The Office of State Revenue (OSR) of Queensland Treasury in Australia has started using SAP predictive analytics from SAP Leonardo to predict potential tax defaulters before they default.
Speaking at SAP’s annual user conference, Sapphire Now 2018, Simon McKee, the Deputy Commissioner of the Queensland Treasury’s OSR, said that a cultural change at OSR took place prior to its digital shift.
The OSR, a business unit within the Queensland Treasury, started using SAP ERP in 2005. It added a tax revenue management system in 2009, subsequently moving to SAP’s HANA relational database management system in 2015.
“The new technology wasn’t going to stick without a plan for digital – and cultural – transformation. In 2017, I initiated a transformation programme. We invested heavily in culture change to get our people ready for the digital change. We invested heavily in leadership.”
One of the OSR’s early goals was to deter employee fears that this ‘transformation’ was a headcount reduction effort, McKee explained. “We communicated that this is not about job replacement – far from it. It was about job enrichment.”
As McKee pointed out, the OSR had to adapt to a world and ecosystem that is changing. “The expectations from our clients is that they are direct with us 24/7, on the device of their choice.”
The Queensland government backed the effort, McKee highlighted. “Our government is being very supportive of this, because they want Queenslanders to be able to get on to do their business, to grow the economy. The whole purpose is to make it easier for our clients.”
The digital transformation effort began with “design thinking and disruptive training” workshops, with eight week sprints for each revenue team, or line. One of the lessons learnt, as McKee soon found out, was not to refer to taxpayers as customers.
“They don’t see themselves as customers. They say, ‘We are tax payers; we have to interact with you, but we don’t necessarily want to. What we want is a really good experience. We want to get in and out quickly.’”
Providing better customer experience could not come at the expense of compromising the customers’ data. “The commissions’ number one priority is around protecting people’s [data].”
The OSR has now run thirty-six digital initiatives out of an SAP-managed private cloud in Queensland (the HANA Enterprise Cloud, or HEC). The range of projects include a virtual assistant and an SAP contact centre solution.
McKee is excited about the OSR’s Machine Learning (ML) projects, as it is the first government agency in Australia to deploy them. The first one is a land tax debt project going live in July 2018. The core goal of land tax debt predictions is to anticipate when somebody might become a debtor before it happens.
In 2017, McKee’s team ran a proof-of-concept with an SAP team from Palo Alto. In eight weeks, they crunched 187 million records from 97,000 tax payers. Three internal sources of data were used. Despite what McKee described as “limited data – not necessarily clean data,” the machine made predictions with 71% accuracy. McKee believes with more data – and cleaner data – the OSR will be able to get that number much closer to 100%.
“As we add more data, we expect it’s got to be greater than 71%. Also, one of the projects we’ve done since then is cleaning our data. We’ve de-duplicated it and cleaned it.”
Partnership with SAP
SAP’s people worked with OSR subject-matter experts to understand the job to be done. “Then they went away and developed the solution, brought it back and said, ‘Is this what you wanted?’ We said, ‘Yeah, but a bit of adjustment here and there.’ They went away again, came back, and it’s been an easy process,” McKee recounts. To build the tool, SAP used the HANA predictive analytics library (PAL) and a customer retention application.
There are two main groups of non-tax-payers, McKee reveals. One group has no intention of paying for whatever reason. Predictive can help with that group by sending out pro-active notifications, or strongly-worded letters to repeat offenders, hopefully to get better results. Another group wants to pay, but is unable to for various reasons. There is plenty of predictive work with this group, including reaching out to them for better payment terms. The ability to segment into these two groups forms the basis of future campaigns, targeted to each.
McKee stresses that the OSR will be transparent throughout this process, and that the process will not be fully automated. “They will be dealing with a human, but the machine will generate automatic messages. It can monitor to see whether their activity has started up again and it might go, ‘Hi, are you able to pay this now? If not, here’s a payment arrangement.'”