1 Chapter 29 CUSTOMER LIFETIME VALUE V. Kumar, University of Connecticut Introduction In the past two decades, the firms tended to focus on either cost management or revenue growth. When a firm adopts one of these approaches it looses out on the other (Rust, Lemon, & Zeithaml, 2004). For instance, if a firm focuses only on revenue growth without emphasis on cost management, it fails to maximize the profitability. Similarly, cost management without revenue growth affects the market performance of the firm. What is needed is an approach which balances the two, creating market-based growth while carefully evaluating the profitability and return on investment (ROI) of marketing investments. Optimal allocation of resources and efforts across profitable customers and cost effective and customer specific communication channels (marketing contacts) is the key to the success of such an approach. This calls for assessing the value of individual customers and employing customer level strategies based on customers’ worth to the firm. The assessment of the value of a firm’s customers is the key to this customer- centric approach. But what is the value of a customer? Can customers be evaluated based only on their past contribution to the firm? Which metric is better in identifying the future worth of the customer? These are some of the questions for which a firm needs answers before assessing the value of its customers. Many customer oriented firms realize that the customers are valued more than the profit they bring in every transaction. Customers’ value has to be based on their contribution to the firm across the duration of their
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
1
Chapter 29
CUSTOMER LIFETIME VALUE V. Kumar, University of Connecticut
Introduction
In the past two decades, the firms tended to focus on either cost management or
revenue growth. When a firm adopts one of these approaches it looses out on the other
(Rust, Lemon, & Zeithaml, 2004). For instance, if a firm focuses only on revenue growth
without emphasis on cost management, it fails to maximize the profitability. Similarly,
cost management without revenue growth affects the market performance of the firm.
What is needed is an approach which balances the two, creating market-based growth
while carefully evaluating the profitability and return on investment (ROI) of marketing
investments. Optimal allocation of resources and efforts across profitable customers and
cost effective and customer specific communication channels (marketing contacts) is the
key to the success of such an approach. This calls for assessing the value of individual
customers and employing customer level strategies based on customers’ worth to the
firm.
The assessment of the value of a firm’s customers is the key to this customer-
centric approach. But what is the value of a customer? Can customers be evaluated based
only on their past contribution to the firm? Which metric is better in identifying the future
worth of the customer? These are some of the questions for which a firm needs answers
before assessing the value of its customers. Many customer oriented firms realize that the
customers are valued more than the profit they bring in every transaction. Customers’
value has to be based on their contribution to the firm across the duration of their
2
relationship with the firm. In simple terms, the value of a customer is the value the
customer brings to the firm over his/her lifetime. Some recent studies (Reinartz &
Kumar, 2003) have shown that past contributions from a customer may not always reflect
his or her future worth to the firm. Hence, there is a need for a metric which will be an
objective measure of future profitability of the customer to the firm (Berger & Nasr,
1998). Customer lifetime value takes into account the total financial contribution—i.e.,
revenues minus costs—of a customer over his or her entire lifetime with the company and
therefore reflects the future profitability of the customer. Customer lifetime value (CLV)
is defined as the sum of cumulated cash flows—discounted using the Weighted Average
Cost of Capital (WACC) — of a customer over his or her entire lifetime with the
company.
In this chapter, we first discuss the importance and the relevance of CLV and
compare it with other traditionally used metrics. Two approaches for measuring CLV,
namely the aggregate approach and the individual level approach, are explained in the
following section. The concept of P (Active) as the probability of customer being active
in the future is also introduced in this section. In the subsequent section, we discuss the
antecedents of CLV followed by a detailed discussion about how CLV measure can be
used for developing customer-centric strategies with specific applications of using CLV
to maximize ROI and/or profitability. We also present organizational challenges in
implementing CLV-based framework and we conclude the chapter by discussing the
future of CLV.
Why Is CLV Relevant and Important?
3
CLV is a measure of the worth of a customer to the firm. Calculation of CLV for
all the customers helps the firms to rank order the customers on the basis of their
contribution to the firm’s profits. This can be the basis for formulating and implementing
customer specific strategies for maximizing their lifetime profits and increasing their
lifetime duration. In other words, CLV helps the firm to treat each customer differently
based on their contribution rather than treating all the customers same.
Calculating CLV helps the firm to know how much it can invest in retaining the
customer so as to achieve positive return on investment. A firm has limited resources and
ideally wants to invest in those customers who bring maximum return to the firm. This is
possible only by knowing the cumulated cash flow of a customer over his or her entire
lifetime with the company or the lifetime value of the customers. Once the firm has
calculated CLV of their customers, it can optimally allocate its limited resources to
achieve maximum return. CLV framework is also the basis for purchase sequence
analysis and customer specific communication strategies. CLV can be considered as the
metric which guides the allocation of resources for ongoing marketing activities in a firm
adopting customer-centric approach.
Traditionally Used Metrics
Some of the commonly used metrics for computing customer value include RFM,
Share-of-Wallet and Past Customer Value.
RFM Method
RFM stands for Recency, Frequency, and Monetary Value. This technique
utilizes these three metrics to evaluate customer behavior and customer value.
4
1. Recency is a measure of how long it has been since a customer last placed an order
with the company.
2. Frequency is a measure of how often a customer orders from the company in a
certain defined period.
3. Monetary value is the amount that a customer spends on an average transaction.
Two methods are generally used for computing RFM. The first method involves
sorting customer data from the customer database, based on RFM criteria and grouping
them in equal quintiles and analyzing the resulting data.
The second method involves the computation of relative weights for R, F, and M
using regression techniques and then the use of those weights for calculating the
combined effects of RFM. RFM can be considered as the sum of the weighted recency,
frequency, and monetary value scores for a customer.
Example
Three customers have a purchase history calculated over a 12-month period. For
every customer numerical points have been assigned to each transaction according to a
historically derived R/F/M formula. The relative weight based on the importance
assigned to each of the three variables, R, F and M on the basis of an analysis carried out
on past customer transactions is as follows:
Recency-50%, Frequency- 20%, Monetary Value– 30%
Table 29.1a about Here Table 29.1b about Here Table 29.1c about Here Table 29.1d about Here
5
In the above example MAGS has highest RFM score (i.e. 30.4) and is preferred to
other customers for resource allocation if we use RFM method. RFM technique can be
applied only on historical customer data available and not on prospects data.
Share-of-Wallet (SOW)
Share-of-Wallet at an aggregate level is defined as the proportion of category
value accounted for by a focal brand or a focal firm within its base of buyers. At an
individual customer level, SOW is defined as the proportion of category value accounted
for by a focal brand or a focal firm for a buyer from all brands that the buyer purchases in
that category. It indicates the degree to which a customer meets his needs in the category
with a focal brand or firm (Kumar & Reinartz, 2005).
It is computed by dividing the value of sales (S) of the focal firm (j) to a buyer in
a category by the size-of-wallet of the same customer in a time period. SOW is measured
in percentage.
Individual Share-of-Wallet (%) of firm to customer (%) = Sj / ∑=
J
j 1 Sj (3)
Where:
S = sales to the focal customer
j = firm
∑=
J
j 1represents the summation of the value of sales made by all the J firms that sell a
category of products to a buyer.
For instance, if a consumer spends on an average $500 per month on groceries
and $300 of her purchases is with Supermarket A, then supermarket A’s share-of-wallet
for that consumer is 60% in that month.
6
The information about a customer’s spending with competitors is not normally
available with the firms. This is obtained from primary market research or surveys
administered to a representative sample of firm’s customers. The results are then
extrapolated to the entire buyer base. However, in certain B-to-B contexts firms can infer
the size of wallet for certain products especially when the number of players in the
market is few.
Past Customer Value
This model is built on the assumption that the past performance of the customer
indicates their future level of profitability and an extrapolation of the results of past
transactions is a measure of customer’s value in the future. The value of a customer is
determined based on the total contribution (towards profits) provided by the customer in
the past. The contributions from past transactions are adjusted for the time value of
money and the cumulative contribution till the present period is the past customer value
(PCV) of a customer. PCV can be computed using the following formula,
Past Customer Value of a customer
Where i = number representing the customer
r = applicable discount rate (for example 15% per annum or 1.25% per
month)
T = number of time periods prior to current period when purchase was made
GCit = Gross Contribution of transaction of the ith customer in time period, t.
Example: Consider an electronic retailer BB Corp. is interested in calculating the
past customer value of all its customers to identify their best customers. They have data
∑=
+=T
t
tit rGC
1)1(*
7
on the products purchased by various customers over a period of time, the value of the
purchases and the contribution margin. They can compare the value generated by each
customer by computing all transactions in terms of their present value. The spending
pattern by one of their customer is given below. The gross margin is 30% of the purchase
amount and discount rate is 15% per year or 1.25% per month.
Table 29.2 about Here
The Past customer value of this customer is then computed as follows;
The above customer is worth $302.01 in contribution margin, expressed as net
present value in May in dollars. By comparing this score among a set of customers we
arrive at a prioritization for directing future marketing efforts. The customers with higher
values are normally the customers deserving greater marketing resources.
Difference Between CLV and the Traditionally Used Metrics
Though RFM, Past Customer Value, and Share-of-Wallet are commonly used for
computing customer’s future value, they suffer from the following drawbacks. These
methods are not forward looking and do not consider whether a customer is going to be
active in the future. These measures consider only the observed purchase behavior and
extrapolate it to the future to arrive at the future profitability of a customer. RFM assumes
that the recency, frequency, and monetary value of a customers purchase explain the
future value of the customer. It fails to account for other factors which help in predicting
302.01486 5)0125.01(2404)0125.01(15
3)0125.01(152)0125.01(9)0125.01(6
Scoring ValueCustomer Past
0.3 Amount Purchase (GC)on Contributi Gross
=++++
+++++
=
×=
8
customer’s future purchase behavior and his/her worth to the firm. Also, the weights
given for R, F, and M greatly influence the computation of customer’s worth. PCV
technique also fails to account for factors influencing future purchase behavior of
customers. It also does not incorporate the expected cost of maintaining the customer in
the future. Since SOW measure is based on responses from a representative sample of
customers, it is unable to provide us a clear indication of future revenues and profits that
can be expected from a particular customer. This limits its use as a valuable input in
designing customer level marketing strategies.
On the other hand, CLV measure incorporates both the probability of a customer
being active in the future and the marketing costs to be spent to retain the customer. As
discussed above, one goal of calculating the value of a customer is to design customer
level strategies so that firms can maximize their return. To effectively do this, we need to
know whether the customer is going to purchase in future time periods and the expected
value of profits he/she brings to the firm. We should also know the effort or marketing
costs to be spent to retain the customer. RFM, PCV, and SOW approaches do not take
into account the probability of being active in the future and the costs whereas CLV
approach incorporates both these aspects in the calculation as can be seen in the next
section. CLV can be effectively used as a metric in allocating resources optimally and
developing customer level marketing and communication strategies.
Measuring CLV
Lifetime value of a customer can be either calculated as an average CLV or
individual level CLV.
9
An Aggregate Approach
In the aggregate approach, average lifetime value of a customer is derived from
the lifetime value of a cohort or segment or even the firm. Three approaches to arrive at
average CLV are explained here. In the first approach, the sum of lifetime values of all
the customers, called Customer Equity (CE) of a firm is calculated as;
tT
tit
I
i
CMCE ∑∑==
⎟⎠⎞
⎜⎝⎛
+=
11 11
δ (1)
where
CE = customer equity of customer base in $ (sum of individual lifetime values)
CM = Contribution margin in time period t
δ = discount rate.
i = customer index
t = time period
T = the number of time periods for which CE is being estimated.
In this case, the CE measure gives the economic value of a firm and we can
calculate average CLV by dividing CE by the number of customers.
In another approach (Berger & Nasr, 1998; Kumar & Ramani, 2004) the average
CLV of a customer is calculated from the lifetime value of a cohort or customer segment.
The average CLV of a customer in the first cohort or cohort 1 can then be expressed as;
( )( )∑
=
−⎥⎦
⎤⎢⎣
⎡
+−
=T
t
tt Ar
dMGCCLV
01 1
(2)
where
r = rate of retention
10
d = discount rate or the cost of capital for the firm.
t = time period
T = the number of time periods considered for estimating CE.
GC = the average gross contribution.
M = marketing cost per customer
A = the average acquisition cost per customer
This approach takes into account only the average gross contribution (GC), the
average acquisition cost per customer (A), and marketing cost (M) per customer. The
retention rate, r is the average retention rate for the cohort and is taken as a constant over
a period. However this is not the case in reality. Customers leave the relationship with
the firm in different points in time the retention probabilities vary across customers. This
means that we have to account for retention probabilities in the calculation for CE.
In another approach, (Blattberg, Getz, & Thomas, 2001) customer equity of the
firm is first calculated as the sum of return on acquisition, return on retention and return
on add-on selling. This is expressed in a mathematical equation as follows;
( ) ( ) ( )∑ ∑ ∏=
∞
=++++
=+
⎥⎥⎦
⎤
⎢⎢⎣
⎡⎟⎠⎞
⎜⎝⎛
+−−−⎟⎟
⎠
⎞⎜⎜⎝
⎛+−−=
I
i k
k
ktAOiktriktikti
k
jktjtititaitititititi d
BBcSNBNcSNtCE0 1
,,,,,,1
,,,,,,,,,, 11ραα
where
CE(t) = the customer equity value for customers acquired at time t
Ni,t = the number of potential customers at time t for segment i
ti ,α = the acquisition probability at time t for segment i
ti ,ρ = the retention probability at time t for a customer in segment i
Bi,a,t = the marketing cost per prospect (N) for acquiring customers at time t for
segment i
11
Bi,r,t = the marketing in time period t for retained customers for segment i
Bi,AO,t = the marketing costs in time period t for add-on selling for segment i
d = discount rate
Si,t = sales of the product/services offered by the firm at time t for segment i
ci,t = cost of goods at time t for segment i
I = the number of segments
I = the segment designation
t0 = the initial time period.
Average CLV can then be arrived at by dividing CE by the number of customers.
One of the important application of average CLV (Gupta & Lehmann, 2003;
Kumar & Ramani, 2004) is for evaluating competitor firms. In the absence of
competitors’ customer level data, firms can deduce information from published financial
reports about approximate gross contribution margin, marketing and advertising spending
by competing firms to arrive at reasonable estimates of average CLV for competitors.
This gives an idea of how profitable or unprofitable are competitors’ customers. Average
CLV approach can also be used for assessing the market value of the firm. Gupta and
Lehmann demonstrated that for high growth companies, aggregate CLV of a firm or
customer equity may be used as surrogate measure of firm’s market value.
However, average CLV has limited use as a metric for allocation of resources
across customers because it does not capture customer level variations in CLV, which is
the basis for developing customer specific strategies. Hence it is necessary to calculate
CLV of individual customers in order to design individual level strategies.
Individual-level Approach
12
At an individual level, customer lifetime value is calculated as the sum of
cumulated cash flows—discounted using the Weighted Average Cost of Capital (WACC)
— of a customer over his or her entire lifetime with the company. It is a function of the
predicted contribution margin, the propensity for a customer to continue in the
relationship, and the marketing resources allocated to the customer. In its general form,
CLV can be expressed as;
( )( )∑
= +−
=T
tt
iti d
tFutureFutureCLV1
it
1cosmarginon contributi
(4)
where
i = customer index,
t = time index
T = the number of time periods considered for estimating CLV, and
d = discount rate.
The CLV has two components, future contribution margin and future costs both
adjusted for the time value of money. To calculate the future contribution from a
customer in a non-contractual setting, a firm should know the probability that the
customer continues to do business with the firm in future time periods or probability of
customer being active, P (Active). Taking into account this probability, we can first get
the net present value (NPV) of expected Gross Contribution (EGC) as (Reinartz &
Kumar, 2003);
NPV of EGCit = ( )( )∑
+
+= +×
xt
tnnit
in dAMGC
ActiveP1 1
AMGCit = average gross contribution margin in period t based on all prior purchases
i = customer index
13
t = the period for which NPV is being estimated
x = the future time period
n = the number of periods beyond t
d = Discount Rate
P (Active) in = the probability that customer i is active in period n
Example
The spending pattern by a customer of an IT company, AMC Inc. is given as
follows. For instance, the customer purchased a desktop PC in January for $800. In the
next four months he purchased some software, flash memory, and DVDs. The average
gross margin is 30% of the purchase amount and discount rate is 15% per year or 1.25%
per month.
Table 29.3 about Here
If the probability of customer being active, P(Active) in June is 0.40 and that in
July is 0.19, then the NPV of EGC for June and July for this customer can be calculated
as follows;
AMGC = (240+15+15+9+6)/5 = 57
( ) ( )82.28
125.015719.0
125.01574.0 21 =
+×+
+×=EGCofNPV
Costs include acquisition cost (A) and the marketing costs (M) in future time
periods. Marketing costs in future time period need to be discounted with appropriate
discount rate, d to arrive at the present value of these costs. The discounted marketing
costs (M) and the acquisition cost (A) are then subtracted from the NPV of ECG to get
the CLV of a customer. If the marketing costs are accounted at the beginning of a given
time period and the gross contribution at the end of time period, we can express CLV as;
14
CLV of customer i = ( )( )
Ad
Md
AMGCActiveP
nx
nin
xt
tnnit
in −⎟⎠⎞
⎜⎝⎛
+×−
+×
−
=
+
+=∑∑
1
11 11
1
Average Monthly Gross Contribution (AMGC)
The average monthly gross contribution, AMGC is the average monthly revenue
obtained from a customer minus the average cost of goods sold. This is calculated based
on his/her past purchases.
Marketing Cost (M)
This includes the development and retention costs. It can be the cost of programs
to increase the value of existing relationship, cost of loyalty or frequent flyer programs,
cost of campaigns to ‘win back’ the lost customers, and the cost of serving the customer
accounts. One main component of these costs is the cost of marketing contacts through
various channels of communication. The contacts through different channels have
different costs to the firm. For example, a face-to-face meeting with customer costs much
higher than communication through direct mail or e-mail. To arrive at marketing costs
specific to a customer, firms need to estimate the number of contacts required to retain
the customer and the cost of contact through various channels. Once firms have such cost
accounting, calculation of marketing cost is straightforward. Estimation of marketing cost
is important in arriving at optimal customer specific communication strategies.
Discount Rate (d)
The revenue or gross contribution from the customer comes at different time
periods in the future, accounted yearly, monthly, or weekly. The value of money is not
constant across time and since the money received today is more valuable than the
received in future time periods, the GC and marketing costs have to be discounted to the
15
present value of money. This is achieved by dividing the cash flow in time period i by
(1+d)i, where d is the discount rate. The discount rate, d depends on the general rate of
interest and is normally proportional to the Treasury bill or the interest that banks pay on
savings accounts. It can also vary across firms depending upon the cost of capital to the
firm.
Time Period (n)
The number of future time periods (n) for which the gross contribution and the
marketing costs are considered for calculation of CLV refers to the natural ‘lifetime’ of
the customers. For most businesses it is reasonable to expect that the customers will
return for a number of years (n). There are no strict guidelines to decide on the value of n.
The word “lifetime” must be taken in many circumstances with a grain of salt. While the
term makes little sense with one-off purchases (say, for example, a house), it also seems
strange to talk about LTV of a grocery shopper. Clearly, there is an actual lifetime value
of a grocery shopper. However, given the long time span, this actual value has not much
practical value. For all practical purposes, the lifetime duration is a longer-term duration
that is managerially useful. For example, in a direct marketing general merchandise
context, managers consider maximum 4-year time span, sometimes only 2 years. Beyond
that, any calculation and prediction may become difficult due to so many uncontrollable
factors (the customer moves, a new competitors moves in, and so on) It is therefore
important to make an educated judgment as to what is a sensible duration horizon in the
context of making decisions.
P (Active) in is the probability that the customer continues to be active in
subsequent time period. For CLV calculation to be at an individual level, this probability
16
of retaining customer has to be calculated at an individual customer level rather than the
average rate of retention at the firm level. Each customer is likely to have different
purchase patterns and their active and inactive periods vary as shown in the Figure 29.1.
Figure 29.1 about Here
Given their purchase behavior in the past, one can predict the probability of
individual customers being active or P (Active) in subsequent time periods. A Simple
formula to calculate P (Active) is
P (Active) = (T / N)n
Where n is the number of purchases in the observation period, T is the time elapsed
between acquisition and the most recent purchase, and N is the time elapsed between
acquisition and the period for which P (Active) needs to be determined. For illustration, if
indicates a purchase, then for customer 1,
P (Active) in month 12 = (8/12)4 = 0.197 where n=number of purchase = 4
P (Active) for customer 2 in month 12 = (8/12)2 = 0.444 where n=2
In the above case, for a customer, who bought four times in the first eight months and did
not buy in the next four months, the probability of purchase after 4 months (i.e. at the end
of month 12) is less than that of customer 2 who purchased only two times in the first
eight months. The formula introduced here for calculation of P (Active) is very basic.
However, other sophisticated methods are employed for the calculation of the probability
of a customer purchasing in future time periods.
One drawback of using P (Alive) to predict customer’s future activity is that it
assumes that when a customer terminates a relationship, he/she does not come back to the
firm. This approach called “lost-for-good” is questionable because it systematically
Points for Recency : 20 if within past 2 months; 10 if within past 4 months; 05 if within past 6 months; 03 if within past 9 months; 01 if within past 12 months; Relative weight = 50%
Table 29.1b
RFM Method (Frequency Score)
Customer Purchases (Number)
Frequency Assigned Points
Weighted Points
1 1 3 0.6 JOHN 2 1 3 0.6 3 1 3 0.6 SMITH 1 2 6 1.2 1 1 3 0.6 MAGS 2 1 3 0.6 3 2 6 1.2 4 1 3 0.6 Points for Frequency: 3 points for each purchase within 12 months; Maximum = 15 points; Relative weight = 20%
Table 29.1c
RFM Method (Monetary Value Score)
48
Customer Purchases (Number)
Monetary Assigned Points
Weighted Points
1 $40 4 1.2 JOHN 2 $120 12 3.6 3 $60 6 1.8 SMITH 1 $400 25 7.5 1 $90 9 2.7 MAGS 2 $70 7 2.1 3 $80 8 2.4 4 $40 4 1.2 Monetary Value: 10 percent of the $ Volume of Purchase with 12 months; Maximum = 25 points; Relative weight = 30% Source: (for Tables 29.1a, 29.1b, and 29.1c) Marketing Research”, Eighth edition, David A.Aaker, V.Kumar, George S. Day (2003), John Wiley & Sons, Inc., New York
Table 29.1d
RFM Score
Customer Recency score*
Frequency score*
Monetary value score*
RFM score
JOHN 16.5 1.8 6.6 24.9
SMITH 2.5 1.2 7.5 11.2
MAGS 19.0 3.0 8.4 30.4 * Recency, frequency, and monetary value scores are sum of weighted points for Recency, frequency, and monetary value for each customer.
Table 29.2
Spending Pattern of a Customer (for Calculation of PCV)
January February March April May Purchase Amount ($) 800 50 50 30 20 GC 240 15 15 9 6
Table 29.3
Spending Pattern of a Customer (to Calculate NPV of EGC)
Source: Kumar, V., Girish Ramani, and Timothy Bohling (2004). Customer Lifetime Value Approaches and Best Practice Applications. Journal of Interactive Marketing, 18(3), 60-72.
Table 29.4
Drivers of Profitable Lifetime
Drivers Description Impact on Profitable lifetime
Spending Level Average monthly spending level over a given period
(+)
Cross-buying Number of different product/categories purchased
(+)
Focused buying Purchase within one category (-) Average Interpurchase Time
Number of days between purchases (average)
(∩)
Loyalty instrument Customer’s ownership of company’s loyalty instrument (B-to-C) or availability of line of credit (B-to-B)
(+)
Mailing Effort by the company
Number of mailing efforts of the company(B-to-C) or the number of contacts (B-to-B)
(+)
Income Income of the customer (B-to-C) or income of the firm (B-to-B)
(+)
Population density Number of people in a two-digit zip code (only B-to-C)
(-)
Source: Reinartz and Kumar (2003), “The Impact of Customer Relationship Characteristics on Profitable Lifetime Duration,” Journal of Marketing, 67(1), 77-99
Observation period
50
Table 29.5
Actual Revenues and Profits for the Selected Group of Customers Based on NPV of
ECM (CLV), RFM, and Past Customer Value Selection (Cohort 1*)
Percentage of Cohort (Selected from Top)
NPV of ECM (CLV method)
Advanced RFM Past Customer Value (PCV)
30% (n=1260) Revenue
Profit
318,831
62,991
140,781
27,582
179,665
35,916
50% (n=2101) Revenue
Profit
361,125
61,636
186,267
36,380
210,860
41,729
70% (n=2941) Revenue
Profit
380,855
60,305
216,798
42,839
225,910
44,738 * Cohort 1 had 4202 observations. Notes: Results were similar for cohort 2 (4965 observations), and cohort 3 (n=2825)
Source: Adapted from Reinartz, Werner J., and V. Kumar (2003). The Impact of Customer Relationship Characteristics on Profitable Lifetime Duration. Journal of Marketing, 67(1), 77-99.
Table 29.6
Comparisons of CRM Metrics for Customer Selection
Percentage of Cohort (Selected from Top)
CLV PCR PCV CLD
5% Gross profit ($) Variable costs ($) Net profit($)
144,883 1,588 143,295
71,908 979 70,929
131,735 950 130,785
107,719 790 106,389
10% Gross profit ($)
78,401
27,981
72,686
55,837
51
Variable costs ($) Net profit($)
1,245 77,156
943 27,038
794 71,892
610 55,227
15% Gross profit ($) Variable costs ($) Net profit($)
56,147 807 55,340
15,114 944 14,170
52,591 809 51,782
44,963 738 44,225
Notes: All metrics are evaluated at 30 months, with an 18-month prediction window. The reported values are cell medians. Gross profit for the firm which provided the database is approximately 30% of the revenue. Source: Venkatesan, Rajkumar, and V. Kumar (2004). A customer Lifetime Value Framework for Customer Selection and Resource Allocation Strategy. Journal of Marketing, 68(4), 106-125.
Table 29.7 Segmentation of Customers Based on Customer Lifetime Profits and Relationship
Duration BUTTERFLIES
• Good fit between company’s offerings and customers’ needs
• High Profit potential • Action
o Aim for transactional satisfaction, not attitudinal loyalty
o Maximize profits from these accounts as long as they are active
o Stop investing once inflection point is reached
TRUE FRIENDS • Excellent fit between company’s
offerings and customers’ needs • Highest profit potential • Action
ο Consistent intermittently spaced communication
ο Achieve attitudinal and behavioral loyalty
ο Invest to nurture/defend/retain
STRANGERS • Little fit between company’s offerings
and customers’ needs • Lowest profit potential • Action
ο Make no investment in these relationships
ο Make profit on every transaction
BARNACLES • Limited fit between company’s
offerings and customers’ needs • Low profit potential • Action:
ο Measure size and share of wallet ο If share-of-wallet is low, focus on
specific up and cross selling ο If size of wallet is small, impose
strict cost controls Source: Reinartz, Werner and V Kumar (2002),”The Mismanagement of Customer Loyalty,” Harvard Business Review, July, 1-13.
High
Low
Cus
tom
er L
ifetim
e Pr
ofits
Low High Relationship Duration
52
Table 29.8
Segmentation of Customers Based on Past and Future Profitability
RISING STARS Action
ο Invest to deepen relationship ο Identify specific up-sell/ cross-sell
opportunities ο Cultivate attitudinal loyalty
TRUE LOYALISTS Action
ο Cultivate attitudinal loyalty ο Invest to nurture/defend/retain ο Reward proactively
TOTAL MISFITS Action
ο No relationship investment ο Aim to extract profit from every
transaction by migrating the customer to low cost channels
FALLING ANGELS Action
ο Identify specific up-sell/ cross-sell opportunities
ο Transact through low-cost channels
ο Optimize (Minimize) Marketing costs
Table 29.9
Change Between Current Year and Previous Year
Test Group Control Group Revenue ($) 1050 (18,130) 1033 (17,610) Cost of Communication ($) -750 (3,625) 75 (4,580) # of attempts before purchase -4 (15) 1 (18) Profits ($) 3,000 (9080) 637 (6,275) Return on Investment (%) 504 (3.7) 2.2 (2) * The reported values are unit values per customer Number indicates change from base level (previous year). Base level is in parentheses. Source: Kumar, V., Rajkumar Venkatesan and Werner Reinartz (2005), “A Purchase Sequence Analysis Framework for Targeting Products, Customers and Time Period’, forthcoming; Journal of Marketing
Table 29.10
Average Customer Relationship Duration (as a Function of Retention Spending)
Futu
re P
rofit
abili
ty
(CL
V)
Low
High
Low High Historical Profits (PCV)
53
Retention spending (per customer)
$40 $50 $60 $70 $80
Estimated relationship duration (days)
122 135 142 143 138
Table 29.11
Average Customer Profitability (as a Function of Acquisition and Retention
Spending)
Retention Spending
$40 $50 $60 $70 $80
$1 $1,423 $1,543 $1,583 $1,543 $1,423
$5 $1,437 $1,557 $1,597 $1,557 $1,437
$10 $1,443 $1,563 $1,603 $1,563 $1,443
$15 $1,437 $1,557 $1,597 $1,557 $1,437
Acquisition spending
$20 $1,418 $1,538 $1,578 $1,538 $1,418
Source: (for Table 29.10 & 19.11) Thomas, Jacquelyn S., Werner Reinartz, and V. Kumar (2004). Getting the Most out of All Your Customers. Harvard Business Review, July-August, 116-123.
54
Table 29.12:
Customer Segments Based on Acquisition and Retention Costs
Source: Thomas, Jacquelyn S., Werner Reinartz, and V. Kumar (2004). Getting the Most out of All Your Customers. Harvard Business Review, July-August, 116-123.
High-maintenance customers 25% of customers 15% of profits
Royal customers 28% of customers 25% of profits
Casual customers 32 % of customers 20% of profits
Low-maintenance customers 15% of customers 40% of profits
High Acquisition cost Low
Hig
h Lo
w
Ret
entio
n co
st
55
Figure 29.2 Soft Drink Consumption Pattern Across Age Groups
Age <13Yrs
µ1 = 1000 oz
13 – 20 Years
µ2 = 1500 oz
31 – 40 Years
µ4 = 2500 oz
> 50 Years
µ6 = 1600 oz µ5 = 1800 oz
41 – 50 Years
Average Yearly Consumption (oz)
Freq
uenc
y
Note: The average yearly consumption figures are for illustration purpose only.