You are here: Home / Analytics / Using Household Analytics for Cross Sell in Insurance
Using Household Analytics for Cross Sell in Insurance

Using Household Analytics for Cross Sell in Insurance

In one of our previous posts we had elaborated on what household analysis is, and how insurers, and to a larger extent – other enterprises, can make use of it. Household analytics helps insurance carriers understand the portfolio dynamics at a household level, instead of just at the individual level.

This approach has multiple benefits:

  1. Most importantly, household analytics helps an insurer understand their customers better
  2. Considering a household helps to understand the sentiment at a larger level, and address discontent or dissonance as soon as it may arise. This helps in retention.
  3. Cross positioning products or upgrades that relevant to the customer based on their household portfolio and current life stage is more effective than throwing the entire catalog at all customers and hoping something sticks.
  4. Risk Assessment of a household can help the underwriting team approve rates for new purchases
  5. Improvements in contactability

Household Analytics for Cross Sell

Cross sell is the process of selling a different product or a service to an existing customer. Selling insurance is one of the toughest jobs out there. And that can largely be attributed to every sales man trying to sell the same thing to the customer, without considering what the customer may actually need.

 

Let’s say, Mrs. Jones has home owner’s policy from Rocketz Insurance. She has been a loyal customer for the past 10 years and is very happy with Rocketz product as per her Net Promoter Score feedback. Mrs. Jones’ car is also insured by Rocketz. Their daughter– Anna, has an automobile for which the motor car insurance is also underwritten by Rocketz insurance. As far as Rocketz insurance is concerned, all three are unconnected individual customers.  Let us look at how Rocketz views these customers:

 

Mamma Jones

 

Daddy Jones

 

Anna Jones

 

As individual customers, not much can be predicted except a possible renewal for each customer. The business teams will cross position products based on what they feel could be relevant to each customer. This would lead to wasted efforts on part of the field sales agents, customer service representatives, marketing teams, operations teams etc…

Now let’s assume that Rocketz Insurance uses a household analytics approach. It identifies customers with ID numbers “7143”, “91445” and “103435” as belonging to one household. This is what the Jones household looks like to Rocketz Insurance now:

 

Jones household

 

When Rocketz Insurance considers the entire Jones household together, the high premium paid by the family together clearly indicates that this is a high value household. This is an important cluster for Rocketz. Household analytics would help identify the following:

  • It is likely that Mrs. Jones is the point of influence in this household. Since she is the oldest customer in the household, it is likely that she has influenced Mr. Jones and Anna to go in for Rocketz Insurance products
  • Between the three, they have Home Insurance and Auto Insurance. None of them seem to have a Health Insurance plan. Since Rocketz also has a health insurance product, it may be a relevant cross sell proposition.
  • Jones has not listed a contact number. But since she resides at the same address as the other two, it may be possible to reach to her through her family, to communicate important policy related information.

 

These are just some of the insights that can be gleaned, when the entire Jones household is considered as a single unit. There could be many other useful insights that can be generated based on the available customer data.

 

Householding analytics enables more powerful and relevant conversations between insurers and consumers.

To know more about how householding analytics can power cross sell for your business, please write to us at marketing@aureusanalytics.com

YOU MAY ALSO LIKE

About Nilesh Karnik

Nilesh is the Chief Data Scientist at Aureus. In this role, he is responsible for development of algorithms and mathematical models that help large organizations with advanced analytics solutions. His PhD dissertation made a substantial contribution to the theory of Type-2 Fuzzy Logic Systems and his work is still widely referenced.

Leave a Reply

Your email address will not be published. Required fields are marked *

*

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>


Scroll To Top