Tools for Tracking Your

Customers and Measuring

Shopper Engagement
Raymond R. Burke and Alex Leykin
Kelley School of Business
Indiana University
November 2, 2007

Copyright 2007 Indiana University

How Do We Measure & Manage

Shoppability?
Survey Research
Measure consumer perceptions of the shopping
experience and diagnose problems with store,
department, and category shoppability

Observational Research
Track shopper behavior, identify points of
engagement and purchase obstacles, and
then manipulate and measure response
Copyright 2007 Indiana University

Key Customer Touchpoints

Store Entrance and Window Displays

Lead Fixtures and Merchandising
End-of-Aisle Displays
High Volume / Margin Departments
Customer Service Desk
Checkout

Copyright 2007 Indiana University

Observational Measures
Engagement:

Examination of signs, displays, circulars

Category dwell time
Salesperson contact
Product/package/display interaction

Conversion:

Aisle penetration
Purchase conversion rate
Product price/margin (absence of incentive)
Shopping basket size
Returns

Copyright 2007 Indiana University

Benefits of Computer Tracking

Breadth of Coverage:

Census of customers/items (e.g., for security, inventory)

24/7 tracking (time of day/crowding analysis)
Potential to track entire store (path analysis)
Scalable to multiple stores (benchmarking, experiments)

Speed:
Real time data (e.g., for staffing, replenishment)

Data Integration:
Link path, penetration, conversion data to consumer
demographics, shopping basket, purchase history
Copyright 2007 Indiana University

Computer Tracking Solutions:

Tracking Carts with Infrared/RFID Sensors

Copyright 2007 Indiana University

Computer Tracking Solutions:

Tracking Carts with Infrared/RFID Sensors
Limitations
Only applicable in retail stores using carts and/or
baskets (e.g., grocery, mass retail)
Only tracks customers who choose to use
carts/baskets, losing fill-in shoppers
Unable to track customers who leave carts. May
overestimate perimeter traffic, dwell times
No measure of gaze direction or package
interaction
No information on group size or behavior

Copyright 2007 Indiana University

Computer Tracking Solutions:

Tracking Shoppers with Video Cameras

Copyright 2005
2007 Burke
Indianaand
University
Sharma

Computer Tracking Solutions:

Tracking Shoppers with Video Cameras

Copyright 2005
2007 Burke
Indianaand
University
Sharma

Automatic Behavior Analysis

Copyright 2005
2007 Burke
Indianaand
University
Sharma

Store Entry and Traffic Patterns

Incoming Store Traffic

Initial Direction Distribution

Total Store Traffic

950

Average Store Traffic by Hour of Day

140

Aisle1
13%

900
850
800

Checkout Area
30%

750
700

Aisle2
6%

600

100
80

Aisle3
7%

650

120

550

60
40
20
10pm-11pm

8pm-9pm

9pm-10pm

7pm-8pm

6pm-7pm

5pm-6pm

4pm-5pm

3pm-4pm

2pm-3pm

1pm-2pm

12pm-1pm

11am-12pm

10am-11am

8am-9am

9am-10am

7am-8am

6am-7am

5am-6am

4am-5am

3am-4am

2am-3am

MainAisle
44%

1am-2am

4/1/2005

3/30/2005

3/28/2005

0
12am-1am

Collection Period 3/3/05 - 4/2/05

3/26/2005

3/24/2005

3/22/2005

3/20/2005

3/18/2005

3/16/2005

3/14/2005

3/12/2005

3/8/2005

3/10/2005

3/6/2005

3/4/2005

500

Copyright 2005
2007 Burke
Indianaand
University
Sharma

Aisle Penetration

Pre Period

Post Period
Copyright 2005
2007 Burke
Indianaand
University
Sharma

Category Dwell Time

Copyright 2005
2007 Burke
Indianaand
University
Sharma

Computer Tracking Solutions:

Tracking Shoppers with Video Cameras
Limitations
Cameras have a limited field of view and work best in
smaller stores (e.g., specialty retail stores, drug
stores, convenience stores, banks)
Tracking entire customer path requires multiple
cameras with overlapping views
Occlusions (e.g., shelving, signage, other customers)
and shadows can interfere with tracking
Difficult to distinguish between employees and
customers
Copyright 2007 Indiana University

Tracking - System Overview

The tracking system works in three steps:

Detection

Tracking

Activity Recognition

Copyright 2007 Indiana University

Tracking Background Subtraction

Each background pixel is represented as a stack
of values
To decide if a new pixel is a part of the
background, a lookup is performed through the
full stack and if no matches are found the pixel is
considered to be a foreground pixel
codebook

codeword

Copyright 2007 Indiana University

Tracking - Blobs
The result of background
subtraction is a binary
bitmap
Foreground regions
corresponding to moving
people are represented
as blobs (in red)

Copyright 2007 Indiana University

Tracking Camera Model

Parallel lines and the heights of objects in the scene are used
to determine the cameras location and field-of-view
The camera model permits the translation from world
coordinates to image coordinates and back

Copyright 2007 Indiana University

Tracking Detecting Heads

The head is usually the least occluded part of the human body.
Therefore, to reliably detect multiple people within one blob, we
look at their head locations:
1. Estimate the height of each vertical line of the blob
2. Find a number of local maxima in the resulting histogram

Copyright 2007 Indiana University

Tracking Detecting Heads (cont.)

Copyright 2007 Indiana University

Tracking Probabilistic Modeling

The system estimates the following parameters
for each person:
body width and height (cm)
current location on the ground (X and Y)
color histogram

At each instant in time, the tracking system attempts to find

the model of the scene which:

Best fits the current observation (whats in the image)

Is consistent with the model from the last observation

Copyright 2007 Indiana University

Tracking Sampling Dynamics

To construct a new model, we randomly apply a number of
jump-diffuse mutations to the old model
Then the likelihood of the new model is evaluated
Jump Steps

Diffuse Steps

Change height
Add body
Delete body
Move

Change width
Change position
Switch ID

Copyright 2007 Indiana University

Tracking - Results

Copyright 2007 Indiana University

Tracking Example: Camera View

Copyright 2007 Indiana University

Tracking Example: Store View

Copyright 2007 Indiana University

Insights from Observational Research

Store Entry
Shoppers take time and space to adjust to
the in-store environment
Identify recognition points where
consumers slow down and start observing
Provide answers and solutions, including
signs, circulars, baskets, cash/wrap

Copyright 2007 Indiana University

Insights (cont.)
Traffic Flow
Identify dominant pathways through the store
Angle and direction of approach determines
best position/orientation for signs and displays.
The greater the speed of approach, the
shorter the message
Facilitate incoming access to destination
products, outgoing access to impulse items

Copyright 2007 Indiana University

Insights (cont.)
Penetration and Purchase Conversion
Low penetration categories may require
additional navigational aids, new product
displays, merchandising, and/or changes in
store layout to improve traffic flow
Categories with low purchase conversion
rates may indicate weaknesses in product
assortment, pricing, or presentation

Copyright 2007 Indiana University

Mens

Womens

Store Penetration
& Purchase
Conversion

Copyright 2007 Indiana University

The Original Mens Section

Copyright 2007 Indiana University

Mens Style Center - Outfits

Copyright 2007 Indiana University

Mens Style Center Product

Table

Copyright 2007 Indiana University

Making It Easier for Men to Shop

Enhanced product display drives category
traffic and sales:
85% increase in product fixture
interaction
44% increase in unit sales
38% increase in dollar sales

Copyright 2007 Indiana University

Insights (cont.)
Crowding
Provide sufficient aisle width for displays,
carts, strollers, crowds
Reposition fixtures or product displays to
eliminate bottlenecks
Avoid crowding in categories requiring
extended decision times

Copyright 2007 Indiana University

Insights (cont.)
Checkout
Measure queue lengths and waiting time to
flag problems with line management,
checkout process and customer service
Reduce waiting time by opening more lines,
eliminating price checks, speeding up credit
authorization, and employing self checkout

Copyright 2007 Indiana University

2005
Copyright 2007Source:
IndianaBurke
University

2005
Copyright 2007Source:
IndianaBurke
University

Challenges

Creating the Digital Store

Employee Identification
Tracking Customer Groups
Measuring Focus of Attention
Recognizing Complex Behavior

Copyright 2007 Indiana University

Summary of Tracking Insights

1. Track customer path
2. Measure category
penetration, dwell time,
and conversion
3. Measure line queues
and crowding
4. Cluster shoppers based
on path similarity

Evaluate store layout and

product adjacencies
Manage in-store
communication, product
assortment, and pricing
Manage service levels,
staffing
Behavioral segmentation

Copyright 2007 Indiana University

Resources
Questions?

rayburke@indiana.edu
Indiana Universitys Kelley School of Business

www.kelley.iu.edu

Copyright 2007 Indiana University