1 (866) 866-2320 Straight Talks Events Blog

Automatic Root Cause & Change Risk Analysis with Evolven’s Patented Technology


Automatic Root Cause & Change Risk Analysis with Evolven’s Patented Technology


This content is brought to you by Evolven. Evolven Change Analytics is a unique AIOps solution that tracks and analyzes all actual changes carried out in the enterprise cloud environment. Evolven helps leading enterprises cut the number of incidents, slash troubleshoot time, and eliminate unauthorized changes. Learn more

Evolven’s AI engine is growing!

Over the last month, we have announced two new patents on Root Cause Analysis and Value Configuration Analysis Approach, bringing our portfolio to a total of five patents.

When we started Evolven, we saw that the industry’s existing approaches to change monitoring and change control are flawed.

There are several reasons:

(1) Visibility

To implement effective change controls, IT needs to collect and track granular changes of various types (configuration, data, code, etc.) from the technology stack across end to end IT environments.

(2) Prioritization

As there are many changes, viable data can easily be lost in the noise, and IT teams quickly become overwhelmed with the amount of data to analyze. Prioritization is the key to get to the golden nuggets and make data actionable.

(3) Policies

Today, most existing solutions rely on a predefined set of rules to evaluate the criticality and impact of detected changes. These policies can be manually extended by users, but still limits users to only defining if the changes that were made in an environment are compliant or deviate from known states. This is flawed, as you simply cannot define an exhaustive set of rules that can accurately assess every possible change.

(4) Context

Changes do not happen in a vacuum; there is a process of change planning, change development and change execution. Once changes are deployed, IT environments are monitored to detect if there are any performance or availability issues that in most cases are a result of changes. Hence, there are strong causal relations between change requests, planned change deployments, actual changes, and performance events. To understand the state of your environment, you need to see the whole connected context glued by the actual change. For example, you experience a sudden outage in a critical business service and there were dozens of deployments that happened over the last 72 hours. It will definitely help you to know that there were a few out of process changes executed without any change requests two days ago in a key database used by the failed business service.

By lacking visibility into actual changes or being overwhelmed with change details, organizations rely on tightening their manual change processes or just accept inevitably high rates of issues.

Is this really the best approach?

Evolven’s patented change collection and analytics technology solves these critical flaws by detecting actual granular changes from a wide range of technologies, automatically prioritizing them by calculating the risk of change and building the full change context correlating planned changes, actual changes and their impact.


Our patent portfolio covers the key components in Evolven’s change analysis and correlation engine, which heavily relies on machine learning and AI using both supervised and unsupervised machine learning.

These unique capabilities allow us to construct a very comprehensive understanding of every single change executed across an enterprise’s IT environments, infrastructure and applications, answering:

Where did the change come from? Where in the stack is it? What kind of change is it? What is the initial risk of the change? What kind of issues is the change causing?

With this understanding, we are in a unique position to build a risk profile, classify change into categories and classes, and estimate lifetime profile for each change individually, no matter how granular the change.

Building a correlated context of the change, Evolven then prioritizes the change according to the use case, for example, using operational risk profile for preventive care, compliance risk for conformance with regulations, and root cause likelihood for incident investigation.

Our goal remains the same, to make changes safer while accelerating their pace without additional overhead to the IT organizations.

Through our AI-based approach, we are excited to help IT professionals work more productively, avoid performance and availability issues in the digital services they build and operate, and reduce their mean time to resolution (MTTR) with automated root cause analysis.

I am proud of the strong portfolio this team has accomplished and excited to see our hard work and our technology’s unique capabilities validated by the industry.

We’re raising the bar high for other companies to catch up.

About the Author
Bostjan Kaluza, PhD

Boštjan Kaluža is the Chief Data Scientist at Evolven. He's also a hardcore researcher who's done a lot of research into artificial intelligence and intelligent systems, machine learning, predictive analytics and anomaly detection. Prior to Evolven, Boštjan served as a senior researcher in the Department of Intelligent Systems at the Jozef Stefan Institute, the leading Slovenian scientific research institution and led research projects involving pattern and anomaly detection, machine learning and predictive analytics.


Focusing on the detection of suspicious behavior and data analysis, Boštjan has published numerous articles in professional journals and delivered conference papers. In 2013, Boštjan published his first book on data science, Instant Weka How-to, exploring how to leverage machine learning using Weka. Boštjan is now working on his second book Practical Machine Learning in Java, scheduled to be published later this year. Boštjan is also the author and contributor to a number of patents in the areas of anomaly detection and pattern recognition.


Boštjan earned his PhD at Jožef Stefan International Postgraduate School in Ljubljana, Slovenia, rigorously defending a doctoral dissertation entitled Detection of Anomalous and Suspicious Behavior Patterns.