Nbn tackles installation problems by throwing machine learning at them

machine learning
Image credit: Kunst Bilder / Shutterstock.com

Australia’s nbn co says it has developed a Tech Lab that will leverage big data and machine learning to improve the end-user experience of its access network and help resolve issues sooner.

With an average of 45,000 premises connected every week, nbn co says it is working closely with the industry to ensure continuous improvement and a seamless installation experience for end users.

When faults occur during installation, nbn’s Tech Lab will help the team determine whether a fault can be dealt with remotely and immediately, or a field technician needs to visit an end-user home to resolve the problem. This will potentially save significant time and disruption for the end user.

The Tech Lab will also help nbn better understand the key factors that drive dissatisfaction and address them so people have a better experience.

The Tech Lab will explore and implement emerging technologies such as machine learning and graph technology – which will provide insights, identify patterns, preferences and trends in people’s use and delivery of services.

Nbn said it will gather the information used in the Tech Lab through a series of end user surveys (with their express consent) about their experiences.

Open source technologies in play in the Tech Lab include Apache SPARK, Kafka, Flume, Cassandra and JanusGraph, as well as partner technologies including Amazon Web Services S3 storage, RStudio, H2O.ai and ArangoDB.

“Our Tech Lab sees us utilizing existing capability to solve a complex problem and will help provide us with crucial insights about the way people are using the nbn network,” said nbn chief systems engineering officer John McInerney. “Developing these insights will help enrich the customer experience of services over the nbn access network and make our systems and processes more agile by synthesising massive data sets. Once the investigation and implementation of the Tech Lab research is complete we could, for example, easily identify trends that occur in a failed activation in order to pre-empt problems before arriving at a house.”

Be the first to comment

What do you think?

This site uses Akismet to reduce spam. Learn how your comment data is processed.