An Intelligence Led Approach to Decision Management in Tax Administration
What is intelligence led? You need to start by thinking about your objectives, but you don’t always have to get top down. there is a little of iteration between top-down and bottom-up.
The Inland Tax Revenue administration aimed to achieve straight through processing, including risk management, with a 360-degree view of customers with real-time data.
In order to do that, it was critical to collect as much data as possible. The platform they put in place allows for the collection, analysis and
- data layer
- integration layer – analytical store
- decision layer – inefrence engine
- services layer – business intelligence
- intelligence team
They started with GST (Goods and Services Tax) because of its large volume of daily transactions. It was a big issue for the business. New Zealand is great lab for technology because big is not huge. Usually they process 4,000 GST refunds for small and medium businesses and another 4,000 for larger companies. They used to review all the refunds but manual process was becoming too much to handle. One important detail is that management was fully supporting the initiative.
They applied the CRISP methodology. Core principles:
- Continuous Improvement
The pilot group was composed of 3 wise men, who make the final decision, and 6 champions. Wise men started capturing the first rules. The champions then developed on the initial work.
The knowledge was captured in declarative form. The expert-based risk assessment model took 4 months. It was captured in rules, including rationale and clarifications.
The pilot was a success. 95% of GST refunds were automatically released. They reduced by more than 2 days the GST processing time. Customers got GST refunds faster, over the nightly processing and release of funds.
They reduced the costs for Inland Revenue and for customers.
The feedback after running the pilot for 3 years. The system is now vital. They do not want to go back to the way they used to do it.
One fraud case they investigated and found within a month. The scam had been going for months before. By printing the whole network, they could visualize the relationships and solve the case. Check the picture in the slides!
After the first results, they started receiving tons of requests to add to the scope. Victims of their own success! They do have to make sure that they control the expansion of the system, and stay focused. The team has grown a bit to 15 people, but it is stable now.
Learn more about Decision Management and Sparkling Logic’s SMARTS™ Data-Powered Decision Manager