CASE STUDIES

Partnered with the Town Manager and their parking vendor to move beyond surface-level metrics. 

We ditched the canned dashboards and ran real price sensitivity analyses to understand what visitors were actually willing to pay — and when. We looked at historical patterns, blended in weather, time-of-day effects, and even special event overlays to fine-tune pricing recommendations. The result? A pricing model that feels fair to locals, profitable to the town, and adaptable in real time. 

 Worked with external marketing partners to move past vanity metrics and into ROI.
Impressions and click-thru rates are cute — but we went deeper. By overlaying ZIP-level booking and retail data, we surgically cut out underperforming audiences and reallocated spend to regions that actually convert. We didn’t just report performance — we fixed it. Every marketing dollar now works harder because it’s backed by real outcomes, not just pretty charts.

Helped the Promotions and Events Committee shift from intuition-based scheduling to laser-targeted event planning.
We blended data from past events, retail traffic, weather patterns, parking demand, and marketing results to identify the sweet spot for future events — right down to the ideal date and demographic. No more guessing who might show up or when. Now, events are planned for the right audience at the right time — and it shows in attendance, revenue, and local buzz. 

 Placer.ai and similar tools only scratch the surface — we go deeper.
You can look at dwell times and heat maps all day, but what do they mean? We dive into the raw data behind the pretty pictures and blend it with retail, weather, booking trends, and zip-code-level intelligence to complete the story. Then we make actual recommendations — what to promote, when, and to whom — instead of just admiring the traffic. 

 Built collaborative forecasting tools with property managers to help local businesses prep for demand.
By combining reservation data (when people booked, where they’re from, how many are coming) with external data like school calendars, weather, and retail behavior, we built rolling forecasts for local shops and restaurants. That means better inventory planning, smarter staffing, and more efficient food prep — because a last-minute Saturday crowd shouldn’t be a surprise. 

 Helped local retailers align stock levels with actual foot traffic and visitor profiles.
Using forecasted visitor trends, point-of-sale data, and weather patterns, we identified inventory mismatches — like beachwear peaking after people had already gone home. One boutique reduced end-of-season markdowns by 27%, simply by reordering based on forecasted check-in dates and demographics. Inventory moves faster when it aligns with who’s actually in town. 

Identified hidden buying patterns that led to a 12% lift in basket size.
We used transaction-level data to uncover which items tend to sell together, then recommend pricing strategies and bundled promotions around those insights. One shop saw wine + cheese combos drive a $4.23 increase in average ticket after just three weeks. It’s not rocket science — it’s just using data to give customers what they’re already trying to buy and maximizing your margins around it. 

Built simple, reliable models to forecast busy days and right-size staffing.
By combining rental check-ins, event calendars, weather, and parking demand, we gave businesses a two-week lookahead on when foot traffic would spike. One restaurant cut labor costs by 18% in slow weeks and improved coverage on peak days — fewer walkouts, happier staff, and smoother operations all around. 

 Added demographic profiles to retail data to show who’s buying — and who’s not.
We matched billing ZIPs from POS systems with census and booking data to identify untapped audiences. Turns out, 41% of weekend buyers came from the same 6 ZIPs — and were never targeted in previous campaigns. After adjusting local ads to focus on those areas, retailers reported a 19% bump in same-week sales.