Imagine you built a machine-learning prediction model that was trained on specific data, from a certain timeframe, and this data includes specific age ranges. But while the model is in production, a new policy is released and a whole new population with different age ranges begins receiving predictions from your model, ultimately leading to inaccurate predictions and revenue decline. You might think your models are working well, only to learn later that a small error or inaccurate report can be causing major issues. By monitoring your machine-learning models, you can better understand the effectiveness of your algorithms and ensure they actually benefit your business.
That’s why New Relic is partnering with Aporia to integrate Aporia’s alerts into New Relic One, provide full model management of the MLOps infrastructure, and offer customized dashboards within New Relic that show inferences investigation.
This allows you to seamlessly collaborate between data science and DevOps teams, making it easier to develop, test, and monitor sophisticated ML models.
The following video shows how to customize your model performance metrics with New Relic to start visualizing accurate prediction reportings, using the Inferences feature from Aporia.
New Relic Alerts and Applied Intelligence offers a flexible and centralized notification system that unlocks the ability of users to monitor their operational needs and uses machine-learning models.
With New Relic Alerts, you can manage alert policies and conditions, letting you focus on the metrics you care most about. Applied Intelligence helps you detect, understand, and resolve problems faster. Specifically, it's a hybrid machine-learning engine that automatically detects anomalies, reduces alert noise by correlating related alerts and incidents, and provides automatic root cause analysis.
New Relic One Alerts & AI: You can use the overview summary page to quickly review your violations, issues, and incidents.
Aporia is a fast, easy, and secure way for data science teams to monitor their machine-learning models in production and build their own customizable monitors to receive live alerts for early detection of issues like data drift, unexpected bias, data integrity issues, and performance degradation.
An example of an Aporia dashboard in New Relic One showing model inferences, features, and data behavior for an insurance sales prediction model in production
Aporia allows you to connect alerts generated by Aporia’s monitors to New Relic’s Incident Intelligence engine and the predictions data to create a comprehensive monitoring dashboard in New Relic for your ML models.
Say goodbye to unclear ML model visibility and hello to customizable and predictable ML performance. New Relic’s partnership with Aporia will provide your team full observability into ML-powered applications and the future of software.
For more information on how to set up New Relic MLOps or integrate Aporia in your observability infrastructure, visit the Incident Intelligence documentation on configuring Aporia.
Next steps
If you’re new to New Relic but interested in digging in, experience the simplicity of New Relic One yourself by signing up for a forever free account.
The views expressed on this blog are those of the author and do not necessarily reflect the views of New Relic. Any solutions offered by the author are environment-specific and not part of the commercial solutions or support offered by New Relic. Please join us exclusively at the Explorers Hub (discuss.newrelic.com) for questions and support related to this blog post. This blog may contain links to content on third-party sites. By providing such links, New Relic does not adopt, guarantee, approve or endorse the information, views or products available on such sites.
