Ex Parte Witting

Patent Trial and Appeal Board

Jan 30, 2013

10445722 (P.T.A.B. Jan. 30, 2013)

UNITED STATES PATENT AND TRADEMARK OFFICE
____________________

BEFORE THE PATENT TRIAL AND APPEAL BOARD
____________________

Ex parte THOMAS WITTING
____________________

Appeal 2010-009206
Application 10/445,722
Technology Center 3600
____________________

Before: MURRIEL E. CRAWFORD, HUBERT C. LORIN, and BIBHU R.
MOHANTY, Administrative Patent Judges.

CRAWFORD, Administrative Patent Judge.

DECISION ON APPEAL

Appeal 2010-009206
Application 10/445,722

2
STATEMENT OF CASE
Appellant seeks our review under 35 U.S.C. § 134 from the
Examiner’s final rejection of claims 1-18. We have jurisdiction under 35
U.S.C. § 6(b).

SUMMARY OF THE DECISION
We reverse.

BACKGROUND
Appellant’s invention is directed to predicting marketing campaigns
having more than one step (Spec. 4:3-5).
Claim 1 is illustrative:
1. A method of predicting outcomes of marketing
campaigns comprising more than one campaign step, using a
computer system, the method comprising:
defining, in the computer system, a marketing campaign
as including at least first and second campaign steps, the second
campaign step configured to be performed after the first
campaign step and only toward customers who responded to the
first campaign step;
compiling first customer objects in a repository, the first
customer objects corresponding to a first target group of
customers registered in the computer system, at least one
constraint taken into account when compiling the customer
objects;
predicting, using the computer system and the first
customer objects, a number of responses to be received if the
first campaign step were performed toward the first target group
of customers, each customer having a response probability;
compiling, using the computer system, second customer
objects from the first customer objects, the second customer
objects corresponding to a second target group selected from
the first target group using respective response probabilities of
Appeal 2010-009206
Application 10/445,722

3
individual customers in the first target group, the second target
group being a subset of the first target group and substantially
equal to the predicted number of responses;
predicting, using the computer system and the second
customer objects, an outcome of performing the second
campaign step toward the second target group; and
generating, using the computer system, a prediction for
the marketing campaign using at least the predictions regarding
the first and second campaign steps.

Appellant appeals the following rejections:
Claims 1, 9, 11, 13, and 15 are rejected under 35 U.S.C. § 103(a) as
unpatentable over Blume (US 6,839,682 B1, iss. Jan. 4, 2005) and Jedid-Jah
Jonker, et al., EVALUATING DIRECT MARKETING CAMPAIGNS;
RECENT FINDINGS AND FUTURE RESEARCH TOPICS, Econometric
Institute Report 9851/A, 1-31 (Nov. 1998) (hereinafter “Jonker”).
Claims 2, 3, and 12 are rejected under 35 U.S.C. § 103(a) as
unpatentable over Blume, Jonker, and Vic Barnett, Comparative Statistical
Inference - Third Edition, 108 (1999) (hereinafter “Barnett”).
Claims 4-6, 10, 14 and 16-18 are rejected under 35 U.S.C. § 103(a) as
unpatentable over Blume, Jonker, and Fisher (US 2002/0052775 A1, pub.
May 2, 2002).
Claims 7 and 8 are rejected under 35 U.S.C. § 103(a) as unpatentable
over Blume, Jonker, and Lin (US 6,847,934 B1, iss. Jan. 25, 2005).

FACTUAL FINDINGS
We find the following facts by a preponderance of the evidence.
1. Jonker discloses a test campaign, stating:
App
App

2.
eal 2010-0
lication 10
If a com
response
a top l
individu
is a dif
more, an
differenc
characte
approach
(Pg. 7).
Jonker dis
marketing
09206
/445,722
pany wan
between
evel incom
als in both
ference in
d as this
e in the
ristics are
mainly d
closes at F
campaign
ts to analy
one or dou
e, the c
groups a
response
differenc
size of t
compara
ouble inco
igure 1 a f
, as follow
4
ze whethe
ble incom
ompany
nd compa
in that d
e can be
he househ
ble), the
me househ
low chart
s:
r there is
e househ
can send
re the resp
ouble inc
attributed
old (beca
company
olds.
of the stag
a differen
olds, both
a mailin
onses. If
omes res
mainly to
use the
can decid
es of a dir
ce in
with
g to
there
pond
the
other
e to
ect

Appeal 2010-009206
Application 10/445,722

5
Jonker Figure 1 disclosing the stages of a marketing campaign.
(Pg. 27).
ANALYSIS
Each of independent claims 1, 11, and 15 recite a step for predicting
an outcome of a second campaign step, where the second campaign step is
“performed after the first campaign step and only towards customers who
responded to the first campaign step.”
We are persuaded of error by Appellant’s argument that Blume fails
to disclose predicting the outcome of a second campaign step that follows a
first campaign step. App. Br. 11-12. Blume discloses a technique to predict
responses (Fig. 14, col. 44, ll. 55-57), and discloses this could be used as
input to a “second-level predictive model” (col. 45, l. 65 to col. 46, l. 3), but
does not disclose that the second-level model would rely only on customers
who responded to the first-level model.
We are persuaded of error also by Appellant’s argument that Jonker
fails to disclose that the second campaign step is performed only towards
customers who responded to the first campaign step, because “other
households are targeted as well.” App. Br. 11-12. Jonker discloses a test
marketing campaign before a second campaign. FF 1. The target of the
second campaign is a market segment similar to that used in the test
campaign, such as “double-income households,” but is not limited to
households who responded to the test campaign, as required. This is evident
in the flow chart which shows test and real campaigns as parallel, rather than
successive, steps. FF 2.
For these reasons, we reverse the rejection of claims 1, 11, and 15, as
well as variously rejected dependent claims 2-10, 12-14, and 16-18.
Appeal 2010-009206
Application 10/445,722

6
DECISION
We reverse the Examiner’s rejections under 35 U.S.C. § 103(a) of
claims 1-18.

REVERSED

hh