Upselling a Promotional Product Using Customer Purchase Information

1
Upselling a Promotional Product Using Customer
Purchase Information

• Serhan Ziya
• Department of Statistics and Operations Research
• University of North Carolina at Chapel Hill
• (joint work with)
• Göker Aydin
• Department of Industrial and Operations
  Engineering
• University of Michigan Ann Arbor

2
Outline

• What is upselling? Who is doing it?
• Problem description
• Dynamic prices and discounts
• Static prices and dynamic discounts
• Static prices and static discounts
• Results
• Conclusion

3
Upselling

• Do you want fries with that?
• Any chips and drinks?
• Would you like a tie that goes with your new
  shirt?

4
Upselling - Definition
Soliciting the purchase of goods or services
following an initial transaction during a single
telephone call Federal Trade Commission

• Soliciting the purchase of goods or services
  immediately after an initial transaction.

5
Upselling Who is doing it?

• Catalog Retailers Lillian Vernon, DM Management,
  Oriental Trading Co., Corona Cigars, Ross-Simons,
  etc.
• Online retailers Amazon.com, Bn.com,
  Walmart.com, Buy.com, etc.
• Traditional retailers Ann Taylor, Banana
  Republic, Gap, Old Navy, etc.

6
Upselling Why do it?

• Upselling relational items
• If you like Die Hard, you will also like
  Lethal Weapon.
• If you buy a digital camera, you will need a
  battery charger.

7
Upselling Why do it?

• Upselling to liquidate excess inventory
• Overstock items
• Slow moving items
• Seasonal products
• 42 of catalogers (63 of apparel catalogers)
  use upselling to reduce excess merchandise,
  Operations BENCHMARK99, Catalog Age.
• Lillian Vernon, DM Management, Chinaberry, etc.

8
Key questions

• Which product to upsell?
• How to price the product?
• What discount to offer, if any?
• may depend on
• customer purchase history
• customer demographics
• inventory levels

9
Research questions

• Pricing and discounts
• How should prices be set?
• When to offer a discount to whom?
• Benefits of upselling
• Benefits of using customer purchase information
• Interaction with dynamic pricing

10
Literature review

• Dynamic pricing of inventories
• Gallego and van Ryzin(1994), Bitran and
  Mondschein (1997), Elmaghraby, Gulcu, and
  Keskinocak (2003), Aviv and Pazgal (2005a,
  2005b), Zhang and Cooper (2005), Maglaras and
  Meissner (2005)
• Elmaghraby and Keskinocak(2003), Bitran and
  Caldentey(2003)
• Bundling
• Hanson and Martin (1990), Ernst and Kouvelis
  (1999)
• Gurler, Bulut, and Sen (2005)
• Cross-selling/upselling
• Armony and Gurvich (2005)
• Netessine, Savin, and Xiao (2004)

11
Two types of products
Promotional product
Regular products
Upsell offer
Demand
No offer
12
Two types of products
Promotional product
Regular products
Upsell offer
Demand
No offer
13
Selling season
Beginning inventory Y
0
1
2
3
4
T
T-5
t
t-1
T-4
T-3
T-2
T-1

Length of selling season
14
Events in each period
Purchase
p(y,t)
?p
No purchase
p(y,t) d(y,t)
Purchase
r
Purchase
?R
No purchase
No purchase
1 - ?p - ?R
Nothing happens
15
Customer population
Two segments for each product TARGET and
NON-TARGET
a
b
c
Target segment of promotional
Target segment of regular
d
Whole customer population
16
Customer population
Reservation price distributions
Target segment
qR1
F1()
?
Assume that F1 ?hr F2
qR2
Non-target segment
F2()
Target segment
qp1
G1()
?
Assume that G1 ?hr G2
qp2
Non-target segment
G2()
17
Assumptions onreservation price distributions
Assumption F1 hr F2 , G1 hr G2
Hazard rate ordering
F1 hr F2 if
implies ordering of price elasticity functions
Assumption Revenue function for each segment is
quasi-concave
Holds under IGFR, concavity, etc.
Weibull, Normal, Uniform, etc.
IGFR means increasing price elasticity
18
Relationship between the two products
?11
Target
Target
?12
?21
Non-Target
Non-Target
?22
If ?11 ?22 1, we say products are similar. If
?11 ?22 ?11 ?22 1 implies positively correlated
reservation prices. ?11 ?22 negatively correlated reservation prices.
19
Using customer purchase information
?
?
?
Upsell offer
random customer
purchased
Update segment probabilities
20
Policies to be considered
Price
Dynamic
Static
Dynamic
?
?
Discount level
?
?
Static
Online and traditional retailers
Online, traditional and Catalog retailers
21
DP formulation
Unconditional prob. of purchasing promotional
product
Conditional prob. of purchasing promotional
product
Prob. of purchasing regular product
22
Structure of optimal discount policy
When should an upsell offer include a discount?
Products are dissimilar (?11 ?22 OFFER DISCOUNT
Products are similar (?11 ?22 1)
DO NOT OFFER DISCOUNT
regardless of inventory level and time
23
Structure of optimal discount policy Multiple
regular products
Upsell offer
Demand
No offer
When should an upsell offer include a discount?
Products are dissimilar (?j11 ?j22 OFFER DISCOUNT
Products are similar (?j11 ?j22 1)
DEPENDS ON INV. TIME
24
Prices, inventory level, and time-to-go

• Optimal advertised prices and optimal discounted
  upsell prices are decreasing in the inventory
  level and increasing in time-to-go

25
Prices, inventory level, and time-to-go

• Given the inventory level, the size of the
  optimal discount is non-monotonic in time-to-go.

26
Static price and dynamic discounts
Set p at the beginning of the season.
0
1
2
3
4
T
T-5
t
t-1
T-4
T-3
T-2
T-1

p
r
p d(y,t)
27
Static price and dynamic discounts - Optimal
discount policy
For any given price p, the optimal discount
policy is of switching-curve type in the
inventory level and time.
Similarly for static price and discount.
28
Numerical study

• Reservation price distributions
• Four different combinations of Weibull
  distributions
• T 20
• qR1 ? 0.7, 0.5, 0.3
• ?11 ? 0, 0.3, 0.5, 0.7, 1.0
• ?22 ? 0, 0.3, 0.5, 0.7, 1.0
• ?R ?P ? 0.7, 0.5, 0.3
• ?R / (?R ?P) ? 0.7, 0.5, 0.3
• y ? high, medium, low
• r ? high, medium, low
• Overall 24300 runs with different parameter
  values

29
Benefits from upselling

• Dynamic pricing does not diminish or amplify
  benefits from upselling.
• Largest benefits when
• There is high demand for a cheap regular product
• The initial inventory for the promotional product
  is high.
• The target segment for the regular product is
  large and the promotional product is similar to
  the regular product.
• It is not always best to pair two similar
  products for upsell offers.

30
Benefits of usingcustomer purchase information

• Dynamic prices and discounts
• 4-5 improv. 10
• 3-4 improv. 5
• 2-3 improv. 41
• 1-2 improv. 154
• Static price and discount
• 4-5 improv. 6
• 3-4 improv. 7
• 2-3 improv. 40
• 1-2 improv. 144

• Static price and dynamic discounts
• 9-10 improv. 1
• 8-9 improv. 1
• 7-8 improv. 2
• 6-7 improv. 4
• 5-6 improv. 5
• 4-5 improv. 23
• 3-4 improv. 71
• 2-3 improv. 314
• 1-2 improv. 2401

Purchase information is most beneficial if prices
are static discounts are dynamic
31
When is using purchase information most/least
useful?

• Largest improvements when
• products are very dissimilar (high negative
  correlation)
• price of the regular product is high
• demand for the regular product is high
• Smallest improvements when
• products are neither very similar nor very
  dissimilar
• demand for the regular product is low

32
Future research

• Which product to upsell?
• When there are multiple promotional products,
  which ones to offer to a customer?

33
Paper information
Upselling a promotional product using customer
purchase information
available at
www.unc.edu/ziya
email ziya_at_unc.edu