CASE STUDY High Tech

Global Telecom Accelerates New Digital Services with AI

This company is one of the world’s leading telecommunications groups, with a significant presence in Europe, the Middle East, Africa and Asia-Pacific.

A leader in network quality, the company prides itself on offering excellent customer experience and providing integrated, worry-free solutions. The company’s roots are in mobile, but its digital service offering has expanded dramatically across multiple channels in order to stay ahead of the competition.

This put enormous pressure on delivery teams to churn out multiple applications, devices, and maintenance releases. It’s QE processes could not keep up and service levels and customer satisfaction suffered.

  • 450M+ mobile customers

    450M+ mobile customers

  • 10m+ fixed broadband customers

    10m+ fixed broadband customers

  • 9M+ TV customers

    9M+ TV customers

ai to accelerate delivery of digital services

Infostretch worked with this global telecom giant beginning in 2018 for over a year.

The focus was on optimizing device and service testing and Infostretch deployed a solution utilizing AI to optimize the most crucial components of the QE process.

the Results

Key Outcomes

Cost Savings

Cost Savings

Cost savings of nearly 1.4M EURO over a three-year period

Faster Cycle Time

Faster Cycle Time

More effective testing cycles are speeding up testing execution by as much as 35%

Higher Service Levels

Higher Service Levels

Better ability to predict risks and failures prevents device and application errors

Our methodology

how
we did it

Infostretch works with companies across the digital lifecycle.

Go Digital
Go Digital

Accelerating the delivery of new digital initiatives with confidence

Be digital
Be digital

Creating the infrastructure and foundation to scale digital initiatives

Evolve Digital
Evolve Digital

Leveraging data and analytics to continuously improve digital delivery processes

The challenge
Heightened QE load & complexity

The rapid adoption of smartphones and next generation digital devices resulted in OEMs launching and updating devices at more frequent intervals. Similarly, new applications and digital services were also being launched to engage customers.

Unable to handle growth unassisted

The company needed a partner with the ability to leverage the latest digital tools and platforms to help it get control of its growing QE requirements for up to 40 different applications, 200 new devices, 25 different device families and 1,000+ maintenance releases.

Lacking technology solutions

The company needed a solution and platform that could leverage the latest technologies like AI, machine learning, cloud computing, and predictive analytics to manage their hefty yearly validation requirements.

Dated digital services

The inability to provide engaging digital experiences and service quality would lead directly to dissatisfied customers and revenue loss.

Difficulty keeping up with evolving technology

This explosion of applications, devices, and maintenance dramatically increased the QE load for the company.

Testing difficulties

Increased testing complexity further exacerbated the situation.

The Solution

Optimizing the qe process

Infostretch set out to optimize the most crucial components of the company’s QE process using ASTUTE, an AI-powered accelerator tool that uses machine learning.

Using ASTUTE, Infostretch provided predictive analytics and prescriptive insights based on historical testing data.

Leveraging data from past releases such as defect data and release notes – features implemented and defects fixed, ASTUTE provided risk levels and test case failure probabilities for each area of an upcoming release.

6-12 Month Timeline

Platform Development, On-Boarding Service, Deployment and Rollout.

testing services

Module Risk Prediction
  • Module Risk Prediction

Based on historical defects

Defect Prediction
  • Defect Prediction

For a future regression test run based on the same historical defects, source code process metrics and current release information

Integration into Test Automation Framework
  • Integration into Test Automation Framework

To automatically trigger Jenkins job

Regression Test Generation
  • Regression Test Generation

Based on historical defects and current release information data

With the solution in place, the company has gained substantial cost savings, faster time to market and increased revenue capability.

Some of the key enablers of these benefits include:

80% average risk prediction accuracy

80% average risk prediction accuracy for device testing

77% test case failure accuracy for device testing

77% test case failure accuracy for device testing

71% defect range prediction accuracy for app testing

71% defect range prediction accuracy for app testing

83% average risk prediction accuracy for app testing

83% average risk prediction accuracy for app testing

50% decrease in total 12K data rows, data set

50% decrease in total 12K data rows, data set