When will another flood hit Australia? Which properties will summer’s cyclones strike? How much damage will the next major bushfire cause? These are just some of the risk assessment questions insurance companies are asking of their data.
And while the questions themselves may seem straightforward, seeing into the future is a capability that’s harder to come by.
The typical industry approach of calculating risk by averaging annual losses across a whole postcode or suburb has significant shortcomings, as it fails to take into account an individual site’s unique attributes – such as its vegetation, topography, unique structures, and a plethora of other dynamics.
There’s a mass of data readily available that can influence a property’s risk exposure, including historical weather data and future forecasts, council development approvals, surveys, consultancy documents, national park maps and even social media feeds.
But much of the insurance industry is yet to discover how to effectively use this Big Data to reach the promised land of pinpoint risk assessment.
Location-based analytics, an advanced new approach to Big Data analytics, has emerged as the Holy Grail for insurers looking to gain an accurate location-specific understanding of risk exposure.
The approach, often referred to as ‘location intelligence’, unifies disparate sources of data into a single, all-encompassing view of an individual property’s risk profile – allowing insurers to see into the future with startling clarity.
For example, location-based analytics apps capture and assess real-time data feeds from public safety agencies and the Bureau of Meteorology to clearly reveal the projected impact of a storm, flood or bushfire – before a crisis fully unfolds.
This helps insurers accurately forecast portfolio exposure, issue warnings to affected policyholders, and pre-emptively begin the assessment process.
Beyond crisis situations, the predictive capability of location-based analytics also empowers insurers to identify high and low-risk customers to drive revenue growth.
The approach enables insurers to price policies more accurately – by taking into account the specific characteristics and history of a property and policyholder. Over time, low-risk customers will trend towards insurers taking advantage of location-based analytics, and price-sensitive high-risk customers will flow to those using the old methods.
Taking this one step further, the insights generated through location-based analytics can also be used to influence government policy and lobby stakeholders around mitigation strategies – such as instigation of levies – in high-risk areas.
The good news for those insurers who have yet to invest in advanced analytics, or have made substantial investments in other technologies, is there are no rules for adopting the capability. Location-based analytics can be implemented as either a standalone or complementary system.
An investigation of location-based analytics capabilities is sure to unfurrow your brow if you’re a data analyst frustrated by traditional postcode risk assessment. Similarly, if you’re tasked with business transformation then you’ll likely experience the same sense of relief, as the answers to the tough questions become more apparent.
And if you’re a CEO questioning the returns of your data analytics investment, your confidence will be restored – as revenues, costs and market share all fall in line with plan.
For more information on how advanced location-based analytics can work for your insurance portfolio, visit esriaustralia.com.au/insurance.