Using Netuitive's self-learning analytics

I was reading through an interesting use case for Netuitive's self-learning analytics technology. It is always fascinating to learn how organizations are using technology.

Here are a few points from the use case

About The Customer -- Global manufacturer of innovative wireless solutions for the worldwide mobile communications market. Solutions incorporate email, phone, text messaging, intranet and internet based applications.

• Provides messaging, email and other services to millions of Telco end-users
• Incur significant financial penalties for downtime
• Using Netuitive, reduced alerts from 600 per day to 60 actionable alerts per week

Situation:

• The customer's biggest direct customers are large, multinational Telcos
• The company enabling critical services like e-mail, messaging, and mobile applications for the customer's millions of consumer and business users
• If services go down, or are degraded for any significant amount of time, the company's service agreements call for huge financial penalties to be paid
• The company's team is responsible for the performance of the application that monitors the service links to the Telco customers

The Problem:

• Customer realizes that it needed application performance management software.
• After selecting and installing a product, administrative staff found themselves "inundated with data" and found that it was humanly impossible to interpret or analyze it all.

The Solution:

The customer's team did more research and then tested multiple possible solutions. They settled on on Netuitive’s self-learning performance management technology.

The customer said “Netuitive is the only vendor that had the advanced predictive analytics for IT for what we were trying to do. It complements our APM solution very well and can give very accurate, advanced warning of impending application performance issues.” After going into production, Netuitive's software proved itself immediately.

Before implementing Netuitive with the APM software, the company was experiencing 600 alerts per day from one of the critical applications. After implementing Netuitive, the alerts dropped to 60 actionable alerts per week. An improvement in accuracy of 99% for performance alerts.

Snapshot analysis

The key take away points are that many distributed workloads, regardless of whether they're executing on physical or virtual server or whether they're running locally or somewhere in the clouds, have become too complex for administrators to manage in real time. In this case, adding self-learning analytical technology to the mix reduced false alerts by 99%.

Although this is a single use case, it is clear that some sort of analytical management solution is very likely to be needed when organizations deploy highly distributed, critical workloads. Netuitive is one of the many competitors to offer such tools. Of all of the competitors I've had the opportunity to speak with, Netuitive appears to be the only one offering a self-learning capability. This should make the product easier to use over the long haul.