by Ambient ArrayRetail Site Selection Strategy
Know which location will make money before you build or sign.
Tupll builds a machine-learning revenue model on your brand’s own revenue and location history, then scores every candidate site by predicted performance. Defensible enough for your CFO. Specific enough to act on.
Retail · multi-location brands · built on your locations and revenue, not generic demographics
Revenue Prediction Score
Candidate shortlist
Predicted top-decile performance vs. your portfolio
Strong, above your portfolio median
Below median, cannibalization risk flagged
15+ yrs
building site-selection models
2,342
locations evaluated
124
verified builds & leases from our reports
A single wrong location can cost millions, and a build or a lease locks the mistake in for years.
- Underperforming stores drag the whole portfolio and stall the next round of expansion.
- New sites quietly cannibalize the ones you already own.
- Gut-feel picks and broker-sourced comps don't survive a CFO's scrutiny.
- Generic demographic tools describe a place; they don't predict your revenue there.
How the model works
Your revenue and location history, turned into a forecast you can defend.
Tupll is a machine-learning evaluation system that combines traditional statistics with multiple models to predict how a location will perform, trained on your own numbers, not off-the-shelf averages.
Start with your numbers
We train on your existing locations and revenue. The model learns what actually drives sales for your brand, the patterns a generic index can't see.
Fuse the signals rivals can't
Demographics, business activity, competitive context, consumer behavior, and local economic patterns fused into one multi-signal view of market viability.
Score every candidate site
Each location comes back with a revenue prediction score and the reasoning exposed, so you compare sites on one number you can put in front of the board.
Almost no work on your end
You hand us two columns. We do the analysis.
No IT project. No data team. No months of prep. The whole ask is your location addresses and one to three years of revenue by site. From there, the modeling, evaluation, and reporting are 100% done for you.
To find out
2 minutes
A quick look at what you already have tells us whether your history can predict your next location.
To hand off
15 minutes
If you are a fit, pulling the file together takes about fifteen minutes. Two columns, address and revenue. Most teams already have it open.
Your analytics effort
0%
Data cleaning, modeling, scoring, and the written report are all on us. You still tour the sites, work with your broker, and negotiate the deal; the analytics are fully done for you.
Why it holds up
Built to survive the room where the money gets approved.
Glass-box, not black-box
Every score traces back to inputs you can inspect. Open the hood for your CFO instead of asking them to trust a mystery number.
Built on your own revenue and locations
A prediction only exists once the model meets your locations and sales. That's what makes it yours, not a market average dressed up as a forecast.
No brokerage ties
We don't earn on the transaction and we don't sell the space. Our only incentive is calling the location correctly.
Proven across 2,342 locations
Fifteen-plus years of models behind real builds and leases: a repeatable method, not a one-off study.
Evidence, from a real engagement
Two sites. Same city. The one with 6× fewer households wins.
A metal buildings manufacturer was weighing two candidate sites in the same metro, Kansas City. By the numbers anyone can eyeball, it wasn’t close.
Kansas City metro · 2026
Site A
Site B
What anyone can eyeball
Site A looks like the obvious winner. More people, more businesses, more of everything. Most site-selection tools, and most gut instincts, would plant the flag there.
Why? Because raw population isn’t what drives this business. The model weighs who is actually nearby: the mix of homes, industries, and buying behavior that this manufacturer’s best-performing locations share. Site B had far fewer people, but exactly the right ones.
Count heads and you pick Site A. Understand the market and you pick Site B.
That gap is the difference between a good location and an expensive mistake, and it’s invisible if you only look at the obvious numbers.
Actual Tupll engagement, 2026. Figures rounded; brand withheld for confidentiality.
What you get
A decision-ready shortlist, not another dashboard.
- Ranked candidate sites, each with a revenue prediction score against your portfolio.
- The model logic and signal weights, documented, so the recommendation is defensible, not a hunch.
- Cannibalization and coverage flags where a new site would eat into your existing footprint.
- A clear next-site call your team and your CFO can act on.
Complimentary bonus
A Location Brief for top-scoring sites
For your highest-scoring locations, we include a close-in read of what the place is actually like: who’s there by day and by night, how many jobs sit nearby, what businesses cluster there, and whether people arrive on foot or by car. Street-level photos included, public data cited, our interpretation labeled as interpretation.
It won’t tell you what you’d make there. That’s the model’s job. It tells you what you’re walking into.
See three sample briefs →Straightforward pricing
Pick the model that matches where your brand is.
Fixed fees, no retainers, no transaction cut. You keep your tools; Tupll adds the prediction layer.
Most common
New Model Development
For brands with existing locations
$12,999
one-time
A custom machine-learning model trained on your revenue history, plus a full evaluation of your candidate sites.
Start hereFirst store
First Location Model
For brands building or leasing their first location
$7,999
one-time
Our full statistical and GIS methodology for brands without sales history yet, the groundwork before supervised ML applies.
Get startedThen, whichever model you start with: ongoing Site Evaluations run $120 per location (per batch, minimum 9 locations) so you can score new candidate sites against your model as you keep expanding.
Straight answers
The questions directors of real estate ask us.
Do you need our sales data?+
Yes, that's the whole point. The model is trained on your own revenue and location history, which is what turns a generic market read into a prediction that's specific to your brand. Your data stays yours; we build the model around it.
This sounds like a data project.+
It isn't. We need two columns: your location addresses and revenue by site for the past one to three years. Most teams already have it in a spreadsheet. Pulling it together takes about fifteen minutes, and the modeling is 100% on us.
How is this different from Placer, Esri, or Buxton?+
Those hand you data and dashboards. Tupll hands you a prediction built on your numbers, with the reasoning exposed. It's a defensible revenue score for each site, not another layer of maps to interpret yourself.
Are you a broker?+
No. Tupll has no brokerage ties, earns nothing on the transaction, and doesn't sell the space. The only thing we're optimizing for is calling the location correctly.
What is the Location Brief you include?+
A complimentary close-in read of what a top-scoring location is actually like: area character, who's there day and night, nearby jobs, the commercial mix, and how people get around. It adds real-world context for stakeholders. It is a bonus. It does not replace, and is not the same as, the revenue evaluation.
What if we're opening our very first location?+
Then there's no sales history to train on yet, so we apply the First Location Model: our full statistical and GIS methodology to find where your first store is most likely to succeed.
Model Readiness Check
Find out in two minutes if your data can predict your next location.
No IT project. No data team. No cost to find out. Tell us roughly what you have, your location addresses and how much revenue history you can pull, and we’ll tell you plainly whether it supports a predictive model.
Don’t have historical revenue by location yet? There’s still a path: a secondary model that costs less and beats guesswork by a wide margin. Either way, you leave with a direction.
Two minutes to find out if you’re ready. Fifteen minutes to hand over the data once you are. That’s the whole barrier to entry.