> ## Documentation Index
> Fetch the complete documentation index at: https://arize-ax.mintlify.dev/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# User guide: ML

> Resources for Best Practices in ML Observability

ML Observability is the practice of obtaining a deep understanding into your model’s data and performance across its lifecycle. Observability doesn't just stop at surfacing a red or green light, but enables ML practitioners to root cause/explain why a model is behaving a certain way in order to improve it. Check out how Arize works across the ML Lifecycle to get the most out of ML Observability.

<Frame caption="Arize across the ML Workflow">
  <img src="https://storage.googleapis.com/arize-phoenix-assets/assets/images/Arize%20cycle%20diagram-100.jpg" />
</Frame>

## ML Observability: Resources

* [ML Observability: Industry Certification](https://courses.arize.com)

* [ML Observability: Advanced Course](https://arize.com/blog-course/)

* [ML Observability 101 Intro Video](https://www.youtube.com/watch?v=MD6vPNCTwdw)

* [ML Observability 101: Ebook](https://arize.com/resource/whitepaper-machine-learning-ecosystem-101/)

* [Model Performance Management (Paper)](https://arize.com/resource/modern-model-performance-management/)

* [What To Look for In An ML Observability Platform (Buyer's Checklist)](https://arize.com/resource/machine-learning-observability-checklist/)

* [A Guide To Automated Model Retraining](https://arize.com/resource/a-guide-to-optimizing-automated-model-retraining/)

* [Central ML: Best Practices for Ramping Up on ML Observability](https://arize.com/resource/best-practices-for-central-ml-teams-ml-observability/)

<Frame caption="ML observability in context">
  <img src="https://storage.googleapis.com/arize-phoenix-assets/assets/images/arize-docs-images/5ef1c579-image.jpeg" />
</Frame>

## ML Observability: Fundamentals

### [What Is Observability?](https://arize.com/blog-course/what-is-observability-data-machine-learning/)

* [ML Observability: The Essentials](https://arize.com/blog-course/machine-learning-observability-essentials/)

* [Tracing In Machine Learning](https://arize.com/blog-course/performance-tracing-machine-learning/)

### [Model Evaluation Metrics](https://arize.com/blog-course/model-evaluation-metrics/)

* [Binary Cross Entropy](https://arize.com/blog-course/binary-cross-entropy-log-loss/)

* [Precision](https://arize.com/blog-course/precision-ml/)

* [Recall](https://arize.com/blog-course/precision-vs-recall/)

* [F1 Score](https://arize.com/blog-course/f1-score/)

* [Calibration Curve](https://arize.com/blog-course/what-is-calibration/)

* [PR AUC](https://arize.com/blog/what-is-pr-auc/)

* [AUC ROC](https://arize.com/blog/what-is-auc/)

* [Mean Absolute Percentage Error (MAPE)](https://arize.com/blog-course/mean-absolute-percentage-error-mape-what-you-need-to-know/)

* [Normalized Discounted Cumulative Gain (NDCG)](https://arize.com/blog-course/ndcg/)

* [Other Rank Aware Evaluation Metrics](https://arize.com/blog-course/monitoring-collaborative-filtering-recsys/)

### [Drift Metrics](https://arize.com/blog-course/drift/)

* [Data Binning](https://arize.com/blog-course/data-binning-production/)

* [Population Stability Index (PSI)](https://arize.com/blog-course/population-stability-index-psi/)

* [KL Divergence](https://arize.com/blog-course/kl-divergence/)

* [Jensen Shannon Divergence](https://arize.com/blog-course/jensen-shannon-divergence/)

* [Kolmogorov Smirnov Test](https://arize.com/blog-course/kolmogorov-smirnov-test/)

### [Fairness & Bias Metrics](https://arize.com/blog-course/fairness-bias-metrics/)

* [Bias Tracing](https://arize.com/blog/machine-learning-bias-tracing/)

### [Data Quality](https://arize.com/blog-course/data-quality-management-for-mlops/)

* [Solving Data Quality With ML Observability](https://arize.com/blog/solving-data-quality-with-ml-observability-and-data-operations/)

### [Service Monitoring Metrics](https://arize.com/blog-course/service-monitoring-metrics/)

* [ML Service-Level Performance Monitoring Essentials](https://arize.com/blog-course/ml-service-level-performance-monitoring/)

### [Explainability](https://arize.com/blog-course/explainability-xai-primer/)

* [Explainability Techniques](https://arize.com/blog-course/explainability-techniques-shap/)

### [Monitoring Image and Language Models and Embeddings](https://arize.com/blog-course/embeddings-meaning-examples-and-how-to-compute/)

* [KNN Algorithm](https://arize.com/blog-course/knn-algorithm-k-nearest-neighbor/)

* [Tokenization](https://arize.com/blog-course/tokenization/)

* [Embedding Versioning](https://arize.com/blog-course/embedding-versioning/)

* [Dimensionality Reduction](https://arize.com/blog-course/sne-t-sne-umap/)

* [Monitoring Embedding/Vector Drift](https://arize.com/blog-course/embedding-drift-euclidean-distance/)

* [BERT](https://arize.com/blog-course/unleashing-bert-transformer-model-nlp/)

* [Bleu Score and Other Large Language Model Metrics](https://arize.com/blog-course/generative-ai-metrics-bleu-score/)