Month: February 2016

Data Analytics and Capital Management

coins-1015125_1920Solvency 2 came into effect on 1st January 2016.  This regulatory framework plays a very important role in how European insurance companies are managed, with risk management  at the core of Solvency 2, imposing capital requirements for the risks that affect insurers.  This article explains how insurance companies can use predictive analytics to improve risk management and reduce capital requirements under Solvency 2.

Data analytics for entity specific risk parameters

The calculation of capital requirements requires the use of risk parameters that calibrate the risk models.  Solvency 2 allows for a range of options such as a full internal model, a partial internal model or a Standard Formula initially calibrated by EIOPA but that accepts entity specific parameters known as USPs (Undertaking Specific Parameters)[1]

Companies using entity specific parameters, in full or partial internal models or by tailoring the Standard Formula with USPs, need to justify the use of these with their own data.  This is an area where predictive analytics can give a competitive advantage.  The more information you can extract from your data, the more appropriate your risk parameters will be.  Furthermore, a better understanding of risk could reduce its volatility, decreasing capital requirements, as deviations from expected values would be smaller or less probable[2].

For example, predictive modelling provides complementary reserving methods that may perform better than traditional actuarial techniques[3], helping to reduce Reserve risk.  Markus Gesmann, Manager of Analysis at Lloyds, highlights the advantages of a Bayesian approach to communicate uncertainty with credibility intervals[4].  Given the complexity of some solvency models, anything making the message easier to understand is a welcome addition.

The goal is not to replace traditional actuarial reserving practice but to consider additional methods that contribute with a different way to look at the risk.  Most winning solutions at the data analytics website Kaggle[5] are an ensemble of models.  Rarely a single method is good enough to cover all scenarios and a combination of models works better in the same way that a team usually performs better than an individual.  However, there must be a balance between accuracy and practicality.

Better understanding of risk may lead to lower capital requirements

In a more specific example, the Standard Formula’s calibration for Premium and Reserve risk in Medical Expenses assumes a standard deviation of 5% for Reserve Risk.  If predictive analytics helped reduce the standard deviation to 4%, the capital charge for Premium and Reserve Risk could decrease by 10%[6], as large deviations from the best estimate of technical provisions would be smaller and less probable.  The capital requirement reflects the severity of potential adverse developments in reserving. Thus the smaller the volatility, the smaller the capital requirement.

A similar change in the standard deviation for Premium risk could reduce the capital charge by 15% and the joint effect would be a 35% reduction in the capital requirement for Premium and Reserve risk.  EIOPA has rules defining what proportion of these savings insurers can acknowledge if using USPs[7].  Insurer’s relying on the Standard Formula may want to check the list of risks for which they can use USPs.

The list of Standard Formula parameters that can be replaced by USPs is short but represents the most significant risks for some businesses.  Entities using partial or full internal models may enjoy greater potential to leverage predictive analytics.  Risk Dynamics, recently acquired by McKinsey, already provides validation services to financial institutions whose risk models are based on predictive analytics[8].

Increasing an insurer’s capital efficiency is not usually in mind when discussing data analytics but it is a secondary benefit worth considering.

Predictive analytics can help insurers understand and manage their risks better, with a clear impact to their bottom line.  With some extra work, insurers can enjoy the benefits of lower risk uncertainty and increased capital efficiency.   This would enable the company to be more profitable, provide more affordable products and increase dividends to shareholders.


Image source: Pixabay

[1] See EIOPA’s advice on USPs, in page 18:

[2] An application in Long Term Care:

[3] Bayesian Analysis in Forecasting Insurance Loss Payments:

[4] See Markus’ blog, “mage’s blog”


[6] Different undertakings could see different results depending on their specific figures. This is just an illustration.




Using Data Analytics to Increase Cross-selling

calculator-385506_1280One of the many advantages of a composite insurer is the company-wide customer base that can be targeted with a range of product offerings.  A customer who purchased a life insurance policy may also be interested in motor or home insurance.

However, it is often difficult for insurance  companies to leverage the potential of cross-selling.  As of 2015, the insurance industry averages 2 products per customer.  Leading insurance companies are prioritising cross-selling, with Aviva announcing a target of 3 products per customer (Aviva currently averages 1.7 per customer).[1]

In comparison, some banks have reached excellent levels of cross-selling.  Wells Fargo is a good example of a company that is successfully capitalising on this opportunity.  In 2012 they averaged 5.9[2] products per customer in retail banking when, to put it in perspective, three years before, USAA was at the top of the cross-selling league with 3.9 products per customer[3].

Wells Fargo has accomplished this by changing the company culture[4] but this is a big task for anyone who wants to replicate that success.  In contrast, some banks have embraced data analytics as a faster, cost-effective means to achieve the same result.

Spanish banks BBVA and Bankinter are great examples of the value that analytics can add to an organisation.

Bankinter has embedded data analytics in their customer relationship management[5].  Revenue increased by more than 18% from 2001 to 2004 with 14% more customers, increasing profit per customer.  The number of products per customer reached 6.1 from a previous level of 5.5.  In addition, customers reported increased loyalty and satisfaction.

Similarly, analytics enabled BBVA to provide 4% more credit to small and medium business with no increase in default rates.  BBVA’s data analytics centre generates actionable insight that is useful not just to the bank but also to retailers.  By sharing this data with retailers, the bank is expecting to indirectly generate more business for the bank[6].

Anyone who has bought something at Amazon has seen data analytics for cross-selling in action and will be familiar with “customers who bought this item also bought…”  That is Amazon’s way to present you with products their data suggests you may also buy.  In fact, Amazon reported in 2006 that 35% of their sales were due to cross-selling.[7]

An insurance company can adopt customer analytics and have similar success by leveraging its customer base and finding opportunities for cross-selling.

Predictive modelling allows an insurer to identify customers likely to switch to a competitor or those at particular stages in their life cycle who are likely to purchase an additional product.  It can also identify the characteristics of those policyholders holding more of the company’s products and detect customers with whom you may form a long-term and profitable relationship.

The more products you sell to individuals, the more profitable those customers are and the more likely they are to remain your customers in the long term.  Data analytics is a cost-effective tool to help increase sales from your existing customer base in a competitive environment where winning market share is increasingly difficult or can only be achieved at the expense of profitability.

If you found this interesting, you may also want to check this presentation Predictive Analytics for Customer Targeting – A Banking Telemarketing Example


Image source: Pixabay

[1] See:

[2] See Forbes magazine:

[3] See American Banker:

[4] See Forbes magazine:



[7] See: