# AI/ML Analytics

ElastiFlow offers a suite of anomaly detection jobs specifically tailored for Elasticsearch's machine learning framework. These jobs are meticulously designed to safeguard and enhance network performance, availability, and security. By integrating seamlessly with Elasticsearch, ElastiFlow utilizes the platform's advanced machine learning capabilities to continuously monitor and analyze network traffic and performance metrics. This integration enables ElastiFlow to detect a wide range of anomalies — from unusual traffic patterns that could indicate performance bottlenecks, to subtle signs of security threats like network intrusions or data breaches.

#### Downloads

| Schema    | Link                                                                                                                      |
| --------- | ------------------------------------------------------------------------------------------------------------------------- |
| **CODEX** | [All ML Jobs for CODEX Schema](https://github.com/elastiflow/elastiflow_for_elasticsearch/raw/master/ml/codex/codex.json) |
| **ECS**   | [All ML Jobs for ECS Schema](https://github.com/elastiflow/elastiflow_for_elasticsearch/raw/master/ml/ecs/ecs.json)       |

{% hint style="info" %}
Tip: If you wish to import **all** of the available ElastiFlow-provided anomaly detection jobs, the above downloads are exactly what you are looking for.
{% endhint %}

#### Elasticsearch ML Framework

Elasticsearch includes advanced anomaly detection capabilities within its machine learning framework, providing a powerful tool for monitoring and maintaining network performance, availability, and security. It uses sophisticated machine learning algorithms to analyze data patterns and identify anomalies. This approach is particularly effective because it adapts to the changing behavior of data over time, providing a dynamic and accurate detection mechanism. It can spot unusual trends, spikes, or drops in metrics that could indicate problems.

One of Elasticsearch's strengths is its ability to perform real-time analysis. This is vital for network systems where immediate detection of issues such as traffic surges, performance bottlenecks, or security breaches can prevent significant disruptions or damage.

The platform's use of unsupervised learning means it can identify anomalies without having been explicitly programmed to look for specific issues. This capability is crucial in detecting unknown or emerging threats and issues, which are not yet understood or have not been previously encountered. Anomalies are scored based on their severity, allowing network administrators to prioritize issues for investigation and response. The system can also be configured to send automated alerts in response to detected anomalies, ensuring that potential problems are addressed promptly.

The anomaly detection jobs provided by ElastiFlow are crucial for preemptively identifying potential issues, allowing network administrators to take timely actions to maintain optimal network health. By leveraging this powerful combination, ElastiFlow empowers organizations to proactively manage their networks, ensuring they remain robust, available, and secure against an ever-evolving landscape of network challenges and threats.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.elastiflow.com/data_platforms/elastic/ml.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.