We're using a predictive modelling tool to better support our clients, faster
The predictive modelling tool is to help identify clients that need extra help and how we can help them with their recovery.
ACC is using a predictive modelling tool to better support people who are injured in New Zealand.
The analytical modelling tool uses the information provided on approximately 1.9 million claims received each year to assess:
- which clients are likely to need help and should be called proactively
- which type of case owner should assist the client
- how long we should expect a claim to be managed.
The prime benefit of using the tool is that we can engage with clients or their families very quickly, which is important in what can be an uncertain time following an accident. Before this, many clients had to call us when they needed help.
Since we implemented this tool, the average time taken to set up weekly compensation for clients has dropped from 11 days in June 2014 to 7 days in June 2017.
We've also seen an increase in customer satisfaction, going from 68% satisfied in June 2013 to a current result of 78%. Case owners are now able to make evidence-based decisions – something we think is important.
The tool is not a key performance indicator for staff. Case owners do not have individual duration targets but work towards local and regional-level targets in order to optimise outcomes for clients.
Our injury claim forms privacy notice outlines our role and responsibility in collecting data and personal information. Individual clients are not able to be identified in the tool.
The data collected is for claims lodged after April 2009 and is verified via statistical tests. Factors used in the model include:
- diagnosis
- age
- lodgement delay
- work type (if relevant)
- questions about whether treatment was sought at a DHB
- a client's injury history (eg whether they’ve had multiple injuries on the same body site)
- initial incapacity outlined on the claim form.
The model was last reviewed externally in 2014, updated in 2016 and 2017, and was built from 364,000 claims that were lodged between April 2007 and May 2013.
This is work done solely for ACC. Other agencies don't have access to the data. The modelling allows us to proactively contact clients earlier than we would otherwise have been able to and reduce the time taken to make weekly compensation payments.
