Skip to main content

Forecasting NBN Broadband Service Demand

Free course


Start anytime




2 hrs

Meet the Expert

Associate Professor Yang Wang

Associate Professor Yang Wang
Associate Director Research, The Data Science Institute

Yang is an Associate Professor at the UTS Data Science Institute. He received his PhD degree in computer science from the National University of Singapore in 2004. Before Joining UTS in 2019, Yang was with Data61 (formerly NICTA), the Institute for Infocomm Research, Rensselaer Polytechnic Institute and Nanyang Technological University.

Yang’s research interests include machine learning and information fusion techniques and their applications to asset management, intelligent infrastructure, cognitive and emotive computing and computer vision. He has over 100 conference and journal publications and has received more than 10 research awards, including the Eureka Prize, iAwards and AWA Water Awards.

More Less

This course explores a collaborative project with the NBN Company on broadband service demand forecasting, to help plan the region-wide, technical workforce needed to connect end customers.

About this course

This is a free, self-paced online course. 

This free course presents the effective rollout of the National Broadband Network (NBN) Australia-wide and the joint project between the NBN Co., CSIRO Data61 and the Data Science Institute at UTS to develop a machine learning model to forecast broadband service demand. Through a case study format, participants will face a real-world problem and are presented with the solution as a learning tool in exploring data analytics.            

Course structure

This course reviews the difference in accuracy between the heuristic and the new machine-learning model, which achieved a 30% improvement in accuracy and greatly reduced the workload of analysts.

We explore data analytics through the case study of the NBN rollout and its perceived success; the project achieved a 96% on-time connection rate, attracting 2.3 million new customers. The team used both clustering techniques and data mining algorithms to identify cohorts of unsatisfactory customers and areas.

Previously, NBN relied on a heuristic method to guide the resource allocation to new regions, based on its past roll-out records. However, increasing customer expectations and the accelerating roll-out speed has led NBN to develop more accurate, data-driven strategies to manage the roll-out process.

This free course uses a real-world problem to illustrate to participants the impact of effective solutions. In this course, the NBN roll-out and the impact the successful use of the new machine-learning model has on collecting and analysing data is showcased, with respect to informing evidence-based decision making.

The question is then put to participants: What lessons can they bring into their own workplaces to mirror this behaviour?

Learning outcomes

This course will provide an opportunity for participants to engage with the following learning outcomes:

  • The ability to describe how data analytics can be used for workforce planning
  • The ability to describe how data analytics can be used to understand customer needs and improve customer satisfaction
  • The ability to explain the impact of a centralised approach to data collection and analytics.

Who is this course for?

This free course is suitable for anyone who is interested in data analytics and machine learning, explored through a real-life application of the NBN company.

We use cookies

We use cookies to help personalise content, tailor and measure ads, plus provide a safer experience. By navigating the site, you agree to the use of cookies to collect information. Read our Cookie Policy to learn more.

Acknowledgement of Country

UTS acknowledges the Gadigal people of the Eora Nation, the Boorooberongal people of the Dharug Nation, the Bidiagal people and the Gamaygal people, upon whose ancestral lands our university stands. We would also like to pay respect to the Elders both past and present, acknowledging them as the traditional custodians of knowledge for these lands.