Sponsored by: ?

This article was paid for by a contributing third party.

Advertising feature: Optimising claims indemnity spend for insurers


Digitisation has become essential for insurers looking to unlock value and deliver excellent customer experience. According to EXL's UK and Europe team, Mohit Manchanda, head of insurance, Rohan Regis, vice-president insurance and Swarnava Ghosh, senior engagement manager - insurance analytics, this is especially true for companies looking to optimise claims indemnity. By identifying opportunities for transformation within the claims function, insurers can reduce costs and enhance efficiency.

Declines in profitability due to rising claim costs are putting pressure on insurers. In 2018 alone, UK insurers paid out a total benefit of around $277bn in indemnity spend, 8.6% higher than their cumulative indemnity spend in 2017. However, insurers have been unable to raise premiums in response due to the price competition in the market. Insurers must instead look for new opportunities to reduce indemnity spend such as fraud cases, leakage across the journeys, supplier costs and recovery performance. 

Traditionally, claims processing involves a large amount of manual effort, complex workflows, and insufficient and disorganised data. The key for profitability for insurers is unlocking the value of the huge amounts of unstructured data flowing through the claims function. By carefully evaluating internal processes, in-house and third-party data sources, and transforming raw data into meaningful information, insurers can generate actionable business insights that enhance both claims efficiency and effectiveness.

Reducing indemnity spend for claims organisations

This approach to claims transformation approach is divided into four key strategic pillars focusing on data, processes, people, and technology. 

Sourcing the right data

Claims organisations must evaluate the accuracy, sufficiency, and availability of their data. By sharing the right datasets across functions, ensuring data definitions are consistent, and addressing any relevant privacy concerns, meaningful insights can be generated from this data.

Insurers possess significant amounts of internal data including customer information, quote and pricing information, policy details, claim details, and historical fraud cases. This can be used for making better, faster decisions, as well as enhancing the claims workflow. 

All internal data sources can be broadly classified into two categories. Structured data consists of well-defined data elements in specific, easy-to-use formats, such as Excel tables, tabular formats, and relational databases. Unstructured data is an aggregation of various data elements in non-structured formats, such as PDFs, conversation recordings, or emails. These datasets need intelligent programs such as natural language processing (NLP) or optical character recognition (OCR) to convert them into usable formats. 

External data that is not generated internally can be sourced and linked to the claims dataset, enriching the available information and increasing decision accuracy. 

External data can be classified into two categories. Open source data includes information available in the public domain such as demographics, weather information, and other sources. Third-party proprietary data sources offer specific data for sale in areas including risk profiling, insurance industry data, and fraud.

Applying the right process 

Traditional claim processes have largely relied on claim handler expertise, making limited use of data and analytics. With the increasing availability of better data, machine learning, and artificial intelligence, more insurers are augmenting handler judgements with predictive analytic insights. Three types of models can help claim handlers take better decisions.

•    Estimation models are used to estimate variables including repair costs, medical costs, legal costs, and other areas. Insurers can use these estimates to better track performance and better direct their efforts. 
•    Classification models provide binary or multi-class decision flags to group similar claims together. Insurers can then devise specific strategies for these specific groups of claims. 
•    Propensity models are used to predict the probability of an event occurring. These models typically output a probability percentage that can be used for preparing to take the appropriate action for likely future events.

Apart from these three type of models, certain process changes within recoveries could also improve performance and cycle times. An optimised chase strategy can be achieved through bilateral agreements with third-party insurers.

Additionally, improvements can be made to fraud identification processes. By applying analytics, insurers can improve fraud capture by identifying subtle or non-intuitive patterns, increase precision and coverage, and optimise referral rates.

Engaging the right people

Achieving lower claims indemnity through data requires resources with the right skillsets and training. This takes hiring people including data engineers, modelers, and similar talent. Professional growth for existing employees through upskilling and cross training in analytics can also go a long way in benefiting both the employee and employer. Aside from recruiting and training analytics talent, retaining the right people is also key for consistently better delivery. 

Deploying the right technology

Using the right technology enables the claims process to operate at maximum potential and generate valuable data.

Analytical tools can improve areas including data management, model development, business intelligence, reporting, and visualisation. 

Claim-specific tools can bring built-in advanced analytical models trained on proprietary third-party data, but will often lack insurer-specific information. 

Internet of Things devices for loss prevention and claim avoidance can positively impact claims frequency and severity using real-time monitoring. This includes smart devices such as water damage sensors, home exterior sensors, and connected cars. 

Implementing a project prioritisation framework 

When transforming claims processes, insurers should utilise a project prioritisation framework that accounts for competing factors. This would measure an initiative’s effectiveness across several areas. 

A detailed analysis on the potential return on investment and benefit value should be performed for each project. Model and analysis simplicity must be considered for every potential modeling technique or analysis. The ease of implementation can be gauged based on the complexity, data asset requirement, and other factors. 

Other factors to take into account include any lag period for achieving benefits based on the amount of time an intervention will require to produce the desired result. The scalability of an intervention should be examined, with special consideration paid to achieving long-term goals while accounting for short-term objectives. Synergy with ongoing initiatives must be analyzed as well. 


Transforming the claims process requires factoring in various decision metrics, dependencies, and process flows. This helps ensure the transformation process doesn’t negatively affect the functioning of existing claims processes. With the right data and analytics strategy in place, insurers can achieve significant indemnity saving. 

This is a paid-for advertorial

  • LinkedIn  
  • Save this article
  • Print this page  

You need to sign in to use this feature. If you don’t have an Insurance Post account, please register for a trial.

Sign in
You are currently on corporate access.

To use this feature you will need an individual account. If you have one already please sign in.

Sign in.

Alternatively you can request an individual account here: