cnvrg.io docs

# Anomaly Detection Blueprint - deprecated from 11/2024

# Inference

Anomaly detection involves distinguishing data variations, deviations, and exceptions from normal expectations for the purpose of detecting outliers in a dataset. Real-world examples of its use cases include detecting fraudulent transactions, adversary attacks, network intrusions, anomalous customers, and abnormal equipment behaviors.

# Purpose

Use this inference blueprint to immediately detect data anomalies or outliers in a dataset. To use this pretrained anomaly-detector model, create a ready-to-use API-endpoint that can be quickly integrated with your data and application.

This inference blueprint’s model was trained using anomalous customers based on their attributes and subscriptions to services. To use custom data according to your specific business, run this counterpart’s training blueprint, which trains the model and establishes an endpoint based on the newly trained model.

# Instructions

NOTE

The minimum resource recommendations to run this blueprint are 3.5 CPU and 8 GB RAM.

Complete the following steps to deploy an anomaly-detector API endpoint:

  1. Click the Use Blueprint button. Use Blueprint

  2. In the dialog, select the relevant compute to deploy the API endpoint and click the Start button.

  3. The cnvrg software redirects to your endpoint. Complete one or both of the following options:

    • Use the Try it Live section with any input data point to check your model. Try it Live
    • Use the bottom integration panel to integrate your API with your code by copying in the code snippet. Integration

An API endpoint that detects whether an input data point is an anomaly has now been deployed. For information on this blueprint's software version and release details, click here.

Refer to the following blueprints related to this inference blueprint:

# Training

Anomaly detection involves distinguishing data variations, deviations, and exceptions from normal expectations for the purpose of detecting outliers in a dataset. Real-world examples of its use cases include detecting fraudulent transactions, adversary attacks, network intrusions, anomalous customers, and abnormal equipment behaviors.

# Overview

The following diagram provides an overview of this blueprint’s inputs and outputs. Overview

# Purpose

Use this training blueprint to train multiple algorithms and identify the best performer to detect data anomalies or outliers. This blueprint also establishes an endpoint that can be used to make inferences for anomaly detections based on the newly trained model.

This is a one-click, train-and-deploy blueprint for predicting data anomalies. Place the labeled input data in CSV format in a connector such as S3 or Splunk, which the blueprint uses to train multiple algorithms. The best performing algorithms are selected and deployed as an API endpoint. Then, users can call this API on new data points and view responses whether the new data points are outliers.

# Deep Dive

The following flow diagram illustrates this blueprint’s pipeline: Deep Dive

# Instructions

NOTE

The minimum resource recommendations to run this blueprint are 3.5 CPU and 8 GB RAM.

Complete the following steps to train an anomaly-detector model:

  1. Click the Use Blueprint button. Use Blueprint

  2. In the dialog, select the relevant compute to deploy the API endpoint and click the Start button.

  3. The cnvrg software redirects to your endpoint. Complete one or both of the following options:

    • Use the Try it Live section with any input data point to check your model. Try it Live
    • Use the bottom integration panel to integrate your API with your code by copying in the code snippet. Integration

An API endpoint that detects whether an input data point is an anomaly has now been deployed. For information on this blueprint's software version and release details, click here.

# Connected Libraries

Refer to the following libraries connected to this blueprint:

Refer to the following blueprints related to this training blueprint:

Last Updated: 9/9/2024, 6:43:51 PM