Today, many insurers are using advanced analytical techniques such as generalized linear modeling for rate-making and product pricing, and a recent survey by Towers Watson showed that 70 percent of U.S. insurers are using predictive modeling for Personal Auto insurance.

However, actuaries often rely on subsets of historical data to run pricing models since it is too time-consuming to prepare large sets and run the models.

But sampling has its limitations. If you are pricing claims with one-million records versus 10,000, you will be much less likely to encounter outliers that throw the models off.

By using HPA, insurers can now get more precise analysis from all their data. They can also incorporate external data (such as Google maps, GPS, credit scoring, social media, etc.) to supplement the results.

Take the example of segmentation and pricing. Insurers currently use a handful of variables to support those two processes. Because it operates much faster, HPA helps insurers increase the number of variables used in “what-if” analysis to find the ones with the biggest impact on profitability.

Here are three more areas where HPA can improve insurer profitability:

• Telematics: According to a study by ABI Research, the number of telematics users will increase from fewer than two million in 2010 to nearly 90 million by 2017, inundating insurers with data from these in-car recorders. Many insurers already are struggling to analyze existing telematics data.
  As it increases, HPA is the only option to analyze billions of data records in a fraction of the time required by traditional computing environments. With that ability, insurers can better understand how to use telematics to create innovative rate plans and learn more about how driving habits influence claims. 
• Customer Intelligence: As customer interactions in insurance move from in-person to digital channels, insurers must react faster and better predict future behavior.
  Insurers can also improve customer experiences and make relevant, real-time offers with higher acceptance probabilities. Faster analytics delivers predictive-modeling results more quickly and identifies the best future actions to take while considering both financial and organizational constraints.
• Catastrophe Modeling: Insurance companies are well-equipped to manage the potential losses associated with claims from individual fires and automobile accidents because of a wealth of data. Actuaries can determine future losses with a high degree of confidence.

However, since catastrophic events are relatively infrequent and historical data is limited, it's virtually impossible to reliably estimate potential future catastrophe losses using standard actuarial techniques.

With HPA, actuaries can take all the data points available from previous events and begin to create more robust models. In particular, modelers can incorporate information available after an event from weather and geological services that denote storm paths, wind speeds and Richter-scale readings and then overlay it onto data for the properties they insure in other parts of the country that might experience similar catastrophes. This can give actuaries a better idea of how to price and who to cover.

WHAT VALUE ANALYTICS?

When I talk with insurers about HPA, I often run across executives who understand they have access to all this data but ask, “So what? How does running analytics faster affect the bottom line?” HPA not only provides enhanced analytical-model performance by eliminating sampling, but it also gives you back something precious: time.

Hours spent prepping and loading data decline to minutes; weeks to days. One of my clients talks about how it takes six days to analyze one day's worth of data. What would happen if you could do it in six minutes?