or True Positive Rate
Specificity/ True Negative Rate:
Precision-recall curve
Confusion Matrix
F score
ROC Curves and ROC AUC
Data Drift
Model Drift