All Posts

3 Emerging Trends in Insurance, Social Media and Predictive Models

The use of social media is growing at a steady rate, and with that, the adoption of predictive analytics is on the rise as well.

Both internal and external data are used with predictive models, including an increasing amount of data gathered from social media. While insurers are sitting on mountains of unstructured, internal data that is valuable, there is a far more significant amount of social media that is generated daily.


  • About 3.03 billion people are on social media around the globe (BrizFeel, 2018)
  • 8% of US businesses with more than 100 employees use Twitter for marketing purposes (Statusbrew, 2018)
  • 48% of customers started searching for the product they bought on mobile first. (Google, 2018)

Some insurers are gathering social media data to “listen” to their customers, agents, and partners. Using this data allows them to better understand and predict the behavior of their customers.

The Injured Worker Water Skiing

One of the most common examples is the use of social media to identify fraudulent claims. We have all heard the stories of the SIU department crawling the web after an employee, allegedly injured on the job and has filed a worker’s comp claim, only to find a picture or video of the person water skiing.

While this is undoubtedly an excellent solution for the insurers’ SIU department to identify fraudulent claims, there are so many other ways in which social media can assist insurance companies.

Proactive vs. Reactive

The common theme across these emerging trends for using social media is to enhance the customer experience proactively by understanding the customer's likes, preferences, and sentiment at any given point in time.

For example, if a policyholder has posted on social media that he recently lost his job, this may not be the best time to attempt an upsell opportunity with him. It may be a better time for the insurer to review their payment history and determine if there are any payment offers that may help the policyholder out proactively.

Another example would be when an insurer is considering contacting their policyholders with cross-sell or upsell opportunities. Social media may provide more information than is available internally. Facebook or Twitter may show that he and his spouse are expecting a baby, which would be an opportune time to upsell life insurance.

Trend #1 - Premium Pricing

According to an article published in Forbes “Life Insurers Can Use Social Media Posts to Determine Premiums, As Long As They Don’t Discriminate,” the State of New York has allowed life insurers to use data from their customer’s social media posts as part of their premium calculations. As you can imagine, there has been some push back from individuals claiming this is an invasion of privacy.

From the insurer’s perspective, if an individual applies for a life insurance policy claiming they are a non-smoker, and publicly available social proof exists that shows the applicant smoking on several occasions, is that any different than our injured worker water skiing?

In this case, the insurer may decide to deny coverage. In other cases, the insurer may choose to charge a higher premium since the applicant is a higher risk.

This type of information collected from social media is valuable since it is current and straight from the source.

Trend #2 - Product Development

Monitoring social media can provide useful insights into customer perceptions and behaviors. By monitoring social media, insurers can better understand what their customer’s perceptions are of their customer services and products. This insight can be used to modify or develop new marketing messages around services and products.

Social media data can also help insurers identify how they can improve existing products as well as develop new products based on a specific customer demographic or geography. For example, an auto insurer could identify a trend where a substantial number of their customers are purchasing a new sports car that is a hot item in the market. This could be a great opportunity to proactively reach out to their customer base to cross-sell a new or existing product targeted for sports cars that are driven less than 5,000 miles per year.

In Florida, a sports car is typically driven 12 months out of the year. In New England, most people take their sports cars off the road for six months starting in October. By segmenting these policyholders by geography, the same product could be marketed slightly different depending on if the policyholder is in Florida or New England.

Trend #3 - Improving Customer Experience

Did you know that according to Lyfe Marketing, in 2018, “59% of Americans believe that customer service through social media has made it easier to get their questions answered and issues resolved?”

Insurers can collect and utilize both the questions and answers the customer presents via social media. Using this data in predictive models can help insurers see trends and better anticipate what issues customers are experiencing and proactively take steps to minimize or eliminate them.

The benefit of using social media in this way is that it helps the insurer understand how the customer is feeling without explicitly asking them in the form of a survey or customer feedback request.


The usage of social media is growing in the insurance industry. There’s a wealth of information available out there; it just needs to be collected and processed. This trend will continue to grow as companies realize the possibilities for its use.

The customer data collected from social media is implicit feedback. The customer is telling you how he or she is feeling without being directly asked. Sentiment analytics makes it possible to take all this implicit data and put it to use to understand your customer and provide a better experience.

Interested in learning more about customer analytics and how you can improve your  customer's experience? Click on the link below to get more information.

More Information

Anurag Shah
Anurag Shah
Anurag Shah is CEO and co-founder of Aureus Analytics. He was the founding member and CEO for EdVenture prior to joining the leadership team at Omnitech, where he served as the COO and Head of Global Operations.

Related Posts

Data-Driven Insurance: The New Normal in the Post-Pandemic World

This is the age of data. This pandemic has forced us to find new ways to get our work done without putting ourselves in danger. Consumer buying behaviours have changed in order to adjust to this new normal in the post-pandemic world.  Before we talk about the changes in the business to navigate in the next two years, we should have a glimpse of the insurance business: What, How, and Why of the insurance business.

Understanding Agency Sentiment

In our previous blog article, “Using AI for Increasing Agent Productivity,” we discussed how many insurance companies can only analyze agent productivity based on the premiums written and the loss ratio of their network of independent agencies. In part 2 of our series of articles on “The Top 3 Emerging Trends for Agent/Advisor Analytics Using AI”,  we will focus on the benefits of understanding agency sentiment for insurance companies that utilize a network of independent agencies.

Using AI for Increasing Agent Productivity

Currently, many insurance carriers can only analyze agent productivity based on the premiums written and the loss ratio of their network of independent agencies. Looking only at past results doesn’t necessarily provide an accurate view of how an insurance carrier can increase agent productivity going forward. By using AI for increasing agency productivity, insurers can now predict the best course of action as opposed to waiting to review past results.