Arize AI
Search…
Arize AI
Arize AI
What is ML Observability?
Examples
Common Use Cases
Click-Through Rate
Collaborative Filtering (Recommendation Engine)
Timeseries Forecasting
Fraud
Churn Forecasting
Lending
Recommendation System
Customer Lifetime Value
Demand Forecasting
Insurance
Glossary
User Guides
Sign Up / Log in
Quickstart
1. Setting Up Your Account
2. Sending Data
3. Set a Model Baseline
4. Set up Model Monitors
5. Performance Tracing
6. Troubleshoot Drift
7. Troubleshoot Embedding Data
8. Model Explainability
9. Set up a Dashboard
10. Troubleshoot Data Consistency
11. Bias Tracing (Fairness)
Advanced
Product FAQ
Data Ingestion
Overview
Model Schema
API Reference
File Importer - Cloud Storage
Data Ingestion FAQ
Integrations
Monitoring Integrations
ML Platforms
GraphQL API
SSO
On-Premise Deployment
Overview
Requirements
Installation
Homepage
Product Release Notes
Powered By
GitBook
Common Use Cases
Use-case specific examples of how to leverage Arize to troubleshoot your ML models.
Troubleshoot common use-case specific problems using Arize —the leading ML Observability platform.
​
Learn how to set up proactive monitors for chargebacks (false negative rate) and false positive transactions for your credit card fraud model.
Fraud
Troubleshoot bad data quality, drifting features, and low performing cohorts of your ad click-through rate model.
Click-Through Rate
Identify where your demand forecasting model is over/under predicting and for which items/locations your model might require retraining.
Demand Forecasting
Improve your customer lifetime value model through identifying low performing cohorts and drifting features.
Customer Lifetime Value
Analyze your recommendation engine model's performance across various slices and dive into which features could be causing performance degradation.
Recommendation System
​
Contact us at
[email protected]
to contribute an example to the list or request a tutorial!
​
Previous
Integrations with ML Platforms
Next
Click-Through Rate
Last modified
1mo ago
Copy link
Contents
Troubleshoot common use-case specific problems using Arize —the leading ML Observability platform.
Learn how to set up proactive monitors for chargebacks (false negative rate) and false positive transactions for your credit card fraud model.
Troubleshoot bad data quality, drifting features, and low performing cohorts of your ad click-through rate model.
Identify where your demand forecasting model is over/under predicting and for which items/locations your model might require retraining.
Improve your customer lifetime value model through identifying low performing cohorts and drifting features.
Analyze your recommendation engine model's performance across various slices and dive into which features could be causing performance degradation.