DFM — Footfall Impact
DFM (The Crowd Predictor)
DFM predicts not just how many people will be in a place, but who they will be, when they will be there, and what they will likely be doing.
How It Works
Traditional footfall planning deals in blunt, daily averages: "This plaza gets 20,000 visitors a day." This is useless for intelligent advertising. The reality is that a city breathes. Its rhythms change by the hour, the day, the weather, and the season. The "crowd" at 8 AM is a fundamentally different entity, with different demographics, intentions, and cognitive states, than the crowd at 8 PM.
Dynamic Footfall Modeling (DFM) uses historical data, real-time sensors, weather feeds, and event calendars to build a dynamic, predictive model of human flow. It understands that a rainy Thursday morning after a public holiday creates a completely different audience profile than a sunny Saturday afternoon before a major concert. DFM turns a static media plan into a dynamic, living schedule.
Real-Life Example
Consider a digital screen on a popular downtown shopping street. A brand manager using traditional planning might buy "prime time" assuming it's always busy. DFM reveals the nuanced truth:
7-9 AM: Delivery workers, early gym-goers. Low dwell time, low commercial intent.
10 AM-12 PM: Retirees, tourists. Moderate pace, exploratory mindset.
1-3 PM: Office workers on lunch breaks. Purposeful, time-pressed, looking for quick eats.
4-6 PM: Professionals heading home, students. Mixed mindset, some open to browsing.
7-9 PM: Social groups, couples on dates. Leisure mindset, highest dwell time and receptivity to entertainment/experiential messaging.
DFM allows the advertising to speak appropriately to each of these different "cities" that occupy the same space throughout the day.
Example Breakdown
Let's predict the audience for our shopping street screen next Saturday at 2 PM.
Base Pattern: Historical data shows an average of 500 people per hour pass this spot on a typical Saturday afternoon.
Time Factor: 2 PM is a known peak shopping time. Multiplier = 1.4.
Weather Factor: The forecast predicts sunny and pleasant weather, encouraging more people to go out. Multiplier = 1.3.
Event Factor: There's a street food festival two blocks away, drawing extra crowds. Multiplier = 1.2.
Calculation:
500 × 1.4 × 1.3 × 1.2 = 500 × 2.184 = 1,092 people/hour
Interpretation
Planning for the average of 500 people would have been a 54% underestimation. DFM predicts 1,092 real, actual people. Furthermore, the model can infer that this crowd, drawn by a food festival, is likely in a festive, exploratory, and hungry mood. This intelligence allows the system to automatically serve ads for nearby casual eateries, dessert shops, or refreshing drinks, rather than a generic brand film. DFM ensures the message meets the moment, not just the location.