Amazon Lookout for Metrics

Automatically detect anomalies in metrics and identify their root cause

Amazon Lookout for Metrics uses machine learning (ML) to automatically detect and diagnose anomalies (i.e. outliers from the norm) in business and operational data, such as a sudden dip in sales revenue or customer acquisition rates. In a couple of clicks, you can connect Amazon Lookout for Metrics to popular data stores like Amazon S3, Amazon Redshift, and Amazon Relational Database Service (RDS), as well as third-party SaaS applications, such as Salesforce, Servicenow, Zendesk, and Marketo, and start monitoring metrics that are important to your business. Amazon Lookout for Metrics automatically inspects and prepares the data from these sources to detect anomalies with greater speed and accuracy than traditional methods used for anomaly detection. You can also provide feedback on detected anomalies to tune the results and improve accuracy over time. Amazon Lookout for Metrics makes it easy to diagnose detected anomalies by grouping together anomalies that are related to the same event and sending an alert that includes a summary of the potential root cause. It also ranks anomalies in order of severity so that you can prioritize your attention to what matters the most to your business.

What is Amazon Lookout for Metrics?


Detect anomalies with better accuracy

Amazon Lookout for Metrics uses ML to accurately detect anomalies in business metrics and reduce false positives. You can provide feedback on detected anomalies to tune the results and continuously improve accuracy and control.

Diagnose root cause faster

Amazon Lookout for Metrics makes it easier to diagnose the root cause of important anomalies by automatically grouping related anomalies together, summarizing potential root causes, and ranking them in the order of severity.

Amazon Lookout for Metrics connects seamlessly to popular AWS databases and provides pre-built connectors to third-party SaaS applications. You can get started monitoring metrics and detecting anomalies in just a few clicks.

Automate customized alerts and actions

You can easily connect Amazon Lookout for Metrics with event and notification services like Amazon Simple Notification Service and AWS Lambda to automate customized alerts and actions when anomalies are detected, such as filing a trouble ticket.

Use cases

Amazon Lookout for Metrics accurately detects and diagnoses anomalies across a broad range of business functions and industry use cases.

Monitor business performance

Improve customer experience

Optimize your digital ad spend

Boost user engagement

Identify unusual variances in your business metrics and get alerts so you can take action. Whether it’s revenue, subscriptions, or conversion rates with Amazon Lookout for Metrics you can proactively monitor business performance to stay on top of sudden changes, identify the root cause and take steps to remediate.  Some example metrics to monitor are revenue, number of purchases, order rate, shopping cart metrics, or fault in the payment gateway.

Understand customer related issues,  churn rates, install or purchase rates by detecting spikes and dips in metrics that are indicators of downstream impacts to customer experience downstream. Amazon Lookout for Metrics can notify you when such anomalies occur to help mitigate the issue and resolve it quickly.  Some example metrics to monitor are downloads, installs, page views, churn rate, or retention rates.

With multiple campaigns running simultaneously and a large number of metrics to monitor, spotting anomalies in campaign data is often time consuming and manual. With Amazon Lookout for Metrics you can immediately understand when your campaign is overspending, underperforming or has encountered an error and alert you to mission-critical incidents that impact your ad spend. Some example metrics to monitor are clicks, impressions, conversions, installs, or ad spend.

Take action to optimize user engagement by understanding changes in new users, app installs, in-app purchases, or retention rates. Get notifications when anomalies are detected in purchase patterns or interactions with ads such as a broken link. Some example metrics to monitor are revenue, number of installs, downloads, in-app purchases.

Customer stories

Using Lookout for Metrics we were able to discover an issue that was negatively impacting pricing for a Mobile Network Operator customer within minutes. We were able to instantly identify the culprit and roll out a fix within 2 hours. Without Lookout for Metrics, it would have taken us approximately a day to identify and triage the issue, and would have led to a 7.5% drop in customer revenue. Lookout for Metrics allows us to act quickly and ensure the optimal performance of our pricing models, leaving us to focus on what really matters - getting everyone connected.” 

Nico Kruger - Chief Technology Officer, Digitata

"With Amazon Lookout for Metrics, we are able to capture 20% of incidents before they actually impact our stores and our customers. It is exciting to be able to see the results in a matter of hours and not weeks or months. The service makes it easy for my team to quickly implement AI/ML driven workloads and allows us to dynamically support our operations team even in the most challenging times.”

Supratim Banerjee - Chief Transformational Officer, More Retail

“At Liberty Latin America we aim to provide the best customer experience possible and we address this in many ways. In a joint venture between IT Business Intelligence and Product Connectivity & Entertainment, we use anomaly detection to track key metrics that are indicators of a fall in the customer experience.  Using Amazon Lookout for Metrics, we are more easily able to identify real anomalies and alert our team to potential drops in customer experience.” 

Sergio Rodriguez -  Sr. Manager, Entertainment & Connectivity Product Quality, Liberty Latin America

"By leveraging Amazon Lookout for Metrics to parse events from CloudWatch we were able to go to production in an afternoon and reduce our false positive rate by 7x. This lets our Site Reliability Engineers focus on alerts with confidence and gives us the tools to tackle even more complex operational and business issues in the future."

Omar Lopez - Tech Lead of Infrastructure, Flywire

"With Lookout for metrics, we are able to automatically monitor data across all the important categories with a few clicks and identify anomalous events in nearly 40% cases that we missed earlier. By quickly identifying such cases, we are able to adjust our inventory planning and distribution across all stores in an optimal way."

Rahul Subrananiam - CEO, Devfactory

"Lookout for Metrics has saved our team many hours of manual investigation and now notifications are viewed as actionable rather than noise, allowing our teams to easily focus on strategic priorities with less technical overhead.”

Mikhail Artyugin - Technical Director, Playrix

Product Features
Check out the product features

Learn more about the features of Amazon Lookout for Metrics

Learn more 
Sign Up
Sign up for a free account

Instantly get access to the AWS Free Tier. 

Sign up 
Start Building
Start building in the console

Get started building with Amazon Lookout for Metrics in the AWS Console

Get started