2. Pitney Bowes in Location-
based Marketing
2
•Mailing, shipping/cross border commerce, customer engagement
•Highly precise, global location data stack
•Data quality, visualization and spatial analytics
•Context for audience creation, insights, attribution and ad delivery
•Neutral supplier to these brands - and 1.5M SMB’s:
mailto: rob.Minaglia@pb.com
3. The “where” factor definition
3
BYUSING LOCATION DATA
TO DERIVE INSIGHTS AND BEHAVIORS
AND THEN BUILDING A MARKETING PROGRAM
AROUND THOSE INSIGHTS
A B O U T Y O U R P R O S P E C T S
A N D C U S T O M E R S
GAINING COMPETITIVE ADVANTAGE
4. The “where” factor EQUATION
=
Your Customer’s
Location
The “Where”
Factor
+
Location
Data
5. Mobile Marketing Use Case:
Precise, boundary-based geofencing
and enrichment
5
TARGET or DRIVE
TIME
Apply factors such as:
• Road network & traffic
• Retail trade area
modeling
• Demos & social data
BOUNDARY-BASED
• Store
• Mall
• Category
• Neighborhood
• Zip, city, state
RADIUS-BASED
Has problems of:
• “cross river”
• “false alarm”
6. Mobile Marketing Use Case:
Location Targeting
Source: IAB Location Terminology Guide
Factual & Trade Desk Survey (Dec 2015)
7. Mobile Marketing Use Case:
Audience Creation & Targeting
1. Match lat/long from exchange to a POI / geofence
2. Correlate affinity to POI / GF to consumer behavior
3. Build audience based on location–based behavior
(frequency and dwell time) within geo-fence
(store/mall/lot boundary)
4. Enrich audiences with range of demographic, geo-
demographic, financial vitality and purchasing power, etc.
Mobile Targeting Engine
Insights and behavior
analysis
Personalization engine
Lat / longs from Exchange
8. Enriching Data with
a Location Stack
8
For a given location:
• POI (carries attributes)
• Retail (Business) Footprint poly
• Building Footprint
• Parcel (Lot)
• Isochrone (travel time)
• Demographics, lifestyle attributes,
financial and consumer vitality, etc.
9. Pitney Bowes POI’s
9
• 107M points, 104 countries & territories
• Businesses (fully attributed
• Identification of franchises by brand
• Financial Stress scores (opt)
• Leisure & geographic places
• Powered by D&B and other trusted sources
• Over 19,000 categories, 72 fields
• Most accurate lat/long (global)
• Consistent data structure (global)
• Monthly updates
Segment Creation using POI
10. Lives in urban professional neighborhood in Boulder, CO.
Works at Management Consulting location and spends lunch hours at
the gym. Frequents nightlife hotspots on Wednesday. Enjoys ethnic
foods. Visits mountains on weekends. Air travel 30% of the time.
Audience Creation
11. Branded Geo-fences
Business...Building…Parcel…Drive Time…Neighborhood
• Retail (Business) “Polygon” -
represents the space occupied
by individual businesses.
• Information stored with each
Building Polygon:
• Geometry for polygon and centroid
• Brand code, name, alternates
• Parent/Child Relationships
• Ability to augment attributes
11
12. Boundary portfolio
• Malls and standalone stores
• Airports
• Schools & Colleges
• Hospitals & healthcare
• Auto dealers
• Neighborhoods
• School districts
• World admin & postal
• Golf courses
• Speedways
• Train Stations
• Amusement Parks
• Ski Areas, Casinos
13. 10/24/2016
• Administrative data - Country, district, locality, postcode
• Over 600,000 boundaries, contiguous globally
• Localization - English and local language
World & Admin Boundaries
15. Recommendations
15
Leverage location-services in
your apps
Use clean, accurate data
Enrich with location data stack
and analytics to better
understand / target your
customer
Data is always changing - be
vigilant with your sources and
vendors
16. November 3, 2016 NYC
rob.minaglia@pb.com
914-262-2003
@ROBMINAGLIA