Author: Sagar Limbu

Why should businesses utilise the latest LLMs and latest NLP techniques?

Posted on: 30 August 2024
Why should businesses utilise the latest LLMs and latest NLP techniques?

In our rapidly evolving world, leveraging cutting-edge technologies is no longer a luxury, but a necessity, and Natural Language Processing (NLP) stands out as one of the most transformative tools available. NLP focuses on the interaction between computers and human language, this is commonly seen in systems such as Large Language Models (LLMs), Interactive Voice Response systems (IVRs), and voice assistants. These technologies have the power to revolutionise a company’s service by making interactions more efficient and effective, whilst reducing costs, so why haven’t more companies harnessed them? 

Let’s consider customer service – an area where the technology has already made significant strides. Many businesses still have systems that heavily rely on human operators, requiring them to tackle customer calls with highly specific and complex issues. Implementing new NLP systems can lessen the reliance on these human operators, leading to decreased wait-times, improved efficiency, and 24/7 availability. However, these systems often come with significant costs and require substantial infrastructure changes. If not executed properly, they can lead to unintended consequences and ruin the customer experience. Therefore, before adding new systems, you must understand and quantify why customers are contacting you and identify where systems can enhance the customer journey and reduce cost.  

What AI tools are there for text analysis

Various AI approaches are available to address a wide range of problems. We can categorise them as follows: 

  • Generative LLMs: Examples include GPT-4 (ChatGPT), Gemini, and Claude. These are the models that excel at generating content e.g. summarising a customer call.
  • Non-generative LLMs such as BERT, RoBERTa and their various forms: These models are used extensively in applications that require deep understanding of context or meaning e.g. accurately classifying known topics for a customer call.
  • Traditional NLP techniques: This category encompasses rule-based systems, Word2Vec, and more. They work well with simpler tasks. E.g. detecting if a particular service is mentioned in a customer webchat.

What’s the difference between generative and non-generative LLMs?

Fundamentally, LLMs like GPT-4 and BERT are built from the same building blocks called transformers, so what makes them differ?

Typically, a transformer is comprised of both Encoder and Decoder parts, but it’s been found that models can be specialised through stacking either encoder or decoder blocks. GPT-4, a generative LLM, is often referred to as a decoder-only architecture. This allows the model to receive an input, then generate text that is contextually relevant to the input. Not only does it mimic human-like text, but these responses can also be seemingly creative.

BERT, on the other hand, is built using encoder-only architecture, so think of it as a specialist in both reading and interpreting human language, rather than generating it. Non-generative LLMs, when utilised effectively, offer considerable power without a lot of the overheads associated with the generative LLMs. While some infrastructure is necessary for their implementation, the costs are not prohibitively high, especially when employing distilled models. For instance, users can avoid making expensive high frequency API calls to generative LLMs or using extensive computational resources. Additionally, users have greater control over model customisation, allowing them to achieve optimal performance for domain-specific tasks. These advantages make non-generative LLMs an excellent choice for handling highly sensitive data within a secure, isolated system e.g. a client’s secure inhouse database and system.

The following table offers a high-level comparison of the different NLP tools:

Are traditional NLP techniques still relevant? 

Although LLMs are highly adaptable and have great performance across a wide-range of tasks, traditional NLP techniques remain relevant due to their task-specific tunability. These methods have been in use for decades and continue to play a crucial role in various niche applications. Traditional approaches often benefit from cost-effective compute resources and specificity, but they require more manual tuning to achieve optimal results, and typically only work well on low-complexity tasks. In general, these techniques are better-suited for curated, lower-performance internal systems, where they can carry-out dedicated automated tasks inside a pipeline.

Intent classification in action 

Back to our customer service example – using a combination of NLP techniques, generative, and non-generative LLMs, we can identify the intent of customers when speaking to customer service operators. 

In the first instance, we can apply quick traditional NLP methods to identify if this alone is suitable for our task. However, due to the complexity of customer interactions, it is unlikely that this will produce robust results. The next step would be to employ a generative LLM on a subset of calls to identify intent topics. While this may provide sufficient insights to enhance the customer journey, for truly informed business decisions, it is essential to gain a holistic understanding. Therefore, quantifying the number of calls related to each topic might be of interest.  

To quantify the number of calls it is best to use a non-generative LLM like BERT, as they will outperform their generative counter parts, are much cheaper and far easier to implement at scale. Previously we have had great results using these types of techniques and methodologies in a range of different projects.

How CACI can help

If you’re looking to enhance your business with cutting-edge NLP solutions, our in-house data science teams are here to help. Contact us today to start transforming your use of data and stay ahead in the ever-evolving landscape of AI and data science.

Related posts:

How to estimate affluence with satellite imagery

Posted on: 19 July 2024
How to estimate affluence with satellite imagery

When looking to understand the geodemographics of a country, a segmentation can be an invaluable tool for describing the differences between neighbourhoods to drive decision making, guiding you towards the areas where your customers or lookalikes are. Indeed, CACI’s Acorn helps thousands of organisations better understand and target their audiences within the UK market. One of the key ways Acorn differentiates between top-level Categories is by affluence, which is a crucial factor for a segmentation in a business context. 

In the UK, there is a wealth of data we can draw upon to build geodemographic segmentations like Acorn, including a robust and detailed census, land registry, and most importantly, a well-defined, small-scale Postcode system. But in foreign markets, such detailed data often doesn’t exist, and where it does, it can be of poor quality, hard to verify and at a regional level. So, how can we build a reliable segmentation in these markets? 

Satellite imagery as a novel approach

In many countries, the nuances in affluence between neighbourhoods can be gleaned not from looking at tables of data, but by looking at them from above. Satellite imagery is incredibly useful when traditional data sources are lacking, but visual differences between affluence levels are clear. Take, for example, the below images of two areas in a desert country: 

In the image on the left, there are large buildings, geometrically defined roads, pools and greenery, which is expensive to maintain in a desert country. This area is likely to be of a generally higher affluence. In the image on the right, there are buildings of uneven height, densely packed together along uneven and jagged roads. This area is likely to be of a generally lower affluence compared to the image on the left. 

We can see by eye the differences between these areas, but we can’t feasibly label all the areas of a country manually. So, how to do we do this programmatically? 

Enter Convolutional Neural Networks (CNNs), a well-established deep learning technique that’s the bedrock of image analysis. Inspired by the visual cortex of an animal, they are trained to identify the patterns and shapes in an image and use this to predict the likely classification of objects or the image as a whole.  

For successful usage of a CNN, however, quality training data is vital. In classic examples of image recognition, such as the MNIST dataset of handwritten digits, most people would have no issue labelling the training images correctly to feed to the model. This is trickier for labelling the affluence of a small area, though, as you need deep local knowledge and the time to manually label thousands of images to achieve a model with usable accuracy. CACI has invested heavily in building a robust pipeline for this process, allowing us to achieve the scale required for accurate modelling. 

H3: The unifying geography

We now have a methodology for generating some information about affluence, but we still have another problem to tackle – what geography should a segmentation be built at? 

The natural response might be to consider administrative boundaries. This is the level at which most governmental social and economic data is released, so it makes sense to consider this as an option. However, the irregularity of the shape and size of administrative regions in many countries means that it can be hard to compare areas like-for-like, hampering effective decision making. 

H3 – a geospatial indexing system developed at Uber – splits the globe into a grid of tessellated hexagons at varying scales, from the largest scale at 110 hexagons to the smallest at ~570 trillion hexagons. It’s gained popularity thanks to its ease of use, speed and availability of algorithms and optimisations for working in its geography. 

H3 is a great alternative to Postcodes in areas where they can’t feasibly be used. It can be applied consistently across a country and at a low level of granularity, meaning that any segmentation applied at this level can clearly show the differences between areas in an accurate way. It’s also easy to aggregate up to other geographies, allowing you to integrate the data into other systems where data is not so granular. 

How CACI can help

Combining the power of H3 hexagon geography with the information gained from analysing satellite images, we can gain great insight into the relative wealth of areas in countries where existing data is simply not available. 

The ability to apply image analysis, however, means nothing without deep expertise in segmentation and location strategy. By combining your knowledge of your customers with our expertise in data science, insight and location, CACI can support you in your journey. 

Whether you’re an established international organisation or looking to move into a new market, contact us today to find out how we can help you take the next step in achieving your goals.

Related posts:

Get ahead with CACI: Unlock the power of AI and ML in your CRM

Posted on: 19 June 2024
Get ahead with CACI: Unlock the power of AI and ML in your CRM

Setting the stage:  

The field of Machine learning and AI has evolved rapidly in the last few years, especially in fields where large quantities of data and quick response times to queries are crucial. But given lots of these techniques and methods have been around for a much longer period, why has it taken so long for other industries outside of small start-ups and ambitious tech giants to leverage these methods in similar ways? 

CRM is an essential component of any company’s strategy. The ability to communicate with and understand customers is more important than ever due to the low barriers to entry in highly competitive global markets. Companies have only brief moments to convince customers that they are the right choice for shopping, spending time, or engaging. Optimising these initial and subsequent contacts is paramount to success. 

Beyond just expanding your customer base and attracting new clients, CRM is vital for any company’s retention strategy. The most advanced cutting-edge models in the world are utterly useless if we don’t know how to activate and capitalize on the value they represent. 

ML Foundation:  

In the CRM space our main goals are increasing consumer retention or spend, and we do this via figuring out the most effective ways to communicate with people. This can be broken down into when to speak to them, how to speak to them and why to speak to them.  

Recommendation engines lie at the core of many of these architectures, models that are designed to figure out what you want before you even know you want it. Broadly they work by looking at the kind of customer you are, then at customers like you, then finding things that they’ve bought recently that you haven’t.  

You can even simplify this down into just looking for customers who have an identical purchase history to you. Maybe a laptop you can buy on Amazon doesn’t come with a charger, so commonly when people buy this laptop their next purchase is a charger!! (You can often see this simple logic in the “People also bought” section of Amazon). But even these simple implementations are incredibly powerful in some ways, an educated guess is always going to be better than a random one. 

So how do these methods relate to CRM? Well, the general structure can be pulled away and applied to any subject. When we think about how to engage with a customer, we’re going to look for ways we engaged with similar customers and how these performed. The customer who likes Sabrina Carpenter will probably need to be spoken to in a different way to the Motorhead fan. 

This is simple stuff, right? Well exactly, but it’s a method to show that the underlying AI processes in these platforms aren’t really all that complicated – there’s a lot of room for improvement especially when implementing bespoke solutions with larger data sets.  

The next (generative) step:  

So, we already have ML methods that can tell us when and why to talk to people, great! But what’s the next step? 

All that’s left of our final stage is how to talk to them and what to say, stages which can and are currently being revolutionised by the advent of enterprise grade Generative AI. 

A current pipeline for devising CRM processes may involve creating template communications that are then populated with more specific information, for example customers in a certain segment defined by age and tenure are assigned one template and differing segments are shown another. 

This approach can be time consuming if it needs to be completed for each campaign, and may miss a level of personalisation that people will respond to, feeling as though each message is tailored to them rather than being an email blast they just happen to be caught up in. 

Skilled AI engineers armed with LLM’s can create a unique voice for each consumer, ensuring that quite literally all communication they will ever receive are exactly personalised to them and their engagement habits with your brand. 

Imagine attempting this even a few years ago, assigning a team of people to trawl through millions if not billions of rows of data to ensure that each customer got the perfect messaging for them would have been completely impossible. 

In practice this level of granularity in communications is probably unnecessary but it speaks to the potential these models have in this space – the sky truly is the limit. 

Even starting off small with these steps, giving a small part of a communication a generative component, allowing for large scale A/B testing and continuous model training, the effectiveness of these comms will improve over time. 

Freeing this time up from your CRM team will give them more time to tackle more involved problems that can’t be automated. 

How can we help you on this journey?

Don’t get left behind. Partner with CACI and our experienced in-house data science teams to integrate cutting-edge ML and AI into your CRM processes and experience unparalleled growth and customer satisfaction. Contact us today to learn how we can help you stay ahead of the curve.

Related posts:

How River Island use ResolvID to effectively perform identity resolution on customer data

Posted on: 14 May 2024
How River Island use ResolvID to effectively perform identity resolution on customer data

Background

River Island is a beloved high street retailer that has brought leading fashion trends to UK shoppers for over sixty years, with both a digital and in-store presence.

When the brand began building a marketing and analytics data technology environment with only a Single Customer View (SCV)— a single record that merges all customer data– available, they recognised the need for a SaaS solution that would be able to perform real-time identity resolution on customer data.

The Challenge

Bringing the entire SCV in-house posed a significant challenge to River Island, having to terminate many data feeds and re-evaluate incoming and outbound data that lacked clarity. The original data feeds were also set up by employees who had since left the business, resulting in a trial by fire with their SCV.

The Solution

CACI configured ResolvID, a cloud native solution hosted on Amazon Web Services (AWS) Cloud infrastructure, to supply River Island with data cleansing, standardisation, identity resolution and deduplication. Developed with a Microservices architecture, the bespoke platform offers significant advantages through its scaling, resilience and flexibility when rapid changes and improvements are required.

ResolvID comprises horizontally and vertically scalable Microservices that perform different functions with a seamless interface to enhance River Island’s accessibility. The solution leverages advanced deterministic name and address matching techniques in conjunction with digital and non-digital identifiers specific to River Island customers and their data. As part of this initiative, CACI took a three-step approach to effectively perform identity resolution on River Island’s customer data.

The Results

Leveraging ResolvID has resulted in many tangible benefits for River Island, including the creation of various customer dashboards to monitor more targeted figures and generate better, more timely data that bolsters targeted customer campaigns. There have also been noticeable improvements in workload efficiencies, such as cutting down the time required to action workloads to increase the team’s focus on refining their future strategy of doing more with their data to retain oversight on customer performance.

Once we swapped to ResolvID, the numbers we got were close enough to give us confidence that the deduplication received from ResolvID worked better than our previous managed service.

Ben Anderton, Technical Lead at River Island, shared how this real-time capability now enables the confident and immediate actioning of data and customer signups to produce effective campaigns based on genuine buying behaviours and generate accurate results.

Read the case study

You can access and download the full case study here.

If you have any questions or want to learn more, please get in touch with us to discuss what strategies and solutions that our team of experts can help you deliver.

How South West Water uses Ocean data to achieve their ambition of eradicating water poverty

Posted on: 8 April 2024
How South West Water uses Ocean data to achieve their ambition of eradicating water poverty

Background

For over 30 years, South West Water (SWW) has been supplying reliable and high-quality drinking and wastewater services to customers throughout South West England.

When the business was tasked with developing an affordability model for their customers, they set themselves a target of getting customers out of water poverty and onto the right support tariffs where necessary. While their own data and customer insight could act as a starting point, SWW recognised the impact that pairing this with CACI’s Ocean data would have on achieving their desired outcome.

The Challenge:

Higher financial strain due to the cost-of-living crisis, coupled with the industry-wide ambition of eradicating water poverty by 2025, made it imperative for customers who require and are eligible for support to be proactively identified and lifted out of water poverty through SWW’s holistic affordability toolkit.

The Solution:

Understanding the SWW brief, challenge and previous models used by the industry, a bespoke and granular dataset was created to supply a unique and current perspective into equivalised income at a 6/7-digit
postcode level, in conjunction with the wider validating characteristics of these customers, the complete SWW household customer and the property base.

South West Water built a model which combines this data with their own billing data at a customer level, enabling them to calculate the percentage of equivalised income from their customers’ current spend on their water bill at a property level. They can further combine this with OBR forecasts of income, housing costs and bill profiles to 2030 to model water poverty and wider outcomes into the future.

The Results:

From July 2022 to September 2023, over 15,000 customers were auto-enrolled onto support tariffs and brought out of water poverty. The affordability model enabled SWW to directly engage with these customers, build their trust and encourage further contact and conversation, particularly where customers may be entitled to or require additional support or services.

The use of the full range of our affordability toolkit remains critical to our ambition, we are now able to a high degree of confidence identify and, subject to further validation, engage with and auto-enrol customers onto our tariffs and bring them out of water poverty. These customers are often the struggling silent and hardest to reach who — without the data provided by CACI and the wider inputs into the model — we would not have had the capability to lift out of water poverty or achieve our commitment of eradicating water poverty which we are on track to achieve and is at the heart of our approach.

John Huxtable, Customer and Recovery Data and Insight Manager at SWW

Read the case study

You can access and download the full case study here. If you have any questions or want to learn more about CACI’s solutions, please get in touch with us.

Byte-sized inclusion: Navigating ethnic diversity in tech and data

Posted on: 18 December 2023
Byte-sized inclusion: Navigating ethnic diversity in tech and data

Whilst completing my masters in London, I (Anisah) had the incredible opportunity to collaborate with students from various diverse backgrounds. We had the chance to learn from each other’s experiences, and it was a privilege to be studying amongst such a melting pot of cultures. After graduating and going travelling, I began job-hunting in a field that I was aware was male dominated, but I didn’t quite grasp how few people looked like me, a woman of colour.  

The UK’s tech industry retained the top spot in Europe in 2022, valued at £50.71bn. However, whilst the UK’s position in this industry is one to be celebrated, achieving true diversity and inclusion remains a formidable challenge. Being a data analyst at CACI, I work with enormous amounts of data and see first-hand how powerful data can be in steering marketing decisions. Hopefully by the end of this blog, you will have a greater understanding of the critical importance that fostering diversity and promoting inclusion hold in the tech industry.

Figure 1: Ethnic Disparity in UK workforce (Tech Talent)

According to research conducted by the Tech Talent Charter, where 580 organisations were interviewed, ethnic minorities are heavily underrepresented in the tech industry, making up only 11% of the UK tech workforce, whilst 84% were represented by white individuals. Despite 87% of ethnic IT specialists holding a higher-education level qualification, in comparison to 67% of those from a white background, an unmistakable disparity exists, emphasizing the need for concerted efforts to bridge this imbalance.

Another pressing concern is the lack of senior positions being held by ethnic minorities within the industry, see Figure 2 below. The deficiency in representation at leadership levels can serve as a contributing factor to the reluctance of individuals from minority backgrounds to pursue careers in the data fields.

Figure 2: Lack of Representation for Ethnic Minorities in Senior Tech Positions

Why should we embrace diversity in the tech world?

Traditionally, the tech industry is known to be one of a homogeneous and non-inclusive nature, but with the world ever evolving and abundant with diversity, it’s crucial that workplaces embrace a culture of inclusivity, and welcome different perspectives.

Bias

Lacking inclusive representation not only in the workforce but also in the datasets we model on can lead to decisions that inadvertently exclude certain groups, introducing biases in the products or services we create. In such an environment, decisions may fail to accurately reflect diverse real-world users.

Performance

McKinsey have found that companies embracing racial and ethnic diversity are more likely to have high financial returns in comparison to those companies that have a less diverse workforce. There is also a higher likelihood of solving complex problems faster with a cognitively diverse workforce, hence performing more efficiently.

Figure 3: Financial Performance and Racial Diversity (Azara Group)

Inclusive Environment

According to PwC, only 4% of organisations succeed in implementing an effective diversity, equity and inclusion programme. Failing to foster an equal and inclusive environment can cause individuals from underrepresented groups to feel excluded and have lower morale. Since employee morale is closely associated with employee turnover, it is crucial organisations pay heed to diversity and inclusion.

Figure 4: When it comes to DE&I strategy, business leaders and employee’s perception are misaligned (PwC)

Innovation

Having a more diverse workforce leads to fresh ideas and innovation, helping the workforce to avoid tunnel vision. Whilst it may be comfortable to stick with familiarity, exposure to individuals from different backgrounds can lead to more unique perspectives, resulting in higher creativity and ingenuity.

Figure 5: Innovation and Diversity (The World Economic Forum)

How to promote ethnic diversity in your workplace

Spotting unconscious bias

Unconscious bias describes associations we hold that may not align with our conscious awareness and plays a significant role in prejudice in the workplace. By encouraging employees to self-reflect, question, and analyse their personal biases and assumptions, people’s awareness heightens and there becomes an opportunity to challenge and replace biased thoughts.

Flexible work schedules

Being open to flexible work schedules and remote working can alleviate stresses that employees may face outside of work, such as childcare. As emphasised by Forbes, women, particularly women of colour, face challenges with accessing childcare. Additionally, with London being the top destination for tech funding in Europe, remote work can appeal to a range of diverse candidates from all over the UK.

Well-being support

Providing well-being support and mentorship programmes for your employees is an action that goes beyond mission statements and training programmes. Personalising support to cater to your employees’ specific needs ensure that they feel included and heard.

How CACI promotes ethnic diversity

At CACI, we acknowledge that “our differences make us better”. We wish to create a workplace where all employees can thrive, develop, and succeed based on their talent – regardless of race, ethnicity, religion, sexual orientation, age, or disability status. We are determined to be a truly inclusive company that reflects the society in which we live and work in, and somewhere every individual can be themselves, heard and respected by colleagues and clients.

Events held across this past year are a testament to the efforts taken by CACI to make employees feel engaged and included. With past initiatives like Diwali desk yoga or the Black History Month webinar with Maggie Alphonsi, CACI is on a constantly evolving journey of education, training and accepting the differences that exist within the organisation.

Key takeaways

Hopefully, this exploration of diversity within the tech workforce has emphasised how underrepresented ethnic minorities are in the field and at senior levels. By embracing diversity in the workplace, we no longer limit the potential talent pool, which leads to higher productivity and innovation. Additionally, it serves to mitigate biases in outputs, catering to a diverse audience. The recommended actionable strategies for both employers and employees, including to embrace remote working and reflecting on personal biases, highlight practical steps to bridge existing disparities. Promoting ethnic diversity in tech will not only align with values of fairness, but also strengthen competitiveness in this ever-evolving industry.

Why Skipton is a perfectly balanced place to live

Posted on: 27 November 2023
Why Skipton is a perfectly balanced place to live

In this third blog of our series looking at balanced locations, we shift our focus to Skipton, a picturesque market town in North Yorkshire known for its rich history and breath taking countryside known as “the Gateway to the Dales”.

With its 900-year-old medieval castle forming a centrepiece that overlooks the town and its charming, cobbled streets, traditional shops and vibrant markets, Skipton has retained its historic character while also providing modern amenities and a welcoming atmosphere for residents and visitors alike. These key contributing factors have earned Skipton its place on our list of perfectly balanced places to live per our report, “Six Pillars of Success: Building Resilient Places”.  

If you have yet to read our blog that introduces these pillars, we consider a ‘perfectly balanced’ place to be:  

  • One that houses a suitable mix of chain and independent retailers at optimal sizes 
  • Supplies unique offline experiences that meet the community’s needs 
  • Provides community infrastructure that supports daily living
  • Offers adequate residential properties for the community 
  • Offers employment opportunities and flexible working spaces 
  • Encourages time spent outdoors in green spaces.  

So, what exactly are the driving factors behind Skipton being a perfectly balanced place to live? 

Pillar 1: Representation & proper sizing of independent & chain retailers

Skipton’s historic High Street is home to an array of independent shops, boutiques and local businesses, which are complemented by national retailers such as M&S and WHSmith, clothing retailers like Next and Phase Eight, and health and beauty retailers like The Body Shop and Boots.  

On the cusp of Yorkshire Dales National Park with hiking and cycling trails galore, the High Street of this historic market town also offers an array of outdoor clothing and equipment specialist retailers such as Chevin Cycles, Trespass, Regatta Great Outdoors and Mountain Warehouse.

Pillar 2: Uniquely tailored offline experiences

One of Skipton’s standout features is its weekly farmers and crafts market that offers a variety of locally sourced, traditional produce and handmade goods. All the stalls are run by local Yorkshire businesses, which generates a lively community atmosphere in and around the town. On Saturdays, locals can stroll through Skipton Market lining both sides of the High Street, establishing itself as a vital player in the town’s overall shopping experience and offerings.  

History aficionados can also visit Skipton Castle, a remarkably preserved medieval castle where the Fattorini family— jewellers and creators of the Football Association Challenge Cup— continue to live to this day. Plaza Cinema is also popular with cinemagoers—a century-old, art deco, single-screen cinema that is the sole survivor of the town’s cinemas. 

Skipton is also home to many small cafes and coffee shops (both independent and chains), pubs and restaurants. 

Pillar 3: Engaging community infrastructure

In terms of amenities and services, Skipton houses nearly everything that would be expected from a town of its size, including both small and large supermarkets like Grape Tree Skipton and M&S, banks like Halifax, Barclays and NatWest, dry cleaners, furniture shops, charity shops and estate agents.  

Skipton’s town hall is also situated near the castle, with a museum and gallery, a library and a small music amphitheatre just off the High Street.  

Skipton Station is also a major force in the town’s infrastructure, with regularly scheduled direct commuter trains travelling to both Leeds and Bradford, and several London-bound trains daily. 

Pillar 4: Support social cohesion through optimised residential design

Skipton features a wide variety of properties that are suitable for several types of people, ranging from large, detached houses to converted mill apartments, with terraced houses being especially prominent in the town. Families with children will find excellent educational opportunities available in the area, with several prestigious schools such as boys’ and girls’ grammar schools in the vicinity. 

Pillar 5: Sufficient & accessible work opportunities for the local population

Although the Skipton Building Society is currently the largest employer in the area, the town’s largest industry is likely to be tourism. Train line connections to Leeds and Bradford have opened many additional job opportunities as well.  

Pillar 6: Appealing open spaces for the community to dwell in

Being the gateway to the Dales, Skipton is home to plenty of green spaces. From inviting woodlands and walking paths situated behind Skipton Castle to impressive views accessible within a half-hour drive, Skipton and its vicinity has something for outdoor enthusiasts.  

In the heart of the town is Aireville Park, a large open space packed with sporting facilities suited for football, tennis, netball and basketball, a wheel park catering to BMX, skateboarding and rollerblading, children’s play areas, a treetop high ropes course and a café. The park is also home to Skipton’s weekly parkrun and annual triathlon, Yorkshire and Humberside’s largest pool-based triathlon. 

Fans of the Harry Potter film franchise will be pleased to know that scenes from “The Deathly Hallows” were shot at the top of Malham Cove, a short drive from Skipton, showing views across Malhamdale, down to Malham Village and Kirkby Malham. Scenes from the 1992 version film adaptation of Emily Brontë’s “Wuthering Heights” were also shot in Malham Cove.  

In the opposite direction and of similar driving distance, the renowned Brontë sisters’ home in Haworth can be found. It is now one of the oldest literary societies worldwide and was converted into the Brontë Parsonage Museum in memory of the celebrated authors of classic literature. 

Saltaire, a UNESCO World Heritage Site built in the mid-19th century as a model Victorian village depicting life for workers in Sir Titus Salt’s textile mill, can also be reached from Skipton within half an hour’s drive. Visitors will find ornate and well-preserved houses, a church and public buildings surrounding a park to stroll through, with the namesake mill, Salt’s Mill, at the epicentre of the site.

Stay tuned for our next pick of a ‘perfectly balanced’ place to live in our upcoming blog.  
 
To learn how our six property pillars can help ensure you are creating resilient places, please speak to one of our Placemaking and Property experts. 

Celebrating World GIS Day with insight on the personal grooming habits of the UK population

Posted on: 15 November 2023
Celebrating World GIS Day with insight on the personal grooming habits of the UK population

Happy GIS Day, where we take a fresh look into the history of the Gillette disposable safety razor blade, appreciate the facial movement of Movember and explore the cutting-edge stats on hairdressers across the UK. 

On 15th November 1904, the disposable safety razor blade patent was granted to King C. Gillette. To understand the grooming habits of the UK population, GIS can be employed to analyse regional expenditures on razor blades. By mapping consumer spending patterns, businesses and policymakers gain razor sharp insights into grooming preferences, allowing for targeted marketing strategies and resource allocation. This data-driven approach enhances our understanding of cultural and economic factors that influence grooming choices. 

Map shows the South East Region has the highest annual expenditure on razors

Fast forward to the 21st century, and we find ourselves in the midst of the Movember movement. This annual event encourages men to grow a moustache during the month of November to raise awareness about men’s health issues, particularly prostate cancer, testicular cancer and mental health challenges. GIS plays a crucial role in tracking the global impact of Movember, helping organisers analyse and visualise participation, identify cutting-edge trends and target areas for increased awareness campaigns.

Shifting our focus from shaving to hairstyling. According to the NHBF there has been a 21% increase in the number of hair salons since 2019. 19 million people, almost a third of the population, now live within a mile of a hairdressers in the UK. GIS provides a powerful tool for mapping the distribution of salons and barbershops, helping identify areas with high concentrations of hairdressing establishments.

Map shows postcode walking accessibility to a hairdressers

Ready to groom your business strategy with GIS? From mapping trends to uncovering hidden opportunities, contact us to explore the cutting-edge possibilities InSite and CACI data can offer your business. Sharpen your strategy, shape up your success!

Travel spend behaviours that will redefine your customer strategies

Posted on: 3 November 2023
Travel spend behaviours that will redefine your customer strategies

travelling

In our previous blog, we explored some of the most common challenges that have arisen in the travel sector in 2023 and how you can leverage digital marketing and personalisation to tackle them. 

In an era where the Cost of Living is placing pressure on consumers’ budgets, the significance of precise, targeted marketing and aligned messaging cannot be overstated. Moving towards the end of the year and the holiday-booking surge that happens in January, marketers will need to be aware of timely shifts in behaviour and expectations to capitalise on customer intent at the right times. 

Through our recent Cost of Living consumer survey, we have identified important shifts in travel spending habits that will influence the January booking window, and have pinpointed the demographic groups experiencing the most significant adjustments:

  • Travellers are more frugal than they were, but still want the best experience they can afford 
  • Travellers will spend more time than usual researching to try and find the best the value options
  • Travellers may be more sceptical about convenient booking options and package deals still offering the best available value 
  • Solo travellers, travellers without children and families are all being hit differently, and will therefore have different needs and expectations when it comes to researching and booking.

Despite these shifts, there are still plenty of opportunities for travel businesses to keep customers interested in going away. Below we have detailed some of the tactics that can help:

Consumers’ travel spending will continue—with exceptions

Many travellers may have set expectations in their minds around what a ‘good trip’ looks like, such as having to be a certain distance away or for a minimum number of days. Our findings concluded that despite the ongoing Cost of Living crisis, holidays remain a priority for consumers of all ages, and they are determined to find ways to make them happen.  

In fact, 57% of consumers surveyed have or will be making changes to their holiday habits to save money and get more for their money. 

Respondents expect to cut their expenditure on their next holiday, with 45% saying they will either find a cheaper destination, travel option, accommodation, do fewer activities or simply reduce their trip length. Which means that they will most likely spend more time researching their holidays and trips. Equally, this may affect the package holiday market as consumers compose their own holidays by booking their own flights, hotels and transfers.

The most affluent Acorn demographic groups expect to cut their holiday expenditure in this way more than other groups, as do millennials and Gen Z respondents. 22% of respondents are also taking fewer breaks compared to previous years.  

To continue to encourage travellers to go away, travel businesses will need to shift the focus from larger packages and holidays and instead start spotlighting the benefits of closer destinations and shorter trips or weekend getaways. Their focus language will need to be around ‘doing more with less’ to ensure travellers continue to see the value in getting away no matter the length of holiday. Travel businesses can promote this throughout the year as well, as shorter breaks are far more flexible and can happen at any time.

Gen Z are spending the least on travel this year

Younger holidaymakers—particularly Gen Z— appear to want to spend as little as possible to keep travelling this year.  

When it comes to cheaper destinations and accommodation, more than 1 in 5 respondents of younger age groups have opted for these. Younger men surveyed are particularly determined to continue to take breaks as they have before. Just 14% of Gen Z men expect to take fewer breaks compared with previous years, yet that rate more than doubles among Gen Z women, 29% of whom reported that expectation.  

To combat this, travel businesses that speak directly to traveller concerns around value will build their trust in the options they’re being presented with. For travellers that are wary of costs and will expect to be researching for longer periods of time to seek the best value, curated options and direct, value-based messaging will help to make their concerns feel acknowledged and will offer a faster and more convenient option for them to browse.

Family holidays are being cut…

Respondents that have children appear to be affected to a greater extent than those without. The appeal of cheaper destinations rises from 14% among those without children to 24% among those with under 18s in their household. Bearing this in mind, more price-sensitive families can be a stronger focus for value-based messaging and cheaper travel options from travel businesses.

…while solo travellers are on the rise

The results show that independently living, single travellers are taking the most advantage of getting away on holiday this year. In fact, rates of those cutting back on holiday expenditure are nearly 1/3 lower among those who live alone. This includes reducing spend in other areas to make room for travel and shortening the length of trips compared to previous years. To maintain interest across all pricing options, travel businesses should target more expensive and premium options towards solo and non-children couples.  

How can CACI help?

As a trusted partner to major brands within the travel industry, our team is highly experienced in supporting strategic targeting by leveraging the necessary data and technology to understand customers and their behaviours as innately as possible and being able to design marketing strategies to target these groups. 

CACI partners with global brands to harness and enhance customer data, enabling them to identify and prioritise the most valuable customers. Insights are then activated through strategic CRM initiatives and acquisition strategies, ensuring targeting is precise and relevant. This approach is pivotal for brands seeking to align their products with consumer needs and foster long-lasting brand loyalty, repeat bookings and maximising share of wallet. 

To find out how we can support your business strategies or operations by enhancing your customer understanding, or to find out more about the products and services we offer, please get in touch. 

Read blog 1 from our travel series: Travel sector hurdles and the promise of digital marketing and personalisation

Leveraging data to underpin your Sustainability strategy

Posted on: 16 October 2023
Leveraging data to underpin your Sustainability strategy

Woman plugging electric charger into car outside Home With Family

Ever since helping an automotive client launch their first all-electric vehicle into the UK a few years ago, I’ve had a growing interest in sustainability and the environment. Now, as part of CACI’s internal working group on Climate Change and Decarbonisation, I’m involved in several exciting initiatives where CACI is using data to drive sustainability.  

Everyone has a role to play

Climate change and what governments, brands and individuals are doing about it has become a constant in the news cycle and data is proving to be a powerful asset in identifying and meeting key sustainability targets. 

Governments need to support their communities

At a local level, governments must understand their communities and provide support via adequate infrastructure. For example, councils are already working with a wide range of data to understand demand and develop strategies for residential EV charging points. Working with CACI means that council-held data can be enhanced through consumer and geospatial data to further define community needs for EV infrastructure or even green space development. 

Strong brands are those taking environmental responsibility

The last five to ten years has seen the rise of new, innovative brands that are disrupting their industries. Among my favourites are a company using flexible solar cells to create solar powered remote controls and headphones, and a packaging company being recognised by Prince William and the Earthshot Prize for using seaweed to replace plastics in food takeaways and hospitality. 

In more traditional industries, environmental responsibility is arguably even more important if we are to have a sustainable future. B-Corp certification is a widely recognised way of measuring a company’s social and environmental impact, and being certified tells consumers a company is serious about their commitments. The CDP (Carbon Disclosure Project) is a not-for-profit charity that enables companies to disclose and take accountability for their environmental impacts – a key first step in positive action – something many of our clients are signed up to.  

Away from these more well-known programmes, we’re working with clients who have clearly stated environmental goals of their own and who understand that all departments have a responsibility. This includes Facilities Management assessing how to cut energy consumption, Logistics optimising their routing to reduce CO2 emissions, and Marketing implementing paperless processes and better segmentation to make communications more efficient. 

Individuals support net zero goals

A survey by CACI at the beginning of September shows that 84% of consumers support the government’s goal of achieving net zero by 2050. Consumers are actively looking for brands that have strong environmental policies, with half of respondents seeking brands that set their own, earlier net zero targets.

Support for Net Zero goals from CACI State of the Nation Update consumer survey

Fig. 1 Support for Net Zero goals from CACI State of the Nation Update consumer survey (September 2023) 

How CACI is making a difference

Data is at the heart of everything we do at CACI, and we’re encouraged to think of innovative ways to use it. One example is Ocean, a database of the UK population containing over 600 attributes across demographic, digital and attitudinal characteristics. Our Green Lifestyle attributes include attitudes to recycling, reducing energy use and dietary choices, and can be used to profile and understand your customers’ attitudes to inform targeting audiences and messaging. 

Further evolving this, we’ve developed an ESG score, that drills deeper into Environmental, Social and Governance issues and can help brands gauge which customers are likely to pay a premium for sustainable products and services.

Example Environmental Score pen portrait

Fig. 2 Example Environmental Score pen portrait 

In addition to these attitudinal variables, we’ve been looking at carbon emissions and developing innovative ideas and solutions that include: 

  • Carbon footprint of Household and Travel: Identifying and measuring the impact of consumer behavioural choices on carbon emission. This will help consumers understand their impact (based on property, travel and consumption) and improve local governments’ understanding of their communities. 
  • Carbon footprint of Fulfilment: Helping commercial property owners and retailers assess the carbon impact of acquiring customers and fulfilling orders. This could be used to inform parking, EV charging infrastructure and determine whether click & collect is better than delivery. 
  • Carbon footprint of Logistics: Evolving CACI’s Pin Routes route optimisation software to support the electrification of fleet and distribution services. Our algorithms help reduce mileage, vehicle count and CO2 emissions, cutting valuable costs and reducing your carbon footprint. 
  • Carbon footprint of Marketing: Measuring the carbon emissions from different marketing campaigns and channels to enhance businesses’ understanding of their environmental impact. This enables marketing teams to balance sustainability with sales and optimise campaign strategies to improve both. 

CACI is registered to the Social Value Portal and is actively working towards achieving social and environmental goals aligned to the National TOMs framework.  

We’re passionate about using data and technology to create more sustainable businesses, so if you’d like to discuss how we can help you, please get in touch.