Algorithmia logo

Algorithmia ML Model Performance Metrics Template

Template built by

Kristopher Overholt
@ Algorithmia

Telegraf Plugins used:

Included Resources:

  • Bucket: insights
  • 1 Dashboard: Algorithmia - ML Model Performance Metrics
  • 1 Telegraf configuration

Quick Install

If you have your InfluxDB credentials configured in the CLI, you can install this template with:

https://raw.githubusercontent.com/influxdata/community-templates/master/algorithmia/algorithmia.yml

Algorithmia ML Model performance metrics dashboard

Algorithmia is an MLOps platform that includes capabilities for data scientists, application developers, and IT operators to deploy, manage, govern and secure machine learning and other probabilistic models in production.

Why monitor your ML models?

Algorithmia Insights is a feature of Algorithmia Enterprise and provides a metrics pipeline that can be used to instrument, measure, and monitor your machine learning models. Measuring your model will help you understand how well your model is doing, how useful it is, as well as helping you to determine if your model could improve its performance with more data.

This template allows you to stream operational metrics and user-defined, inference-related metrics from Algorithmia to InfluxDB using Telegraf and Kafka to help you gain performance insights of your models.

How to use Algorithmia ML Model Performance Metrics Template

Once your InfluxDB credentials have been properly configured in the CLI, you can install the Algorithmia ML Model performance metrics template using the Quick Install command. Once installed, the data for the dashboard will be populated by the included Telegraf configuration, which includes the relevant Kafka Consumer Input. Note that you might need to customize the input configuration to better serve your needs, including by specifying a new input value. All of this will depend on how your organization is currently running Kafka.

To find out more information about environmental variables within the Telegraf configuration, consult the following link.

Key Algorithmia ML model performance metrics to monitor

Some of the most important Algorithmia ML Model performance metrics that you should proactively monitor include:

  • Risk Score
  • Approvals
  • Algorithm Duration
Scroll to Top