Safer roads, less CO2: How Downer won the 2023 Practice Prize for analytics
An innovative software tool to cut planning time and carbon emissions during road maintenance has won this year's Practice Prize.
Using math to optimise road maintenance across Australia may not be the first thing that comes to mind at the mention of data analytics, but it's how a team from Downer Group won the $10,000 Practice Prize at the Melbourne Business Analytics Conference this month.
Dr David Ming (pictured, left) and Elton Shi (right), both alumni of Melbourne Business School's Master of Business Analytics program, created a decision support software tool to automate and standardise road maintenance schedules using mathematical optimisation.
The software was developed for the group's DM Roads brand, which performs road maintenance works across Australia and New Zealand.
"Our challenge is really to find ways to be productive and keep roads safe," says David, a Data and Analytics Manager for Transport and Infrastructure with Downer.
"We noticed that the business does that task in a very manual intensive and domain knowledge-intense way, and we saw an opportunity to modernise it and leverage the benefits of business analytics."
The 'travelling salesman' problem
Road maintenance comprises two main activities, which are inspecting road networks and fixing defects. To do it successfully, three key things must be decided: what jobs should be done, who should do them and what sequence they should be done in – a variant of the "travelling salesman" problem in computer science.
"The actual task of driving around and fixing roads can be quite time consuming," David says.
"And if you don't get it right, you end up not being so productive. There's a lot of complications if you think about how many things could go wrong on a road – barriers or potholes, litter and all that stuff."
A trained human scheduler takes two to three hours to manually set up a reasonable route, according to Elton. But thanks to the tool they developed, that time is cut down to 20 minutes – a sixfold reduction in planning time.
Although many off-the-shelf vehicle routing tools are available to tackle the problem, David and Elton say they can be costly, inflexible, include unnecessary features, or difficult to adapt for roadworks scheduling.
"We have empowered our planning leads and our supervisors to spend time on more impactful work rather than spending hours every single day creating this plan," says Elton, a Strategic Improvements Analyst with Downer who also holds a degree in Mathematics and Statistics from the University of Melbourne.
"It's a daily task that we've automated into a 20-minute tool that they can use right in the background – go get a coffee, come back and the job is much easier."
The productivity growth is passed on to road users in the form of safer roads, the pair say. After the tool was implemented, preliminary analysis showed a 25 percent increase in jobs completed, a 15 percent higher crew utility and 50 percent reduction in critical jobs.
As an added benefit, optimising the road maintenance schedule also led to a reduction in carbon emissions.
"We're quite a heavy transportation-based company," says Elton.
"We do a lot of driving with a lot of trucks and a lot of fuel. So, one major outcome is that we now do it more efficiently, which means much less CO2 emissions."
A new industry standard
Established in 2022, the Centre for Business Analytics Practice Prize recognises the best applications of advanced analytics that have resulted in significant and measurable organisational impact.
The prize also serves as a platform to showcase effective solutions, methodologies or initiatives that can potentially have broader applications.
In 2022, the inaugural Practice Prize was awarded to Suncorp (pictured) for its use of geospatial data to inform the way property insurance risk is assessed and priced.
This year, the Practice Prize judging panel included senior executives and prominent academics from the United States, United Kingdom and Australia.
"(Downer's) work not only showcases the power of analytics in solving complex operational problems but also sets a new standard in this industry," said Professor Nicos Savva, Chair, Management Science and Operations Faculty at London Business School.
Cornell University Professor Huseyin Topaloglu said "the project demonstrates how data and algorithms can effectively come together to achieve high-quality and fast decisions". Melbourne Business School Professor and Deputy Dean, Academic, Tava Olsen described it as a "very impressive use of optimisation combined with heuristics to make the work implementable".
Other judges included Natalie Fields, Chief Digital and Data Officer at Bupa, George Saoud, Chief Executive of Emerging Business at Coles and Dr Jenny George (pictured, above), CEO of Converge International.
Two other finalists from L'Oréal and Taylor Fry were also praised by judges at the conference for their outstanding submissions.
From L’Oréal Australia and New Zealand, a team led by Louise Turner (pictured) developed a machine-learning model that allowed the business to more accurately forecast product demand for its direct-to-consumer online sales channel.
"Forecast accuracy is of enormous importance," said Louise during her presentation.
"If we don't correctly forecast the products we're going to sell, we could end up with 'out of stocks'; we can have the wrong staff in our warehouse; we could have wasted effort."
From Taylor Fry, a team led by Hugh Miller (pictured) and Laura Dixie worked with the New South Wales Department of Communities and Justice to comprehensively understand homelessness in Australia with the help of analytics.
"It was really about understanding the pathways you can take around homelessness”, said Hugh.
"To do this, we assembled what we think is probably the best-ever linked homelessness data set. It involved about 200,000 people in New South Wales who had presented as homeless at one point in a six-year period."
'All companies will be data companies'
With the theme 'Leading the Way: Navigating Data and Digital Transformation in the Age of AI and Automation', the conference was attended by more than 600 data practitioners, business executives and academics.
"It's a great group of people within the community from very diverse backgrounds," said Dr Amina Crooks (pictured, above), Director, Customer Strategy and Design at Deloitte, and a panellist in the Generative AI session.
"I always find it really interesting to see the academics, the industry and also the vendors and the consultants all come together in one space."
For David Baker (pictured, above), Account Chief Technology Officer and Technology Strategist at Microsoft, the conference showed "just how much the analytics trade or craft has advanced over the years and how truly embedded it is into people's businesses".
Keynote speaker Rodrigo Pizarro (pictured), CEO of L’Oréal Australia and New Zealand, said being at the conference was important to him because data analytics is "completely changing the way we operate".
"In the future, winners and losers are going to be defined in the way they use both data analytics and generative AI to a level they've not seen before. So, I think you want to make sure we are on the winning side by using it first."
Elisa Koch (pictured), Head of Data and Analytics at the AFL, was one of almost 30 expert speakers at the conference, giving a presentation on how to leverage the power of data in sports.
"The broader business needs to know that they can trust the data and analytics team to have a good gauge on how the business is performing," she said.
"At the end of the day, especially if you work in a consumer facing industry, data can tell you stories about your customers."
Dr Stephen Brobst (pictured), the Chief Technology Officer of California-based cloud analytics firm Teradata, said the most interesting part of the conference for him was being able to meet people from academia, government and industry.
"The highlight for me was theory meets practice and the intense conversations around making reality from those things."
"In Silicon Valley, we have this phrase that in the 21st century, all companies will be data companies or will be extinct. If you're going to be a survivor... everything needs to be much more data-driven."
To see the full list of speakers from this year's conference, visit the Melbourne Business Analytics Conference page.
To stay up to date with analytics information and research at Melbourne Business School, visit the Centre for Business Analytics page.