Case study

How Money and Pensions Service (MaPS) helps people improve their financial futures through a refreshed segmentation solution

Money and Pensions Service logo

Summary

The Money and Pensions Service (MaPS) is a statutory
body sponsored by the Department for Work and
Pensions dedicated to helping people – particularly
those most in need – make well-informed decisions
about their money and pensions and improve their
Financial Wellbeing and resilience to build a more
secure future.

CACI has worked in partnership with MaPS for a
decade, delivering a range of analytical solutions
that have enhanced MaPS’ understanding of the
UK’s financial wellbeing. This work has included the
development of MaPS’ current Financial Wellbeing
segmentation solution, which supported the
understanding and underpinning of their national
strategy.

To fulfil their remit, MaPS must understand the
varying financial needs of UK consumers and the
characteristics, features and locations of consumers
with lower Financial Wellbeing. This insight is critical
for targeting the right groups of consumers and
offering them the necessary support.

Company size

0-500

Industry

Financial Services

Products used

Challenge

The UK’s economic landscape has changed since the development of the previous Financial Wellbeing solution in 2019-2020, with many households’ finances having been and continuing to be affected. As such, MaPS needed CACI to review and refresh the existing segmentation to ensure it remained fit-for-purpose in reflecting the Financial Wellbeing of the UK population and would distil a complex array of characteristics into one cohesive solution.

Solution

The UK’s economic landscape has changed since the development of the previous Financial Wellbeing solution in 2019-2020, with many households’ finances having been and continuing to be affected. As such, MaPS needed CACI to review and refresh the existing segmentation to ensure it remained fit-for-purpose in reflecting the Financial Wellbeing of the UK population and would distil a complex array of characteristics into one cohesive solution.

A blended data approach was instrumental in the innovative development of this segmentation. MaPS’ flagship Financial Wellbeing survey (known as “MoneyView” from 2025) and scoring methodology was used to inform the clustering algorithms alongside CACI’s UK-wide datasets to define the segments and add further colour and context into who these people are. Consolidating research with Fresco, CACI’s powerful individual-level financial services segmentation, and Ocean, CACI’s attribute-rich consumer database, ensured segments and sub-segments would be accurately rolled out across the UK at various geographic levels. This ranged from more granular postcode sectors to local authority area or region and can be applied to financial service providers’ customer databases. Through the range of data inputs, segments and sub-segments could be profiled across over 900 characteristics to enhance understanding and drive ongoing strategy through data-driven insight.

As a result, this refreshed solution is helping MaPS define, describe and outline a set of characteristics of those most in need, as well as who to target and reach. It will also enable the opportunity to profile service users and whether users with lower financial well-being were adequately supported.

Outcomes

MaPS’ refreshed Financial Wellbeing segmentation offers a range of new benefits, including:

  • An enhanced understanding into how consumers’ needs differ and the areas of greatest need.
  • An accurate representation of the current population’s financial situation, given changes to the market.
  • Aligning to MaPS’ Financial Wellbeing scoring for consistency with internal methodologies.
  • Ensuring reach is applicable to the whole of the UK.
  • Underpinned by Fresco, enabling its use by wider financial service organisations to bolster their understanding of Financial Wellbeing (which can be particularly helpful in the context of Consumer Duty).

The refreshed segmentation has been fundamental in aspects of MaPS’ operations, from content design to communications activity. For example:

  • Informing MaPS’ UK strategy for Financial Wellbeing.
  • Identifying the target audience for MaPS’ cost of living campaign
  • Participant recruitment in user research when developing new tools and services.
  • Understanding local regions and areas across the UK most in need of support for partnerships.
  • Understanding needs, issues and policy innovation.

To find out more about the Money and Pensions Service Financial Wellbeing strategy, click here

Case study

How personalisation enabled easyJet to reduce the cost of disruption & increase retention & revenue

Summary

In the airline industry, where customer experiences can be impacted by factors outside of the airline’s control, communication is crucial to maintain satisfaction and loyalty, especially during operational disruptions. In fact, the impact of disruption to annual global air passengers will increase to 7.3 billion by 2034, more than double the 3.5 billion passengers that will travel this year.

Disruption management is therefore becoming increasingly important, demanding greater investment in the cost-to-serve and improved collaboration to enhance the industry’s ability to respond effectively. The topic must be considered with the commercial realities of improving sales and seasonal offers through marketing, however, which was a key component of CACI’s project with easyJet.

The business case centred on reducing the cost of disruption, improving retention and increasing revenue through personalisation. With disruption estimated to cost airlines up to 8% of annual revenue due to refund requests, brand damage and customer churn, investing in a unified customer communications platform would help easyJet dramatically reduce these losses.

Company size

17,000+

Industry

Travel

Challenge

Operating in an extraordinarily complex and competitive category, easyJet was experiencing a significant reduction in customer satisfaction and was losing customers and shares to competitors. EasyJet’s own analysis showed CAST (Customer Satisfaction Score) scores declining significantly within only minutes of a disruption event, and the first hour is key to securing satisfaction.

While the airline understood that reversing this trend and mitigating losses would only be possible by overhauling their customer communications, they needed help prioritising and executing this transformation. The most significant challenges were improving the consistency of information between customer communication channels, targeting communication more effectively and quickly, improving accuracy through automation and enhancing their MarTech stack and data strategy.

Solution

EasyJet endeavoured to address critical gaps in the consistency, personalisation and timeliness of customer communications across all stages of the travel journey, along with the following KPIs:

  • CAST score increasing to 13% over the next three years
  • Reducing the amount of refund requests through better communications (50% of easyJet claims for refunds being rejected). 
  • Improving communications as 37% passengers are reportedly unhappy during disruption events.

At the heart of this initiative was a holistic service design methodology that fused MarTech, a data strategy and operational transformation into one cohesive solution. To make such changes, CACI helped develop and implement easyJet’s customer-facing strategy, with three primary goals: 

  • MarTech implementation:Identify, assess and implement the MarTech solution to enable customer-centric communications including marketing, service and disruption.
  • Customer-led campaign optimisation: Improving marketing campaign targeting and messaging, reducing email volume and ensuring sales and disruption messages do not overlap.
  • Disruption management: Developing a strategy to improve and unify communication around flight disruptions across multiple channels (from email to airports).

Alongside this, CACI had to consider the operational service and business plan to ensure that processes, back-office systems and staff could deliver the new ‘to-be’ strategy while considering stakeholders’ vision and real user data based on interviews and surveys.

CACI’s approach was to run the following series of connected workstreams:

  • MarTech & customer strategy audit: Unpack challenges and limitations across the existing landscape, identifying areas of improvement and streamlining across data and tech, customer comms strategy and operating model, during which 17 workshops with easyJet stakeholders took place.
  • Customer data foundations strategy: Defining the aspirational architecture to resolve data challenges and enhance data processing, management and communications.
  • Customer marketing contact strategy: By delving into a range of behavioural, attitudinal and demographic data that had rarely been used for customer insight and targeting, CACI could identify and quantify the value of multiple cross-sell and upsell opportunities.
  • Operational & disruption customer journey: Designing the blueprint of the easyJet end-to-end customer journey to understand expectations, performance analysis and opportunities for experience optimisation. CACI also developed an aspirational customer journey, showing an improved, consistent, multi-touch experience for disrupted travellers as they prepare for their flights. 
  • MarTech implementation: CACI helped easyJet select new MarTech platforms (mParticle and Braze) and implement the new solutions, including campaign migration and activation. Working collaboratively with MarTech partners, CACI and easyJet stakeholders defined requirements that would help power personalised customer communications.
  • Operational & disruption contact strategy: Leveraging new MarTech and customer journeys, designing contact strategies to increase relevancy and accuracy through personalised messaging. 
  • Operational change: Understanding the current design and team structures across the marketing function, identifying challenges and bottlenecks in processes, skills gaps and capabilities, leading to a defined operating model that would enable easyJet to fully leverage the new capabilities, redirect core skills to higher-value activities and create efficiencies by redefining roles and responsibilities across core teams. 

Results

This initiative has already delivered measurable commercial and experiential impact, helping easyJet become more resilient, customer-centric and operationally efficient.

Through the setup and implementation of the new MarTech stack, CACI enabled a real-time customer communications platform for easyJet that moved away from legacy systems and technical debt, including:

  • 10+ data and system integrations, with web, warehouse, analytics and automated GDPR management
  • 200+ customer and behavioural events/data points that can be used for targeting and personalisation
  • Migrating over 40 million customer profiles, taking them through a process of IP warming to ensure campaign deliverability
  • Deploying 500+ campaigns, including real-time behavioural triggers and data processing campaigns
  • Training and support for easyJet development and communications teams.

CACI was also tasked with proving the value of a customer-first communications approach against the existing trade-led strategy. The team designed multiple contact strategies around different audiences to bring the new strategies to life while utilising easyJet’s price-led messaging. The resulting Winter Sale Campaign delivered:

  • 57% fewer emails sent (but more personalised)
  • 5% increase in email open rate
  • 21% increase in click through rate
  • >2x revenue generated per email sent.

Furthermore, CACI developed a comprehensive toolkit that, when implemented, will enable easyJet to lead the category in disruption management. Complete with 203 data-driven, actionable recommendations, the airline can significantly improve passenger experiences during disruption events across three distinct categories of opportunities. These either directly depend on or enable communication management capabilities in the near-mid-term.

These results demonstrate how strategic transformation, when paired with service design and data-driven insight, delivers value at scale. EasyJet is now positioned not only to weather disruption but win customer loyalty.

Case study

How CACI updated the Ocean consumer lifestyle database using AI techniques

Summary

CACI’s Ocean database contains variables relating to consumer attitudes and behaviours of the UK population at individual and household level.

Whilst already providing a market leading solution, a major update gave CACI the opportunity to rebuild many of the associated predictive models using AI techniques to even further improve the modelling, and to make predictions more balanced and “fair” across demographic subgroups such as sex and age groups. 

Industry

Technology

Products used

Challenge

Traditional classification techniques optimise “mathematical accuracy,” which measures the number of predicted labels that match the true labels; however, optimising solely for this measure can result in an imbalance in prediction quality across Yes and No labels (as to whether particular behaviours, interests or attitudes are exhibited), and unfairness across demographic subgroups such as sex and age, especially when there is a natural imbalance in the true Yes/No label proportions, i.e. where behaviours have a strong skew towards a particular sex or age group.

Addressing these deficiencies is an area of ongoing research within the AI community. 

Icon - Outline of a person with three ticks next to them

Ocean enhances clients understanding of their customers by indicating their likely attitudes and behaviours 

Icon - Outlines of three people

Traditional modelling methods can be biased in terms of prediction quality for different sexes and/or age groups 

Icon - Magnifying glass with the outline of three people

The challenge was to remove this bias, achieved by developing new AI based techniques that can optimise across both sex and age groups 

Solution

Advances in machine learning science and computational power allow Ocean to use a targeted technique for each variable rather than a one-size-fits-all approach. ​ 

CACI has developed new in-house classification techniques that significantly improve standard methods to ensure balanced prediction quality across both Yes and No predictions and demographic subgroups.  

For fairness, various measures can be used. CACI specifically optimises its predictions as measured by the Equalised Odds Difference, across sex (Male/Female/Unknown) by default or across age bands or both. 

Results

Fairness has been implemented across age and sex to ensure we are more accurately predicting attributes and behaviours whilst eliminating bias. 

In addition, a set of insightful driver variables has been added, enabling the modelling to achieve a better understanding of the real world, and over 100 new variables have been introduced for the latest version of Ocean. 

Ocean Consumer Lifestyle Database - Three women shopping together in front of a clothing store

Case study

Using the Bedrock Agent to respond to customer queries

Summary

The CACI team has developed a method using Amazon Bedrock Agent to respond to customer queries. 

Industry

Technology

Products used

Challenge

CACI has multiple software products and most of these products have their help pages. These help pages are hosted in different environments using different formats. When customers have any questions related to the products to related to how to do things, they go to these sites/documents, browse through the pages and finally find the answer. This process is not user friendly and often wastes a lot of valuable time. Some products have help pages saved in different files, which makes finding answers more difficult.  

The challenge was to find a way to easily find answers to questions from the help manual(s). 

Solution

CACI resolved this challenge using Amazon bedrock agent and demonstrated this in Pin Routes. Users can click on the icon and ask questions. The agent returns satisfactory answers. If the agent cannot find answers to the questions in the manual, it returns a message saying it could not find the answer to the questions. 

Amazon bedrock agent has some advantages over other technologies that were investigated: 

  • Native AWS services. Low setup effort and maintained by AWS. 
  • Built in Guardrails, blocking harmful queries and inappropriate responses 
  • Well documented API and SDK support allowing for relatively easy integration
  • Functionality can be extended as required 

AI backend can be standardised across multiple products and services, the integration will vary. 

Results

Amazon bedrock agent has revolutionised how customers access the help or retrieve answers to their questions. 

This granular view is a game-changer for any organisation or product wanting to improve user experience and increase the usage of the products. 

Bedrock Agent - A screenshot of the implementation of the Amazon Bedrock agent in Pin Routes

Case study

Activating data for a flagship customer experience project for the RAC

Summary

The RAC provides complete peace of mind to more than 12.7 million UK personal and business members, whatever their driving needs. They’re famous for breakdown assistance, but they also provide motor insurance and a range of other services, including buying a new or used car, vehicle inspections and checks, legal services and traffic and travel information.

Company size

1,000 – 5,000

Industry

Transportation & Logistics

Services used

Products used

Challenge

The RAC had outgrown its relatively basic campaign tool. They needed something more flexible and efficient to transform the existing manual and time-intensive process for campaign delivery. Their on-premise SQL solution was hosted by a third-party agency. Poor access to data constrained the RAC marketing team, which needed to be more self-sufficient in campaign operations.

The RAC’s Data and CRM Strategy Leader, Ian Ruffle, says:  “Because the legacy technology wasn’t efficient, it took over 48 hours to refresh the data. If it fell over, as it often did, because we were at the limits of the solution’s capability, it could take up to ten days from a customer being acquired to reflect that in the marketing solution. This was becoming a real problem.”

Solution

The RAC and CACI worked together to implement a suite of tools to transform the RAC’s marketing capabilities and to create the efficiencies and flexibility they needed. The first step was to build a single customer view (SCV) database using Snowflake. The pay-by-consumption processing function made it scalable and cost effective as well as future-proof. This gave the RAC direct access and control of their own data, which was a key requirement. Within Snowflake, CACI built a secure, accurate and compliant dataset, in line with GDPR requirements.

The database is hosted in the MS Azure cloud, and is refreshed and managed using Azure Functions, event triggers and DBT models. CACI’s resolution identity product, ResolvID, also plays a part in the solution. It’s hosted in Amazon Web Services (AWS) and consumed in real-time as event-triggered files are added into the database. This gives the RAC a complete view of each customer across multiple datasets and sources, allowing them to engage their customers in a more holistic way.

CACI implemented Adobe Campaign, Target and Analytics. For the campaign implementation, the team created 42 different tables and two different data structures – one for the B2C side of RAC’s business and one for the B2B side. Then, the RAC and CACI worked together to migrate all their existing campaigns from their legacy solution into the new Adobe Campaign instance, automating everywhere that was possible.

Adobe Triggers mean that web-based events from the customer can feed through into Adobe Campaign in real time. The RAC are using this for their enhanced abandoned baskets campaign. Communication can be triggered instantly, catching customers at a key point in the purchase lifecycle.

With Adobe Target, customer journeys can be personalised throughout the RAC’s website. Now, when a customer lands on the home page, they see personalised content based on interaction they’ve had with the brand before and products that they have or have not purchased.

Results

CACI’s team worked closely with the RAC design team to create them an on-brand template within the CACI Email Studio application. This reduced their previous dependency on third party creative agencies. Now, the RAC team is empowered to control and to create their own emails, without needing an HTML skillset. Email Studio delivers confidence in the usability and the rendering of emails when they land in the customer’s inbox, making sure it’s a positive experience throughout.

Ian Ruffle quantifies the value of the transformation: “Our marketing activation project has delivered a seven-fold improvement in data latency. We’re getting a reliable daily build of the core tables, plus many tables maintained in real time or via hourly batch processes, to meet the various trigger needs of the business.

“75% of the campaigns in the new solution are fully automated. We’re in the process of embedding this for newer campaigns. This gives our teams a huge amount more time to think about how to optimise the campaign and get the best ROI. At the roadside, when customers aren’t sure where their patrol was, they phone us. We’ve seen a 6% reduction in these calls, which is huge for us. It’s a massive cost saving and a much better customer experience, to be kept fully informed”

Case study

How Nationwide developed an understanding of individual members

Summary

Nationwide Building Society approached CACI to undertake a major segmentation exercise across their entire consumer database to enhance their understanding of consumers’ online and offline behaviours and its impact on the wider business.

Company size

10,000+

Industry

Financial services

Products used

Challenge

After the banking crisis, Nationwide Building Society wanted to engage with customers and underline its status as a mutual building society. Unlike the big banks, Nationwide is owned by its members and the business model is built on trust and a deep understanding of its customers. This makes it all the more important to respond to their changing needs.

In an increasingly complex financial services environment, developing a common understanding of their customers across the entire online and offline business has been recognised as key.

Solution

The Society approached CACI to undertake a major segmentation exercise across their entire consumer database. This exercise focussed on developing pen portraits of key customer segments, focussing not only on life-stage but also incorporating other dimensions that were relevant to the business, such as affluence, channel behaviour and attitudes.

CACI conducted workshops with key stakeholders across marketing, products and channel management. Models were developed which brought together both Nationwide and CACI’s own datasets (Ocean and Fresco), so that customers could be coded with both an overall life-stage score and a range of dimension scores. The data was pulled together to create a set of pen portraits covering the entire financial services marketplace and Nationwide’s customers within that.

Results

Nationwide Building Society is now able to understand their individual members at a glance, and offer them the right products, services and advice to help them with their banking needs. This new toolset helps Nationwide to understand its customers’ needs, and develop compelling, targeted products, services and marketing messages and has won Nationwide significant new business among younger members.

Find out more about Ocean and Fresco.