Are you:
- Having trouble in identifying customers who you could confidently say would buy a product from you?
- Not sure whether your product pricing is competitive enough?
- Finding it difficult to predict an accurate claim rate?
As an insurer, if you are thinking on the above lines, then read on, we have a solution for you!
In a survey on “the usage of predictive modelling and analytics in insurance industry” conducted by ÏSO and Earnix, 81 % of the insurance professionals said they use Analytics in Pricing while 52% use in Underwriting- two of the core actuarial domains.(September 2013)
Enter, the Iron Man of Analytics, a character we spoke about in an earlier blog “How to become the Iron Man of Analytics“. Armed with repulsor weaponry, rotary cannons, shoulder-mounted gun turrets, a personal force field as well as an automated combat AI, he will come to your rescue in times of need. Let’s just call him Iron Man for ease of use. Now, how you let Iron Man use data to reveal hidden truths about your business is what ANALYTICS is all about!
An insurance company is not satisfied by its existing customer database and is constantly finding new avenues to gather more information to augment customer data. The insurer is in need of deeper customer insights for which he seeks Iron Man’s help. He leverages gigabytes of DATA from profile, social media and geospatial information (like Google maps). In order to obtain and manage this vast pool of DATA, Iron Man suggests an in-house database and high-performance analytics to provide faster processing on vast volumes of real time DATA.
P R I C I N G
Today, Iron Man has integrated the cost estimates with knowledge of customer behaviour. He performed scenario testing of possible rate changes and analysed its effect on KPI’s. Iron Man did price optimization to systematically integrate cost and demand that recommended an optimal set of prices which met the insurer’s business objectives for profitable growth.
U N D E R W R I T I N G

Recently, CEO of a global insurer sought Iron Man’s help to gauge and manage risk in the homeowner’s insurance market. This market is plagued with low investment returns and weather related losses.
While the CEO, until now was trying to contain these losses by geographically diversifying risk exposures, he was sceptical if current risk management practices were effective enough in accurate risk assessment. His underwriters were facing challenges in assessing the risk profile of properties pertaining to insurance premium and renewal charges. With Iron Man’s advice, the CEO was able to obtain a better alignment between risk quality and pricing. Iron Man aided the underwriters with models that enabled accurate predictions about future events.
C L A I M S
Incoming claims are categorized in to different levels of priority based on urgency and legitimacy. Insurers are today relying heavily on unstructured data to categorise incoming claims into different levels of priority based on their urgency and legitimacy. Since up to three-quarters of this data are unstructured (i.e., email, social media, medical records or police reports), Iron Man implemented algorithms, systems and processes for mining insights from unstructured data. This greatly improved the practice of claims triaging.
Iron Man also used a combination of business rules, predictive modeling, anomaly detection and social network analysis for minimizing opportunistic and organized claims frauds. Further, he also adopted modern data mining techniques to carry out claims pay-outs and loss-adjustment expenses which accounted for as much as 70 percent of an insurer’s written premium.
Iron Man also used a combination of business rules, predictive modeling, anomaly detection and social network analysis for minimizing opportunistic and organized claims frauds. Further, he also adopted modern data mining techniques to carry out claims pay-outs and loss-adjustment expenses which accounted for as much as 70 percent of an insurer’s written premium.
M A R K E T I N G
The marketing head of a leading insurer approached Iron Man to provide a sound strategy for maximizing return on his investments. He helped the marketing head do “Intelligent marketing” and greatly reduced customer acquisition cost. He resorted to “science driven marketing” approach by using predictive models to:
- Efficiently allocate resources for marketing campaigns
- Acquire superior leads
- Prioritize leads
- Prevent policy cancellation
- Identify customer segment likely to buy high premium products
Iron Man also penned few of his strategies below:
1. One could supplement lead prioritization models with response models to score the present list of prospects on the basis of who’s most likely to respond in near future by:
- learning from the experience gained during prior campaigns
- observing which customer did or did not respond to solicitations in the past
2. The diagram above illustrates the implementation technique of such models for the entire product portfolio by only bearing the cost of contact – be it via direct or tele-marketing on those more likely to respond. The campaigns get more “bang for their buck”, a higher response rate and ultimately a desired higher ROI!
Iron Man enabled the Insurer:
- Identify superior customers by
- Reducing cost of lead acquisition by 20%
- Yield an increase of 30% in customer conversion and 25% in average premium per customer
- Increase profits by 15% through price optimization
- Predict an accurate claim rate of 4%
Similar Problems? Contact the Iron Man! 🙂
This blog is written by Trina Maitra, Analytics Consultant at BRIDGEi2i
About BRIDGEi2i: BRIDGEi2i provides Business Analytics Solutions to enterprises globally, enabling them to achieve accelerated business impact harnessing the power of data. Our analytics services and technology solutions enable business managers to consume more meaningful information from big data, generate actionable insights from complex business problems and make data driven decisions across pan-enterprise processes to create sustainable business impact. To know more visit www.bridgei2i.com
The views and opinions expressed in this article are those of the author and do not necessarily reflect the official position or viewpoint of BRIDGEi2i.