Transcription
Transcript
This customer story has been adapted from a talk given by Joseph Guy and Lara Baitarian, Geospatial Solutions Consultants at CACI, at CARTO's Spatial Data Science Conference.
Introduction: A Global Geospatial Journey
Good afternoon, everyone. We're Joe and Laura, and we're both from CACI. Today we're taking you on a journey around the world to demonstrate how CARTO's cloud-based mapping system works in real time, and how CACI's consumer and market intelligence data can plug straight into it.
We'll do this through three real-world case studies, each from a different market, a different industry, and with different challenges to match. Along the way, we'll meet Lou, a property director for a fashion retailer; Matt, a distribution manager for a soda company; and Paul, a marketing director for an advertising agency.
Paris, France: Retail Expansion for a Premium Fashion Brand
Our first stop is Paris, where we meet Lou, a property director representing a British premium fashion retailer. The brand is looking to enter the European market with no stores at present on the continent — just a handful of stores in the UK — and no real knowledge of the retail landscape across Europe. The only location Lou knows of is the Champs-Élysées, which is very expensive and difficult for a first market entry. Her question: where are the top locations in Paris that might be a good fit for the brand?
Lou already licenses CARTO, so she loads up CACI's Retail Footprint dataset from the Data Observatory, ready to use out of the box. Retail Footprint identifies and scores all 64,000 retail destinations across Europe, based on the quality and quantity of retail provision found in every center. That same attractiveness score feeds a gravity model that predicts catchments for every destination, combining retail strength with distance traveled and consumer demand — giving Lou visibility into both market supply and consumer demand.
Using the country and city filters, Lou narrows straight down to Paris and its surrounding region — 443 retail destinations. Filtering by Retail Footprint Score cuts that to the 123 largest locations. Since raw size doesn't tell her which locations fit a luxury fashion brand, she adds a luxury filter to surface only destinations with synergy retailers and luxury brands nearby. That leaves just a handful of locations — including Haussmann Opera and Victor Hugo alongside the Champs-Élysées she already knew — which she ranks and exports to share with the business.
Manila, Philippines: Optimizing FMCG Field Sales Routes
Next, we fly to Manila to meet Matt, a distribution manager at a soda brand that wants to rapidly expand distribution across the Philippines by selling into more outlets. On paper that sounds simple, but in reality there are hundreds of thousands of potential outlets — convenience stores, cinemas, restaurants, and more — and nowhere near enough field sales reps or time to visit them all. There's no off-the-shelf dataset that tells you which outlets will deliver the highest return, so this is where CACI builds a bespoke demand model, bringing Matt's internal sales data together with CACI's spatial datasets in a single environment.
At a national level the scale is huge: over 200,000 potential outlets across the Philippines where soda could be sold. The first filter is purely spatial — Matt filters to his own sales territory, which instantly reduces the universe to 8,700 outlets. Still too many to visit, so CACI layers in bespoke spatial modeling: a demand layer built at H3 hex level, combining drivers like footfall, population, leisure, and tourism to model demand consistently across the country.
Filtering that demand layer down to the highest-opportunity areas takes Matt from 8,700 outlets to 2,000 with the highest expected return. Using postcode-level geographies to find the highest concentration of high-value outlets narrows things further into tight clusters where field reps can cover multiple high-value outlets within minimal travel time. Finally, Matt draws a bespoke polygon directly in CARTO around the cluster he wants his team to focus on — bringing the original universe of over 200,000 outlets down to 661 targeted ones, ready to deploy to dozens of field sales reps.
Riyadh, Saudi Arabia: Audience Segmentation for Mall Advertising
Our final stop is Riyadh, where we meet Paul, who works at a media and advertising agency selling digital media placements around shopping malls. Paul wants to increase engagement by tailoring campaigns to local audiences, but every mall is currently treated the same — same visuals, same messaging — even though mall audiences are completely different. His question: how should advertising and messaging differ by mall catchment to maximize impact?
Tailoring messaging properly requires a micro-level segmentation of Saudi demographics. In markets like Saudi Arabia, official figures on population and affluence are only available at a regional level — too coarse for micro-level analysis. CACI disaggregates that data into H3 resolution-9 hexagons using techniques like satellite imagery, creating the granularity needed to differentiate between micro-locations. This is the building block behind CACI's flagship Acorn dataset, which segments the Saudi population into five categories, 11 groups, and 23 types based on life stage and affluence, further enriched with survey data covering behavioral, attitudinal, and lifestyle insights.
Paul licenses both Retail Footprint KSA, to identify the catchment of each mall, and Acorn, to understand who lives within those catchments. Loading Retail Footprint KSA in CARTO, he filters to Al Nakheel Mall in Riyadh and visualizes the spread of its catchment. Layering Acorn segmentation on top quantifies the distribution of visitor segments — revealing that almost 50% of visitors to the mall are “Motivated Metropolitans”: urban residents, often expats or highly mobile professionals, married with young children or planning families, and mid-to-upper income with lifestyle aspirations. Instead of advertising discounts, Paul can now advertise lifestyle upgrades — fitness, fashion, dining, and experiences — a message built around modern city living for an audience with limited time.
Conclusion: Understanding People Through Data
All three of these market challenges were addressed through CARTO's interactive mapping system paired with CACI's data and consultancy work. Lou can now make confident, data-backed decisions to justify investment, with room to layer in her own internal and external data as she expands further. Matt no longer relies on gut feel — instead of sending his sales team to hundreds of thousands of locations, he can direct them to a specific area with a high concentration of high-opportunity outlets, resulting in fewer wasted journeys, higher conversion rates, and measurable ROI. His next step is integrating directly with cloud data platforms for automated outlet refreshes and a direct connection to field force automation tools. Paul can now have more nuanced conversations with brands about relevant, targeted advertising.
What CACI and CARTO help clients answer are fundamentally human questions: who their customers are, where they live, where they go, and what they do when they get there. Our strength isn't just in the data — it's understanding people through data. Through CARTO's Data Observatory, flagship CACI datasets like Acorn, Retail Footprint, and Local Footprint are all available to license with no complex onboarding.
