How Spending is Affected by
Discount Voucher Redemptions:
An Approach to Explain Customer Value Through Direct Marketing Efforts
Fyne van Breevoort
Master Thesis Msc Marketing Intelligence & Marketing Management
Introduction (personal note)
› Internship: customer value & email effectiveness › Email advertising effective?
§ Spam
§ Unnoticed
Introduction (2)
› Alternative approach to traditional customer-employee communication
› Competitive online shopping environment › Discounts everywhere..
Research Questions
› To what extent does the use of discount
communications by email influence the purchase intentions of individual consumers?
› And does the use of these communications alter
the amount spent by individual customers?
› Loyalty
› Relationship length
Relevance
› Adds insights to the customer value marketing interface by focusing not only on purchase
probability but also explicitly on spending amounts › Provides executives insights into how customers
respond to the discounts proposed in emails: evidence of ineffectiveness
Data
› Global hot beverages retailer for in-home use › 33-month period
Methodology(1)
Tobit Type II, Maximum Likelihood estimation; how the explanatory variables affect
› 1. the purchase incidence by customer i in time t › 2. the amount spent by customer i in time t
!
!= !!
1!!!!!!!!!"!!!!
0!!!!!!!!!!!"!!
!∗> 0
!∗
≤ 0!
!
!=
!
!∗!!!!!!!!!"!!!!
!> 0
Results (1)
› First purchase discount: increases z value › Frequency of previous discounts: increases z value › Opened Email 2: decreases z value › Holiday promotion: decreases z value
Table 4 – Discount Purchase Regression
Estimate p-value Intercept 0.4570598 < 2e-16 *** Age -0.0002398 0.38778 Gender -0.0084629 0.28630 Household size -0.0006778 0.81019
First Discount 0.1974994 < 2e-16 ***
Frequency Discount 0.1916710 < 2e-16 ***
Relationship length 0.0004927 0.00484 ** Email 1 -0.0214102 < 2e-16 *** Email 2 -0.0841225 < 2e-16 *** Email 3 0.0147423 1.83e-10 *** Email 4 0.0117065 2.44e-06 *** Spring -0.0848055 2.42e-09 *** Summer 0.0314521 0.03681 * Winter 0.0141746 0.31955 Holiday -0.1940202 4.30e-14 *** Significance levels: ***= 0.001 **= 0.01 *= 0.05 .=0.1 McFadden R2: 0.47
Results (2)
Table 5 - Regression Amount SpentEstimate p-value Intercept 4.54e-05 *** Age 0.019352 0.147283 Gender 0.432863 0.256366 Household size 0.158703 0.242290
First Discount -2.872683 5.17e-07 ***
Frequency Discount 0.416583 5.25e-09 ***
Relationship length 0.115030 < 2e-16 ***
Email 1 1.778552 0.010628 * Email 2 3.860467 1.49e-05 *** Email 3 2.799495 0.000988 *** Email 4 4.073845 5.80e-07 *** Spring 2.638960 0.000411 *** Summer 0.807369 0.268818 Winter 0.463124 0.522614 Holiday 3.276835 0.021464 * R2= 0.076 Adjusted R2= 0.074 Significance levels: ***=0.001; **=0.01; *=0.05; .=0.1
› First purchase discount: spending will decrease with €2.87
› Frequency of previous discounts: spending will increase with €0.40
› Opened Email 2: spending will increase with €3.86 › Holiday promotion:
Results (3)
Selection equation Outcome equation
Estimates P-value Estimates p-value
Intercept -1.626 < 2e-16 *** -43.29986 < 2e-16 ***
First Discount 6.960e-02 < 2e-16 *** -5.36257 < 2e-16 ***
Relationship length -1.7339 < 2e-16 *** 0.15842 < 2e-16 ***
Model comparisons
Pseudo R2 MSE RMSE Hitrate TDL
Probit 0.47 - - 83.2% 1.247
Monetary - 232.31 12.58 - -
Discussion and Implications
› Email advertising is ineffective: low response rate › Small proportions positive effects
§ First discount: positive/negative
§ Frequency: negative/positive
§ Relationship length: positive/negative
Limitations and Future Research
› Limitations
§ Focus is on only one industry and one country
§ Conversion rate is low (1.5%)
§ Other forms of marketing out there
› Future research directions:
§ Other marketing efforts (social media)
§ Link other behavior (online search/surf)