Consumer and Demographic Data Archives

Multi-touch attribution (MTA) vs marketing mix modelling (MMM)

Posted on: 24 July 2025

What is marketing mix modelling (MMM)?

Marketing mix modelling (MMM) is a statistical tool that helps organisations understand and quantify the impact of marketing activities on consumers’ behaviours, sales, return on investment (ROI) and more. It breaks down an organisation’s performance by channel, incorporating various types of data to evaluate effectiveness and determine which marketing activities are most heavily influencing the organisation’s business outcomes, which we explore further in our blog on marketing mix modelling.

Based on a series of steps, MMM begins with data collection of marketing variables, followed by an analysis of the data collected to identify relationships or patterns and building a customised model to showcase actions and results. Finally, scenario testing can be conducted to gauge possible outcomes, leveraging the results to optimise marketing strategies and bolster decision-making.

What is multi-touch attribution (MTA)?

Multi-touch attribution values each customer touchpoint leading to conversion, with its goal being to decipher the marketing channels or campaigns that should be credited with the conversion. The intention of this is to measure the effectiveness of each channel or touchpoint so that marketers are aware of where they should focus efforts and resources and allocate future spend in the most effective ways possible to enhance customer acquisition efforts.

Through multi-touch attribution, a more comprehensive view into customer journeys can be gained, enabling organisations to create better strategies or optimise their ad spend in line with market shifts. The ability to see how each touchpoint impacts a sale is what allows organisations to dissect customer journeys and allocate budgets accordingly.

What are the differences between multi-touch attribution (MTA) vs marketing mix modelling (MMM)?

Aggregated versus disaggregated data

Aggregated data is statistical data used in MMM that is grouped into channels, regions or times to assess trends in terms of how channels contribute to sales. Disaggregated data, on the other hand, is behavioural data that is used in MTA to gain the most detailed insights possible at user or individual level.

Organisations require aggregate information for visibility into external trends that may be affecting marketing efforts and conversions. In comparison, the precise level of detail available through disaggregated data is critical in MTA as it is required for assigning multiple touchpoints within a customer journey.

Objective and impact assessment

MTA uses trackable customer interactions to understand the importance of each touchpoint. As a result, one of the most substantial differences between these two is their objective. MTA focuses on the impact of specific, individual touch points and their sale or conversions impact, whereas MMM focuses on the overall impact of your marketing mix and how that combination influences sales or other outcomes.

Choosing the right approach for your company

MMM’s main goal is to help organisations deduce overall business outcomes and MTA helps organisations understand the contributions of individual touchpoints to conversions or actions. MMM includes both online and offline channels, whereas MTA only includes digital channels that track individual user behaviours.

While MTA may not be easy to implement due to ever-changing customer journeys paired with uniting all touchpoints across various devices, channels and platforms, it does enable flexibility and offers a more granular understanding of what does and does not work within marketing initiatives. This flexibility and granularity equips organisations with insights that allow for informed, data-driven decision-making for digital marketing campaigns.

When to use multi-touch attribution modelling (MTA)

Multi-touch attribution has become a staple for organisations requiring tactical insights and are focused on short-term optimisation by measuring and quantifying the impact that their digital marketing campaigns are having. The visibility that multi-touch attribution modelling provides into the success of touchpoints across a customer’s journey is unparalleled. This insight is critical for organisations to consider amidst consumers’ increasing wariness of marketing messaging. Through this, the right audiences and their respective marketing preferences can be identified across channels, enabling customised messaging to be created and the right consumers on the right channels at the right times to be reached.

Maximising ROI can also be made possible through multi-attribution modelling by engaging with consumers in fewer though more frequent and impactful marketing messages that ultimately shorten sales cycles.

When to use marketing mix modelling (MMM)

Marketing mix modelling should be used when needing to understand the combined impact of advertising spending, promotions, pricing and distribution channels. It can be particularly impactful for organisations that are well-established and have a plethora of data over the course of many years to work with. From media activities to external variables including macroeconomic factors and competitors’ activities and internal variables like product distribution, product changes and price changes, countless categories can be monitored for organisations to analyse data and understand the relationship between sales and these elements. Its [immunity to the everchanging privacy landscape] is also a key advantage.

How to use both approaches together

Both MTA and marketing mix modelling MMM are key approaches in the realm of marketing analytics. When used together, MMM can offer macro-level views into marketing impact on revenue, while MTA can supply granular insights into the effectiveness of specific marketing channels. Organisations that understand when and how to use both approaches will find themselves transforming their marketing strategies and maximising their ROI.

Combining these two approaches when building an attribution strategy is often recommended. However, MMM will ultimately be most effective for gaining long-term, strategic insights that can bolster planning and financial outcomes, whereas MTA is best suited for short-term, tactical insights that can enhance day-to-day optimisation, campaigns and decision-making.

How CACI can help

CACI supports businesses in their delivery of optimised marketing efficiency by:

Determining the value and performance of activity through evolved multi-touch & econometric modelling
Producing results to sustain & increase growth through targeted investment & improved marketing performance
Delivering improved accuracy, consistency and availability of marketing performance insights
Enhancing capability by evolving data, technology & process
Supporting the provision of ongoing strategic & delivery resource.

Find out more about the impact that digital attribution modelling can have on your business by contacting us today.

Watch a session from our recently event on how to optimise marketing performance through Commercial Mix Modelling.

Sources:

How Marie Curie use data & insights to improve supporter engagement & increase income

Posted on: 15 May 2025

At CACI, we have been supporting charities in optimising their data by supplying ongoing support through solutions, technology, tools and data that work in a more targeted and efficient way and ultimately help more people. Marie Curie, a leading charity dedicated to providing free palliative and end of life care and support to people living with terminal illnesses, has been making significant strides in enhancing its fundraising and supporter engagement strategies. Their work has been raising public awareness and influencing decision-makers across the UK on the issues affecting those reaching the end of their lives and the people closest to them, enabling more people to access high quality care and support when and where they need it most.

In a recent webinar, we came together to share insights into their collaborative efforts of leveraging data for greater impact. In this blog, I’ll uncover the key takeaways from the webinar and the value of Marie Curie’s work with CACI, combining their own data with CACI’s to improve their supporter engagement and ultimately increase income.

Building strong data foundations and data enrichment

I kicked off the webinar by emphasising the importance of building strong data foundations, highlighting common challenges faced by charities, such as siloed data and inconsistent supporter information. These challenges hinder the depth of data insights and the unification and linking of data, ultimately impacting improvements for the quality of end-of-life outcomes and gaining a granular view into supporters. By addressing these foundational issues, Marie Curie can better enrich their data and activate it for meaningful engagement.

Why did Marie Curie embark on a data enrichment journey?

Mark Lumby, Head of Fundraising Insight at Marie Curie, shared the charity’s motivation for embarking on a data enrichment journey: the necessity of understanding more about their supporters beyond basic demographics. The more data charities have access to, the more robust their engagement strategies can be shaped, resulting in more income from supporters. By partnering with CACI, Marie Curie aimed to gain these deeper, necessary insights into supporter profiles, affluence, interests and behaviours.

CACI’s Acorn and Ocean data have played a crucial role in Marie Curie’s data enrichment efforts. Acorn is CACI’s powerful consumer classification tool that segments the UK population by postcode, enhancing the charity’s understanding of different types of people and places by analysing demographic data, social factors and behaviours. Ocean is CACI’s consumer database that offers lifestyle variables, further enhancing Marie Curie’s customer understanding through the ability to assess 100 variables that illustrate supporters’ profiles and interests to target them effectively. Together, these tools have enabled the charity to create detailed supporter profiles and uncover new engagement opportunities.

What were the strategic objectives & key use cases?

Our collaboration with Marie Curie was driven by strategic objectives, including enhancing their product portfolio by identifying overlaps and opportunities for cross-selling. By understanding the profiles of their supporters through a lens enriched by data, Marie Curie could tailor their engagement strategies more effectively by engaging with supporters at individual or segment cohort levels and determine the best methods of interaction via online or offline channels. Through data enrichment, the type of content and messaging could also be crafted to appeal to the target demographic of supporters and personalise their experience.

What has worked well?

Steph Gray from Marie Curie’s insight team shared practical examples of how enriched data has been used to drive value. One notable success was the creation of a profile model for cash appeals, which significantly improved response rates and ROI. By targeting supporters who resembled existing cash donors, the charity improved engagement and secured higher second gift rates.

Marie Curie’s efforts to cross-sell and acquire new supporters have also benefitted from data enrichment. By identifying key audience groups and tailoring their messaging, the charity has seen improved results in cold acquisition campaigns. This targeted approach has led to more effective use of resources and better overall outcomes.

What’s next for Marie Curie?

Going forward, the charity plans to continue refining their data models and datasets and explore new variables for up-to-date, accurate supporter understanding. They aim to combine demographic data with behavioural insights to create even more robust supporter profiles, along with additional creative and channel selection testing. This ongoing commitment to data-driven strategies will help Marie Curie maximise their impact and influence supporter journeys.

Our partnership exemplifies the transformative power of data in the charity sector. By enriching their supporter data and leveraging advanced segmentation tools, the charity has been able to enhance their fundraising efforts and engage supporters more effectively. By watching the webinar here, you can find out how data can drive meaningful change in the charity sector. To learn more about the continuous innovation and strategy refinement Marie Curie is undertaking, visit their Knowledge Hub.

What is Marketing Mix Modelling (MMM)?

Posted on: 9 April 2025

For any marketing activities to be successful, understanding consumers’ behaviours and whether a channel is oversaturated is essential. While data and analysis play undeniably important roles in this, marketing mix modelling (MMM) plays an even greater one, representing the merging point of data and analysis with the psychology of consumer understanding.

Marketing mix modelling (MMM) is a statistical tool that enables an understanding of how each part of an organisation’s marketing activity impacts consumers’ behaviours, sales, return on investment (ROI) and more. Through MMM, an organisation’s performance can be broken down by channel and various types of data can be incorporated to evaluate the effectiveness of marketing activities and determine which are making the most substantial differences to the organisation’s overall performance.

Benefits of marketing mix modelling (MMM)

Enables organisations to quantify and measure marketing channels effectively to assess which drive the most sales and return on investment
Equips organisations with long-term insights that will bolster planning through effective forecasting and marketing campaign generation based on previous performance
Helps organisations allocate budgets according to the best performing channels due to measuring growth based on investments
Instils confidence due to its statistical reliability and being privacy-safe, both of which are particularly important in a post-cookie world
Offers organisations a holistic view of the impacts that various factors will have on achieving specific KPIs, ensuring marketers can make more informed decisions based on how and when marketing activities will impact KPIs.

How do marketing mix modelling (MMM) & commercial mix modelling (CMM) work?

Marketing mix modelling (MMM)

Marketing mix modelling (MMM) is used by organisations aiming to understand how marketing activities impact KPIs being measured. Its ability to measure the impact that certain pricing choices, promotional offers, product launches or advertising campaigns may have on sales makes it a game-changer for organisations.

In MMM, the dependent variable used to assess the relationship between sales and marketing activities is usually:

Sales volume: to assess the impact of different marketing activities on sales
Revenue: to track the amount of money generated by sales
Competitor analysis: to understand how your organisation’s marketing activities are affecting your position in the market.

In contrast, the independent variables in MMM are the marketing activities or factors that might drive those results, such as:

Advertising spend: the amount invested in promotion across various channels.
Price: to explore the impact of price adjustments on sales
Promotions: discounts, coupons, or offers that could increase sales
Distribution: the potential impact of product availability across various locations on sales.

Commercial mix modelling (CMM)

Commercial mix modelling (CMM) is an analytical approach that examines a variety of commercial factors that drive an organisation’s performance. It begins with collecting data from across the organisation on pricing, promotions, distribution channels, products and more, combining the resulting data into a cohesive dataset. The insights presented within the dataset help organisations gauge which factors contribute most to performance and where investments result in the highest returns. It also enables organisations to test various scenarios— price changes, promotional adjustments, changes within distribution channels— to assess the potential impact on performance. Through this, organisations can optimise their overall commercial mix to grow and become more profitable.

How does commercial mix modelling (CMM) differ from marketing mix modelling (MMM)?

While both commercial mix modelling (CMM) and marketing mix modelling (MMM) are granular approaches that help organisations analyse the impact of marketing activities, their scope, methodology and applications differ.

Scope

CMM offers a broader approach when it comes to evaluating the marketing activities that would impact an organisation’s performance, integrating various functions to optimise revenue and profitability. It encompasses external, non-marketing data sources such as weather, seasonality, competitor pricing, interest rates, etc.

MMM, on the other hand, is more partial, purely marketing data that offers a more detailed and expansive result. As a statistical analysis method, it quantifies the impact that marketing activities— campaigns, paid advertisements, promotions, etc.— have on specific KPIs. Focusing more on media and investments rather than a wider marketing strategy, its granularity is what marks its stark contrast to CMM.

Despite the broad scope of CMM, it is just as granular and technical as MMM.

Methodology

CMM blends analytics, business intelligence and strategic insights, considering both internal and external factors that can affect an organisation’s growth. The approach entails:

Scoping & data auditing: Understanding the KPIs and defining whether the model should target revenue, acquisitions, renewals or some combination form the scoping basis. Data auditing includes tech and journey mapping to determine the stages comprising the funnel for lead gen and closing, as well as the tools and tech used at each stage.
Data collation & cleaning: This includes a data request to outline the full scope of what can be used in the model, with cleansing, organising and playback taken into consideration to check for completeness and broad accuracy. During this stage, data is also combined and reaggregated for ingestion into the model.
Exploratory analysis & feature configuration: Plotting all the raw data to understand distribution and periodicity and exploring this raw data to identify gaps and anomalies is conducted during this stage. Correlation analysis helps find feature relationships and possible collinearity, feature types are configured for use in the model and decay is applied (AdStock) to channel features to simulate the memory effect of advertising. Diminishing returns to channel features simulate channel saturation and other transformations such as smoothing or feature combination.
Pre-processing & feature engineering: Calendar and dummy variables can be included to represent milestones and seasonality, with each variable transforming across a range of parameters to find the most realistic behaviour.
Commercial mix modelling (an iterative process with pre-processing & feature engineering): Once the model for the approach is scoped (e.g. logistic vs. linear, pooled, nested, hierarchical) and fit for processed features to optimise accuracy and generalising power, it is then checked against existing commercial knowledge and external priors and returned to feature processing to refine variables and tune parameters accordingly. All candidate variables are imported and tested from the pre-processing stage. Finally, the model is refined continually by adjusting variables to optimise statistical measures of accuracy.
Optimisation & simulations: The present channel saturation is analysed, the optimal channel mix is delegated for specific budgets and results are presented from scenario simulations to understand which channels have headroom and which are oversaturated. A budget guide is provided for optimising revenue and the ability to plan for different scenarios: mitigating headwinds, capitalising on opportunity and planning contingencies.
Next steps & recommendations: Recommendations are given based on budget optimisations and added value.

MMM, in comparison, focuses on econometric modelling and regression analysis to determine the contributions made by various marketing channels on an organisation’s outcomes. Econometric modelling is a statistical, mathematical approach that quantifies the relationship between marketing activities and business outcomes, built with historical data. Regression analysis is a technique used within econometric modelling to measure the impact of independent variables (marketing activities) on dependent variables (sales or revenue).

Application

Senior executives and C-suite employees may use CMM for longer-term strategic planning and decision-making, whereas MMM would be used by marketing teams to optimise spending and budget allocation towards campaigns or advertisements.

The broader scope of CMM enables senior executives and C-suite employees to gain a complete picture of the various commercial drivers and their impact on marketing rather than isolated results. On the other hand, the granularity of MMM ensures marketing teams strategically plan and forecast how changes in spending across channels might impact sales and plan scenarios accordingly.

How to build a marketing mix model

The first step in building a marketing mix model will be to collate and prepare your data. This will involve collecting historical data on sales and marketing spend across different channels and should go back far enough in time to effectively capture market conditions and seasonality fluctuations.

Next, selecting the appropriate model to facilitate this will be crucial. Selecting the model can come from its robustness or flexibility, catering to your organisation’s unique needs.

Building the model will come after this. This will include defining the relationship between marketing spend and sales or other KPIs and considering carryover effects, saturation or external factors.

Furthermore, fitting the model will use your historical data to estimate the parameters of the MMM. Once the model is fit, the results can be analysed to precisely determine their contributions towards each marketing channel.

Finally, the insights gleaned from these results can help you adjust marketing strategies accordingly, increase budgets within the highest-performing channels and reduce it in those underperforming.

Examples of marketing mix modelling (MMM)

Organisations across a variety of industries can apply marketing mix modelling (MMM) to lead to improved outcomes. A few of such examples include:

Consumer Packaged Goods (CPG): Gathering data on sales, advertisements, campaigns and pricing can help CPG organisations understand which channels—digital advertising, TV campaigns, etc.— drive the most overall return on investment.
Retailers: From seasonal promotions to discounts and the influence of both in-store and online presence, retailers can leverage MMM to understand peak performance periods, digital sales and foot traffic to allocate budgets accordingly or reassess promotional calendars.
Financial Services: Financial institutions can use MMM to evaluate their multi-channel advertising efforts and ensure they are reaching the appropriate audiences, encouraging sign-ups.

Why businesses should choose CACI to carry out CMM

CACI supports businesses in their delivery of optimised marketing efficiency by:

Determining the value and performance of activity through evolved multi-touch and econometric modelling
Producing results to sustain and increase growth through targeted investment and improved marketing performance
Delivering improved accuracy, consistency and availability of marketing performance insights
Enhancing capability by evolving data, technology and process
Supporting the provision of ongoing strategic and delivery resource
Helping businesses dig into bespoke segments and utilise in-house data products to unlock insights
Offer businesses location-based insights into the effects that marketing has at various levels, from stores to regions.

Find out more about the impact that marketing mix modelling can have on your business by contacting us today.

Click here to read our short infographic to learn how CACI’s Commercial Mix Modelling can transform your business strategy.

SOURCES:

How Kirklees Council enhanced its digital service efficiency with the help of demographic insights

Posted on: 18 December 2024

Background

Kirklees Council has a population of 437,593 and covers an area of 157 square miles. It is the third largest authority in West Yorkshire and is a constituent member of the West Yorkshire Combined Authority. Like many local authorities, Kirklees Council faces a dual challenge of managing budgetary constraints while addressing increasing demand for services. To maintain the quality of services that residents value, the council has focused on encouraging the use of lower-cost digital self-service options wherever possible. One key area identified for improvement was the handling of council tax inquiries, which placed a significant burden on call centre resources. Following conversations with CACI about the impact that demographic data insights could bring to alleviate this challenge, it was clear to Kirklees Council that this was the solution to the challenge.

Challenge

With over 190,000 households in the Kirklees area, the council’s call centre received a substantial volume of calls related to council tax. During the 2022/23 period, approximately 16% of these households contacted the call centre about council tax issues. A significant portion of these calls – 47% – were categorised under ‘check or query a bill,’ with 60% of these queries related to checking instalments or outstanding balances and seeking advice. Additionally, 16% of callers made payments through the call centre. Notably, 31% of accounts had repeat callers, with 5% of households calling four or more times within the year. The council recognised the need to delve deeper into not only understanding the reasons behind these calls, but also the demographics of the callers, particularly repeat callers. This insight was crucial in shaping the design of effective strategies that would reduce the volume of calls and promote the use of digital self-service solutions. Lacking data or insight about these callers heightened these challenges, which is where CACI’s data would prove to be essential.

The Council recognised the need to delve deeper into not only understanding the reasons behind these calls, but also the demographics of the callers, particularly repeat callers. This insight was crucial in shaping the design of effective strategies that would reduce the volume of calls and promote the use of digital self-service solutions. Lacking data or insight about these callers heightened these challenges, which is where CACI’s data would prove to be essential.

Solution

To address this challenge, the Council’s project team collaborated with their Data and Insight (DI) team to analyse call centre data using CACI’s segmentation tool, Acorn. Acorn supplied a detailed demographic and socioeconomic profile of the households contacting the council. The profiling revealed that a significant proportion of both first-time and repeat callers belonged to younger and less affluent Acorn demographic segments, specifically Cash-Strapped Families, Urban Diversity and Hard-Up Households.

Acorn’s Knowledge Sheet, which includes over 800 variables from digital behaviours to channel preferences, helped illustrate that these groups should be the ones to utilise self- service capabilities instead of calling. As these groups continued to call, the Council was compelled to investigate additional factors that could bolster self-sufficiency for residents, such as their website. They quickly realised that if they were to redesign the website to better support self-service options for these target groups, the Council would have a better chance at encouraging behavioural change and telephone enquirers online, thus reducing service demand and achieving cost efficiencies.

Benefits

With an evidence base provided by Acorn’s detailed analysis, the Council is set to undertake several initiatives to reduce the need for phone calls by further enhancing digital self-service options, including:

Implementing chatbots: Implementing chatbots capable of answering common queries related to council tax will provide immediate relief and reduce call volumes.
Council tax balance checker: The Council is developing a quick and easy-to-use online tool allowing residents to check their council tax balance and instalment details without having to call the council.

These initiatives are guided by the insights gained from Acorn, which identified specific demographic segments and their preferences. By focusing on these insights, the Council can effectively target improvements that will encourage the use of digital self-service options, resulting in fewer calls. The enhanced website, combined with the introduction of chatbots and the balance checker tool, will provide residents with sufficient alternatives to calling the Council. These changes will not only improve the customer experience, but ensure the Council allocates resources more effectively to achieve further cost efficiencies.

Furthermore, the Council will be planning targeted outreach activities with landlords and tenants—identified through Acorn segments—to further reduce call volumes. This initiative aims to educate these groups on the available digital self-service options and encourage their adoption.

Find out more

Please view the full customer story here. If you want to learn more or have any questions please get in touch with us.

Which Klepierre retail centres in France would benefit the most from Gymshark?

Posted on: 17 December 2024

In our previous blog in this two-part series, we uncovered why France would be a good option for a Gymshark European market expansion and key considerations the brand could take for a successful expansion. Today, we’ll assess which Klepierre retail centres in these high-potential French cities would benefit most from housing a Gymshark in their centre as part of a hypothetical Gymshark French market expansion.

How Retail Footprint Europe could help Klepierre understand which retail centres would benefit from a Gymshark store

While there are many centres in France that would be suitable to bring Gymshark into based on the best shopper profile correlation in a hypothetical Gymshark market expansion, Retail Footprint Europe, CACI’s machine learning catchment model defining catchments for thousands of destinations, has helped determine three particular Klepierre centres that would ultimately become a good fit. With key Gymshark shoppers comprising Affluent Singles & Couples, Affluent Young Families, Middle Income Singles and Student Life profiles from Acorn, CACI’s geodemographic segmentation, these insights were cross-referenced against Retail Footprint Europe insights to equip the business with granular insights and tangible actions to help landlords deduce which centres would work and why.

Finally, to gain insight into actual footfall and compare actual versus expected footfall against these Gymshark profiles and conclude which centres presented opportunities to attract more of Gymshark’s core shoppers, Mobility Data was leveraged.

Saint-Lazare Klepierre in Paris

According to our findings, one of the Klepierre centres that would benefit most from the presence of a Gymshark would be the Saint-Lazare in the Haussmann-Opera retail area. This centre is expected to attract the highest potential of Gymshark’s core shoppers at 43%. Saint-Lazare also has the most affluent profile at an expected 34%. However, the area is home to lower levels of Student Life profiles, with just 1% expected to visit the centre.

Paris houses a strong proportion of premium retailers that align with Gymshark’s offering, with this particular Klepierre centre featuring a blend of competitors and complementary retailers, already housing the likes of Adidas and Nike, which both have similar offerings to Gymshark. Its shopper demographic also lends itself to those who are likely to either be existing Gymshark customers or will become ones once the brand enters the physical market.

Retail Footprint Europe insights for Saint-Lazare Klepierre

The Haussman-Opera retail area holds the third largest clothing and footwear store presence across France, with many premium and broader retailers and a higher percentage of affluent and younger consumers. Our findings also show that people travel well outside of Paris into this area to shop, making it a fantastic location to quickly grow brand reach and exposure.

Acorn insights for Saint-Lazare Klepierre

Saint-Lazare appears to perform the most in line with Gymshark’s core shoppers, with 44% originating from its expected profile according to our Mobility Data findings. This data provides insight on actual footfall and illustrates the comparison between actual and expected versus the Gymshark profile to understand if a centre had an opportunity to attract more of Gymshark’s core shoppers.

As a more premium brand, Gymshark achieves particularly high indexes for affluent consumers, but also performs well with aspiring, younger and urban consumers within the Gymshark core shopper profiles outlined by Acorn. Compared to fellow sportswear brand, Adidas, the brand has a much broader appeal and can perform in-line with their average consumers, while Gymshark performs significantly weaker in these segments.

Centre Commercial Centre Bourse Klepierre in Marseille

Retail Footprint Europe insights for Centre Commercial Centre Bourse Klepierre

Centre Commercial Centre Bourse would be a strong runner up to Paris thanks to its high-performing site in terms of its Clothing and Footwear Score and its high proportion of premium retailers that align with Gymshark’s offering, according to our Retail Footprint Europe findings. However, this centre has a rather low proportion of a young and affluent shopper demographic compared to Saint-Lazare in Paris, which could see the brand running the risk of not attracting the right shoppers upon opening.

Acorn insights for Centre Commercial Centre Bourse Klepierre

Another defining factor behind Centre Commercial Centre Bourse being a suitable location for a French market expansion is due to the city’s likelihood of having the highest proportion of Affluent Young Families (15%) compared to the other locations. According to Acorn, Centre Commercial Centre Bourse in particular attracts 36% of Gymshark’s core shoppers.

Mobility Data insights for Centre Commercial Centre Bourse Klepierre

Marseille sees a 14pp higher proportion of footfall from Gymshark’s shoppers than expected, driven by the centre attracting significantly more Affluent Singles and Couples than expected, according to Mobility Data findings. Centre Commercial Centre Bourse highly reflects Gymshark’s core shoppers (both in expected and actual footfall) and has strong proportions across the different core shopper groups, while Paris is much more concentrated on a singular Affluent group.

This centre ranks 9th out of over 10,000 retail centres for its Clothing & Footwear Score and has a strong premium retail score, even higher than that of Paris. Marseille also only has one competitor in its centre, meaning the addition of another sportswear brand wouldn’t saturate the market, but shows there is demand for this category in the area.

Les Passages Pasteur Klepierre in Besancon

Retail Footprint Europe insights for Les Passages Pasteur Klepierre

Surprisingly, despite this smaller size of this city and inevitably lesser likelihood of Gymshark opening here, it is actually home to a high level of one of Gymshark’s core shopper demographics, Student Life, as seen in our Retail Footprint Europe data. As with Centre Commercial Centre Bourse in Marseilles, Les Passages Pasteur has a strong Clothing and Footwear offering, a substantial percentage of which are classed as premium retail. While Besancon doesn’t have any direct competitor or complimentary brands, this could be navigated with the help of clever marketing strategies.

Acorn insights for Les Passages Pasteur Klepierre

Les Passages Pasteur has a much younger profile that comprises 31% of Gymshark’s core shoppers, with 12% of its catchment expected to be Student Life, based on findings from Acorn. Unlike Centre Commercial Centre Bourse, Les Passages Pasteur has a high percentage of young and affluent shoppers (even higher than Paris), which would ensure that Gymshark was opening to a shopper demographic most likely to shop with the brand. However, the city has the least affluent profile out of the three.

Mobility Data insights for Les Passages Pasteur Klepierre

Les Passages Pasteur appears to attract the most significant amount of Gymshark’s shoppers in real footfall, with 53% of its actual footfall being from Gymshark core shoppers, as seen in our Mobility Data findings. This is because the centre is significantly over-achieving in attracting Student Life (+21pp versus expectation), showing the centre resonates very well with younger shoppers.

Using the data, which Klepierre centre would best perform in France?

With the aforementioned data to consider, the strongest contender for a successful French market expansion for Gymshark would likely come from Centre Commercial Centre Bourse Klepierre. This is due to its strong representation of Gymshark’s core shoppers, both in expected and actual footfall, as well as the proportions across the different core shopper groups compared to the other two cities and centres being more concentrated on a singular group (e.g. Affluent groups in Paris and Student Life in Besancon). With only one competitor in the Centre Commercial Centre Bourse Klepierre, the addition of another sportswear brand won’t oversaturate the market. Instead, it’d reiterate the demand for this category in the area.

Ready to Find Your Next Market?

With insights from Retail Footprint Europe, pinpoint the best locations for your brand’s growth across Europe.

How Zero Gravity use Acorn to support underrepresented students

Posted on: 11 December 2024

Background

Zero Gravity is a digital platform connecting low-income students in years 12 and 13 with undergraduate mentors for app-based mentoring into highly selective universities. Zero Gravity has previously worked with CACI to enrich their understanding of the backgrounds of thousands of applicants through CACI’s Acorn. This is a geodemographic segmentation of the wider UK population used to assess students’ socio-economic backgrounds based on their postcodes.

Challenge

Matching social and economic needs with educational and career opportunities is one of the major challenges that Zero Gravity has sought to address. Every year, around 50,000 students from socially mobile backgrounds achieve top GCSEs. However, only a third of these students make it to highly selective universities, and even fewer progress into top graduate careers. This discrepancy underscores a prevalent issue: while talent is evenly distributed across socio-economic backgrounds, opportunity is not.

The underrepresentation of socially mobile talent at elite universities and in prestigious careers is not due to a lack of ability. Instead, factors such as the “Network Advantage” (the intangible advantage of having access to a broad professional network identified in Zero Gravity’s Gap Zero report), resource shortages and imposter syndrome often hold these students back. The challenge for Zero Gravity is to bridge this gap, ensuring that talent from low-opportunity backgrounds can access the education and careers they deserve.

Solution

To address this challenge, Zero Gravity developed a sophisticated ‘potential identification system’ to identify and support socially mobile talent. A key component of this algorithm is the integration of contextual student profiling from Acorn. Insights drawn from Acorn provide a granular understanding of the socio-economic environment faced by students at home, enabling Zero Gravity to accurately evaluate their academic potential and their challenges.

By combining this information with Zero Gravity’s own academic performance data, the algorithm indexes top-performing students within the bottom groups of social advantage. This allows Zero Gravity to connect with socially mobile talent at the earliest stages of their educational journey.

By providing rich socio-economic insights, Acorn enhances the precision of Zero Gravity’s talent identification process, ensuring that support is directed towards students who are not only high achieving, but also from disadvantaged backgrounds.

Benefits

In the most recent academic cycle, Zero Gravity has achieved remarkable success by helping over 8,000 students from low-opportunity backgrounds secure places at top-tier universities – all free of charge – due to the social value the organisation drives. Notably, 800 of these students gained admission to Oxford and Cambridge, both of which rank among the top 10 higher education institutions globally. Additionally, Zero Gravity has launched the Zero Gravity Fund, directing nearly £1.5 million towards scholarships for its latest cohort of students.

The success of the current model has enabled Zero Gravity to focus on other opportunities to support disadvantaged students. The university mentoring platform has been such a success that they’ve now developed an innovative new service to help students into the workplace following graduation. Zero Gravity now pairs these young people with industry mentors and provides them with tailored support to access leading universities and, ultimately, successful careers. This enhanced approach not only equips students with the tools and guidance needed to reach their full potential but also contributes to a more diverse and inclusive talent pipeline for employers.

Find out more

Please view the full customer story here. If you want to learn more or have any questions please get in touch with us.

Why France would best suit a Gymshark European market expansion

Posted on: 5 December 2024

A new sportswear retailer emerges on the international stage.

Gymshark, a fast-growing activewear brand, has been rapidly expanding its global reach and brand presence as it ventures into the world of brick and mortar. Having recently opened new stores in the UK (Stratford City), the Middle East (Dubai) and a pop-up concept in New York City, this brand with a prominent social media and predominately online presence is now rapidly infiltrating physical retail.

Despite not yet launching across wider Europe, it’s only a matter of time before these markets will be ventured into via physical pop-ups and stores. Selecting the right locations out of countless options may be a daunting task that comes with the territory, however. So, once the time comes for Gymshark to decide which locations to expand into that will maximise their increasing growing brand recognition and ROI, how should they effectively go about it?

In this two-part blog series, we’ll walk you through a hypothetical European market expansion for Gymshark in France, sharing how the brand can use data to accelerate and enhance their international store network strategies. Three French cities that demonstrate viable market expansion potential based on insights taken from CACI datasets and segmentation tools will be focused on, as well as key takeaways that Gymshark (or brands in a similar position) could consider when it comes to international market expansion.

How France was identified as an optimal location for a Gymshark European expansion

CACI possesses a complete universe of defined retail areas to consider, a detailed understanding of different types of consumers and where they shop. This enables us to guide a brand like Gymshark to maximise success and value from go-to-market strategy and launch through to expanding into broader brand recognition and market share capture. With this in mind, and with Gymshark expanding into physical and new regions, we investigated European markets that might fit their need should they decide to expand into Europe.

With Gymshark already a brand on CACI’s Brand Dimensions, a dataset tracking hundreds of the UK’s most popular and emerging brands to reveal spend, sales and average transaction value insights, key groups in French Acorn could also be identified. Key Acorn groups were identified by using Brand Dimensions data followed by selecting key Acorn groups within French Acorn data, which correlated accordingly. In France alone there are over 10,000 retail areas, each with differing levels of existing premium clothing shops and competitors, types of customers, footfall, population and spend.

By comparing this to the expected view from Retail Footprint Europe, we could identify locations that were currently failing to engage Gymshark’s key shoppers but had the opportunity to. From these collective findings, we were able to conclude the following three French locations that could benefit from the opening of Gymshark: Paris, Marseille and Besancon.

Why Paris would perform well in a Gymshark France expansion

According to our findings, Paris presents the highest performance potential and should be a primary focus for Gymshark. Aside from being the biggest city in France– an obvious bonus for any brand– Paris presents the best shopper demographic, a strong array of existing premium retailers and the ability to attract the relevant demographic groups that would align to Gymshark’s brand identity of being a premium retailer with similar retailers already in the centre.

Retail Footprint Europe enables the use of transactional data across brands to develop an understanding of the typical Gymshark shopper, brand positioning and establishing criteria for the most suitable locations for Gymshark to consider regarding new store openings. Considering these criteria, Paris ranked incredibly high on Clothing and Footwear, with the Haussmann-Opera retail area Klepierre centre ranking among the top three across France.

Why Marseille would perform well in a Gymshark France expansion

Marseille presents itself as another viable option as our findings show it to be the middle ground between high affluence profiles and younger, ‘student life’ populations found in other larger, prominent French cities. The city’s strong clothing and footwear and high proportion of premium retailers also contributes to its performance potential. However, its lower ‘young and affluent’ target demographic runs a potential risk.

Why Besancon would perform well in a Gymshark France expansion

Despite Besancon presenting itself as more of a curveball, the granularity of our Retail Footprint findings demonstrate that in spite of its smaller size and lesser known location, the city is home to a strong clothing and retail offering including premium retailers, a high percentage of young and affluent shoppers and is overall more likely to attract the right shoppers.

Key takeaways that Gymshark can consider for a French market expansion

These aforementioned insights would enable Gymshark to better understand their long-term audience capture of sites through physical retail and experiment with different formats and experiential offerings. Combining Retail Footprint data across Europe with demographic, transactional, brand alignment and footfall data can ultimately be used to shape an evolving store network strategy, and the national view further solidifies an understanding of the entire retail landscape of France. Through these insights, Gymshark would be able to accelerate store openings with greater confidence and success if or when they decide to expand into Europe.

Ready to Find Your Next Market?

With insights from Retail Footprint Europe, pinpoint the best locations for your brand’s growth across Europe.

Stay tuned for next blog in this two-part series, where we’ll assess which Klepierre centres in these high-performing potential French cities could perform well in a Gymshark French market expansion.

The importance of interpretability within machine learning: A case study with Acorn

Posted on: 30 October 2024

In today’s data-driven world, understanding and leveraging data effectively can transform how we approach various challenges. One powerful technique in the realm of data science and machine learning is K-means clustering. This is the algorithm behind Acorn, CACI’s flagship data product which groups together postcodes with similar characteristics into segments. Whilst this process can all be done fairly easily with modern ML techniques, one crucial component is often overlooked: human interpretability.

What is K-means clustering in the context of Acorn?

K-means clustering is an unsupervised machine learning algorithm used to group data points into clusters based on their features. The goal is to minimize the variance within each cluster and maximize the variance between different clusters. To demonstrate how this is done in practice, the following steps are used in the build of Acorn, although the same process will broadly apply to any K-means algorithm:

Initialisation: The number of clusters (K) for initial segments is chosen
Assignment: Every UK postcode is assigned to the nearest cluster segment based on information such as average house price and children per household before the mean distance between postcodes and their segment is calculated
Update: The cluster centroids are repositioned and mean distances for each segment are recalculated
Repeat: The assignment and update steps are repeated until distances are minimised and centroids no longer change significantly

The need for human interpretability

This process looks like it requires very little intervention from a human at any point – and that’s because it doesn’t – in theory. However, in practice as with all unsupervised ML techniques, for Acorn to be of any use as a segmentation tool, information must be scrutinised at every step along the way.

First, the number of clusters must be chosen either randomly or with prior domain knowledge. Acorn has been around for nearly 50 years and the last iteration featured 5 marketable segments, making it a good starting point. However, after stakeholder input from across the business, a conscious choice was made to increase the number of groups to 6 to reflect changes in society since the previous build.

Next, input variables need to be decided on before the clustering process begins. With a wealth of data from the 2021 Census as well as newly available information such as disposable income data, this list of variables needed to be carefully refined for Acorn to be both a mathematically and commercially sound product. As an example, the inclusion of planning extension data was tested as a promising new input to highlight areas undergoing gentrification. However, the results from this didn’t make intuitive sense and so this variable was excluded from the model. Such conscious decisions were also made to ensure that Acorn is fully compliant with the UK Equality Act and exemplify the need for human input before even running a model.

With the input variables decided on, K-means clustering can be applied, but the element of human input does not end here; the segment outputs must be dissected to ensure they are dissimilar from each other and contain an acceptable minimum number of data points. In the context of Acorn, this meant looking at the number of postcodes in a segment and measuring average values for the input driver variables. For example, averages for percentage of houses that are detached and household income were measured for each segment. These figures were found to be highest for groups containing individuals more likely to be in managerial roles, which acted as a useful sense check and allowed such groups to be labelled as more affluent. The number of postcodes within each group also needed to be sufficiently large to allow different marketing strategies to be applied for each segment.

Postcodes were also analysed visually on a 2D scale using a Python package to identify overlaps between segments. The difference between the old and new versions of Acorn can be seen below.

Figure 1: A representation of old (left) and new (right) Acorn postcodes drawn down from a multidimensional space to a 2D visual, with each colour representing an Acorn segment.

The reduced ‘bleed’ of segments into other segments as seen from this visual made it clear to analysts that this newer version of Acorn has much more well defined segments – a result of new data, advanced ML capabilities and of course, stakeholder input.

Finally, and arguably most importantly, the ultimate question must be answered: will the outputs of the model be valuable to the end user? If the answer is not a definite yes, then the process needs to be reviewed and, more often than not, this will involve decisions around the human element of the process rather than consulting the ever-growing list of ML techniques and tweaks. To increase the value of Acorn for clients across sectors including retail, finance, charities and utilities, questions from survey partners were mapped onto Acorn to provide insights such as digital attitudes and channel preference by segment. These questions are updated on an annual basis based on stakeholder feedback to ensure questions are current and relevant to clients.

Conclusion

Ultimately, results need to be useful for individuals or teams and there is currently no way of achieving this without human interpretation and intervention to some degree at every stage of the process. This rings even more true in consumer segmentations, where there is no ground truth or right or wrong to compare to. Lots of packages will allow you to build a model with very little input or intervention, especially with the rise in autoML capabilities, but to build a trustworthy, useful product, humans need to be on hand at every step along the way.

Challenging areas for the grey belt: London and the South West

Posted on: 28 October 2024

In this final article in our grey belt series combining CACI’s housing demand data with VirginLand’s grey belt site identification, we take a deeper dive into two areas where the impact of the grey belt will be less obvious: London and the South West.

This is not to diminish the overall value of the initiative, but to point out that it is not the single answer to the UK’s housing challenges. To be most effective, grey belt reallocation should be considered alongside other mechanisms to accelerate housing delivery such as brownfield, infill, repurposing and urban regeneration.

How will the grey belt initiative affect London?

Home to over 7 million adults, London is by far the most densely populated region in the UK. As a result, demand for housing is particularly acute in the capital and the conversation is dominated by affordability. It’s easy to see why; house prices are 11 times the average household income, and private rent is 37% of income. Although households in London earn 17% more than the national average, these high prices mean that homes are 59% less affordable to buy and 32% less affordable to rent.

In this context, any initiative to increase the overall supply of housing in this region is welcome; particularly if it’s targeted at the more affordable end of the scale. So, what impact will the grey belt have in London?

Although home to 14% of the population, London can house just 0.4% of all grey belt homes – a total of 1,955 dwellings across 31 sites. This is not for want of green belt (22% of the London region, by area, is currently designated as green belt), but for want of suitable locations that could be re-designated. Analysis by VirginLand shows that just 0.2% of the available green belt land is likely to be reallocated grey belt, with much of the London’s green belt holding additional designations like Designated Open Space, Country Park, Woodland or Nature Reserve and Conservation Area and Grade 1-3b agricultural land grades.

The challenge in London is also compounded by the location of the sites relative to movers. Being on the outskirts of the urban sprawl, just 11% of all London home movers live within the catchment of the identified sites; roughly 192,000 individuals. Although more than enough to absorb any new homes delivered, the scale of movers puts into perspective how limited the impact would be on demand; if all sites were built out to their fullest, there would be 98 movers for each home.

While there is little doubt that the 31 identified locations would be additive to the overall housing stock, the question is over how much of an impact these limited sites can have on a particularly strained market. With the population set to grow by another 6.1% in the next 10 years, London will need other initiatives, alongside the grey belt, to accelerate housing delivery in more urban neighbourhoods.

How will the grey belt initiative affect the South West?

Just 4.5% of the South West is designated as green belt, well below the national average. It therefore follows that grey belt opportunities in the South West will be similarly limited, and just 228 potential sites have been identified with the combined potential to deliver 11,868 new homes.

While this is not an insignificant number of homes, it represents just 2.2% of the total grey belt opportunity spread across 9.4% of the population. The location of grey belt sites also limits the initiative’s regional impact, as just 18% of the 1.6 million potential South West movers live within the grey belt catchment, against a national average of 36%.

Although limited in scope for the region as a whole, there are some pockets where the grey belt will be more impactful, and the characteristics of the catchment movers in these locations point to the type of homes that should be prioritised.

With concentrations of sites close to urban populations in the likes of Bristol, house-to-earning ratios and rent-to-earning within the grey belt catchment are higher than those outside of it (7.1 times income and 27.4% of income respectively). High concentrations of Family Renters, Tenant Living and Cash-Strapped Families within this catchment, and relatively large sites averaging 1.7 hectares, suggest a particular opportunity to deliver larger mixed neighbourhoods with high levels of rental product.

As with London, the grey belt initiative has the potential to support some of the housing needs of the South West, but an overarching housing strategy for the region should also be mindful of the 82% of home movers that live outside of the grey belt catchment.

How CACI can help?

To learn more about how you can ensure that your developments are meeting the demands of local movers, contact CACI.

Missed the previous blogs? Find the links to the series so far below:

How grey belt sites will help tackle the UK housing crisis – CACI – Tolga Necar

Grey belt sites: what they are, locations & impact on housing – CACI – Steve Norman and Sam Bedford, Virgin Land

Assessing the impact of the grey belt initiative on a National scale – CACI – Tolga Necar

How will the grey belt initiative affect North West England & Scotland? – CACI – Tolga Necar

How grey belt sites will help tackle the UK housing crisis

Posted on: 30 September 2024

The UK has not been meeting its house building targets for some time. This is not new news, but it is worth reiterating the scale of shortfall. Over the past five years, we have consistently delivered 20% fewer homes than were targeted: a total miss of nearly 300,000 homes (or put another way, an entire year’s target).

Couple this with projected population growth and we can see why house building has made its way up the political agenda. The population is expected to swell by 3.8 million people over the coming 10 years, and naturally, these people will need somewhere to live.

In this blog series, CACI and Virgin Land will uncover key questions around the future of house building targets and how they can be addressed via grey belt sites, including their locations and desirability, whether they create suitable opportunities for inhabitants and how they vary by region.

Where should new house building targets be focused?

Population growth will concentrate around major towns and cities, especially given that 14 of the largest 15 towns and cities have projected growth rates that outstrip the UK average. However, cities are not always where the market has delivered new homes. In fact, eight of those top 15 towns and cities have housing delivery rates that lag behind the national average. Therefore, new housing targets should be geographically directed to the places that people want to live.

Who should be the focus of house building targets?

Housing growth should be targeted at the people that need it most. Left to its own devices, the market has delivered new housing that concentrates around a few demographic groups. Using CACI’s Acorn segmentation to profile new homes delivered in the last five years, we can see clear trends in the data; Tenant Living (young, urban renters) comprise 18% of new homes but just 12% of the population, Semi-Rural Maturity and Mature Success (two affluent, older groups who are likely to be downsizing) collectively account for 20% of new homes but just 13% of the population. Lower affluent, urban families such as Limited Budgets, Hard-Up Households and Cash Strapped Families, however, have received disproportionately little housing development.

This is not to lay blame on housebuilders; the commercial challenges of development in urban environments are clearly contributing factors, however, the impact is one of acute supply challenges in specific demographic groups who are coincidentally the groups most likely to be living in over-occupied housing. To maximise the impact of housebuilding initiatives, the route forward requires a more collaborative approach, which the newly formed MADE Partnership may well deliver.

How will the grey belt make a difference for house building targets?

Central to the Labour government’s housing policy is the rezoning of poor-quality green belt sites into the “grey belt”, effectively opening swathes of previously unavailable land for development. But how influential could this policy change be? CACI and Virgin Land have partnered to uncover the potential impact that opening up the grey belt can have on housing market dynamics.

How CACI can help?

Stay tuned for the next blog in this series, where we’ll dive deeper into grey belts, their locations and their impact on housing. In the meantime, contact CACI to learn more about how you can ensure that your developments are meeting the demands of local movers.