Predictive analytics for IT operations management

The client is one of the world's largest data center & colocation provider offering the fastest application performance, lowest latency routes worldwide and a digital ecosystem for financial, content or rich-media, enterprise and cloud networks.

Business Challenge

  • The client had no visibility into problematic infrastructure components and hence was unable to get any insight from its current monitoring solution for infrastructure capacity planning. This was leading to a high number of incidents, negatively impacting business services availability. The client was also unable to forecast incident and event trends.

Technology Component

  • R System and Kaggle for building statistical modelling

  • Power BI for visualization layer

  • IT Operations data from various monitoring tools


  • Conducted workshops with business and IT stakeholders to understand the challenges

  • Collected the sample data from various monitoring tools

  • Performed data preparations and cleansing activities in PoC environment

  • Developed three statistical models (ARIMA, Negative Binomial, Zero Inflation) for predicting incidents

  • Establish correlation based on Pearson Correlation

  • Integrated Kaggle with Power BI for Dashboards and Reports

  • Demonstrated the solution approach to client senior leadership team

Transformational Effects

  • Ability to forecast incidents and report trends

  • Ability to forecast disk, network, memory usage metrics and proactively plan capacity

  • Visibility into event and incident occurrence patterns

  • Incident and event correlation

Contact Us Today

By submitting your information, you agree to our revised  Privacy Policy.


Get in Touch

Let us help you
transform and grow

Let’s Talk


Status message

We're eager to assist you! Please leave a message and we'll get back to you shortly.

By submitting your information, you agree to our revised  Privacy Policy.