Ex Parte Bateni et al

Patent Trial and Appeal Board

May 19, 2016

12545263 (P.T.A.B. May. 19, 2016)

UNITED STA TES p A TENT AND TRADEMARK OFFICE
APPLICATION NO. FILING DATE
12/545,263 08/21/2009
26890 7590 05/23/2016
JAMES M, STOVER
TERADATA US, INC.
10000 INNOVATION DRIVE
DAYTON, OH 45342
FIRST NAMED INVENTOR
Arash Bateni
UNITED STATES DEPARTMENT OF COMMERCE
United States Patent and Trademark Office
Address: COMMISSIONER FOR PATENTS
P.O. Box 1450
Alexandria, Virginia 22313-1450
www .uspto.gov
ATTORNEY DOCKET NO. CONFIRMATION NO.
20438 1983
EXAMINER
WALKER III, GEORGE H
ART UNIT PAPER NUMBER
3683
NOTIFICATION DATE DELIVERY MODE
05/23/2016 ELECTRONIC
Please find below and/or attached an Office communication concerning this application or proceeding.
The time period for reply, if any, is set in the attached communication.
Notice of the Office communication was sent electronically on above-indicated "Notification Date" to the
following e-mail address( es):
michelle. boldman @teradata.com
jam es.stover@teradata.com
td.uspto@outlook.com
PTOL-90A (Rev. 04/07)
UNITED STATES PATENT AND TRADEMARK OFFICE
BEFORE THE PATENT TRIAL AND APPEAL BOARD
Ex parte ARASH BATENI and EDWARD KIM
Appeal2014-004647
Application 12/545,263 1
Technology Center 3600
Before JENNIFER D. BAHR, STEFAN STAICOVICI, and
SEAN P. O'HANLON, Administrative Patent Judges.
O'HANLON, Administrative Patent Judge.
DECISION ON APPEAL
STATEMENT OF THE CASE
Arash Bateni and Edward Kim (Appellants) appeal under 35 U.S.C.
§ 134 from the Examiner's Final decision rejecting claims 1-18. We have
jurisdiction over this appeal under 35 U.S.C. § 6(b ).
SUMMARY OF DECISION
We AFFIRM.
1 According to the Appellants, the real party in interest is Teradata US,
Incorporated. Appeal Br. 2.
Appeal2014-004647
Application 12/545,263
SUMMARY OF INVENTION
The Appellants' "invention relates to a [sic] methods and systems for
forecasting product demand using a causal methodology, based on multiple
regression techniques, , [sic] and in particular to a method for de-
seasonalizing causal factors having strong seasonal patterns and using the
deseasonalized variables within the causal demand forecasting
methodology." Spec. i-f 7. Claim 1, reproduced below from page 12 (Claims
Appendix) of the Appeal Brief, is illustrative of the claimed subject matter:
1. A computer-implemented method for forecasting product
demand for a product during a future sales period, the method
comprising the steps of:
maintaining, on a computer, an electronic database of
historical product demand information and historical causal
variable data;
identifying a causal variable having a seasonal pattern
influencing demand for said product;
removing, by said computer, the seasonal pattern from
said historical causal variable data associated with said causal
variable to generate de-seasonalized causal variable data for
said causal variable;
analyzing, by said computer, said historical product
demand information and said de-seasonalized causal variable
data for said product to determine a regression coefficient
corresponding to said causal variable;
calculating, by said computer, an initial demand forecast
for said product during said future sales period from said
historical demand information;
receiving, at said computer, a forecast value for said
causal variable during said future sales period;
removing, by said computer, the seasonal pattern from
said forecast value for said causal variable to generate a de-
seasonalized forecast value for said causal variable; and
blending, by said computer, said initial demand forecast,
said regression coefficient corresponding to said causal variable
2
Appeal2014-004647
Application 12/545,263
and said de-seasonalized forecast value for said causal variable
to determine a product demand forecast for said product.
REFERENCES
The Examiner relies on the following prior art references in rejecting
the claims on appeal:
Crosswhite
Niiyama
US 6,611,726 Bl
JP 2000293203 A
Aug. 26, 2003
Oct. 20, 2000
Aaron Hirst, Brigham Young Univ., Deseasonalizing Forecasts (Fall 2005)
(hereinafter "Hirst")
REJECTIONS
Claims 1--4, 6-10, 12-16, and 18 are rejected under 35 U.S.C.
§ 103(a) as being unpatentable over Crosswhite in view of Hirst.
Claims 5, 11, and 17 are rejected under 35 U.S.C. § 103(a) as being
unpatentable over Crosswhite in view of Hirst and Niiyama.
ANALYSIS
Claims 1--4, 6-10, 12-16, and 18-Crosswhite in view of Hirst
Claims 1--4 and 6
Regarding independent claim 1, the Examiner finds that Crosswhite
discloses the invention substantially as claimed (including the step of
"removing, by said computer, the seasonal pattern from said forecast value
for said causal variable to generate a de-seasonalized forecast value for said
causal variable"), but does not disclose, inter alia, the step of:
3
Appeal2014-004647
Application 12/545,263
blending, by said computer, said initial demand forecast, said
regression coefficient corresponding to said causal variable and
said de-seasonalized forecast value for said causal variable to
determine a product demand forecast for said product.
Final Act. 6-7. The Examiner further finds that Crosswhite discloses
applying a number of forecasting methods to historical causal variable data
to generate forecast causal variable values, Crosswhite discloses using the
Holt-Winters seasonal forecasting method, and the Holt-Winters seasonal
forecasting method includes removing the seasonal pattern of the subject
variable (citing works by Goodwin and Kalekar), and concludes that
Crosswhite, therefore, discloses generating de-seasonalized forecast values
for the causal variable. Ans. 2--4; see also Final Act. 2-3.
To cure the deficiencies of Crosswhite, the Examiner turns to the
teachings in Hirst regarding de-seasonalizing forecast data. Final Act. 7-8.
Based on these teachings, the Examiner concludes that it would have been
obvious for a skilled artisan to add the steps of 1) "analyzing the historical
product demand information and the causal variable data for said product to
determine a regression coefficient corresponding to said causal variable,"
2) "calculating an initial demand forecast for the product during the future
sales period from that historical demand information," and 3) "blending the
initial demand forecast, and the regression coefficient as taught by Hirst,
with the de-seasonalized forecast value for the causal variable taught by
Crosswhite" to the method of Crosswhite, the rationale being that "the
claimed invention is merely a combination of old elements, and in the
combination each element merely would have performed the same function
as it did separately, and one of ordinary skill in the art would have
4
Appeal2014-004647
Application 12/545,263
recognized that the results of the combination were predictable." Id. at 8.
The Examiner further finds that Hirst discloses using linear regression to
determine a regression coefficient identified as variable "b" in the forecast
formula Y = a + bx. Ans. 4; see also Final Act. 3--4. The Examiner further
determines that it would have been obvious to the skilled artisan "to expand
Hirst' s example to use linear regression to determine the value of
coefficients for other causal variables" in addition to demand because "Hirst
also teaches multiple causal variables." Final Act. 3--4, citing Hirst pp. 4
and 10.
We find that the Examiner has satisfied the burden of showing "some
articulated reasoning with some rational underpinning to support the legal
conclusion of obviousness." KSR Int'! Co. v. Teleflex Inc., 550 U.S. 398,
418 (2007) (quoting In re Kahn, 441F.3d977, 988 (Fed. Cir. 2006)).
Having set forth a case of prima facie obviousness, the burden shifts to the
Appellants to refute the Examiner's rejections. See In re Oetiker, 977 F.2d
1443, 1445 (Fed. Cir. 1992) (discussing how, ifan examiner presents a
prima facie case, "the burden of coming forward with evidence or argument
shifts to the applicant"). We find that the Appellants have not satisfied this
burden.
The Appellants argue that while the section of Crosswhite cited by the
Examiner in the Final Action does discuss time series forecasting,
Crosswhite contains "no discussion or language in this cited paragraph
concerning removing seasonal patterns from a forecast value of a causal
variable to determine a de-serialized forecast value for the causal variable."
Appeal Br. 8-9 (discussing the paragraph beginning at Crosswhite col. 3, 1.
5
Appeal2014-004647
Application 12/545,263
39). Furthermore, the Appellants argue, the Goodwin and Kalekar
references (cited by the Examiner to provide details about the Holt-Winters
seasonal forecasting method) "describe exponential smoothing techniques,
seasonal models and indexes, and the removal of seasonality from historical
data," but, the Appellants argue, "it is not seen that either Croswhite [sic]
... or the Holt-Winters references, Goodwin and Kalkar [sic], teach or
suggest removing a seasonal pattern from a [sic] forecast values." Reply Br.
2-3. We find these arguments to be unpersuasive because the Examiner did
not rely solely on that single paragraph of Crosswhite in setting forth the
rejection. Rather, as explained by the Examiner:
Crosswhite teaches a method of forecasting comprising
"selecting a dependent variable for which a value is to be
forecast, gathering historical data on values of the dependent
variable and explanatory variables (i.e. causal variables) in prior
time periods" (col. 6, lines 4--8); "this historical data is used
with a variety of forecasting methods to estimate future product
demand" (col. 3, lines 3 6-3 8), the variety of methods including
Holt-Winter's seasonal forecasting methods as noted in the
passage cited by the applicant; where "Organizations typically
apply some, or all, of these forecasting methods to individual
historical data" (col 4, lines 1-2), which historical data includes
causal variables as noted above and time series forecasting
methods applied to causal variables will yield forecasts for
those variables. Thus, Crosswhite explicitly teaches applying at
least the named time series forecasting methods to the historical
causal variable data associated with the causal variable to
forecast values for those causal variables.
Final Act. 2-3. The Appellants have not addressed the rejection actually set
forth by the Examiner, and the rejection, therefore, remains unrefuted.
The Appellants further argue that Hirst does not teach the recited
blending step because "[ t ]he quarterly seasonal index ... of Hirst is not a
6
Appeal2014-004647
Application 12/545,263
regression coefficient" and Hirst does not teach including a de-seasonalized
forecast value in its unadjusted regression forecast model. Appeal Br. 10-
11. We find these arguments to be unpersuasive because while the
Examiner's rejections were based on a combination of the teachings of Hirst
and Crosswhite (see Final Act. 3--4, 7-8; see also Ans. 4--5), the Appellants'
arguments only address the Hirst reference and do not address what the
combination of references teaches, as explained by the Examiner.
"Nonobviousness cannot be established by attacking references individually
where the rejection is based upon the teachings of a combination of
references." In re Merck & Co., 800 F.2d 1091, 1097 (Fed. Cir. 1986).
Accordingly, for the foregoing reasons, we sustain the Examiner's
rejection of independent claim 1 as being unpatentable over Crosswhite in
view of Hirst. The Appellants do not make any other substantive argument
regarding the rejection of dependent claims 2--4 and 6. See Appeal Br. 7-11.
Therefore, we likewise sustain the rejection of dependent claims 2--4 and 6
as being unpatentable over Crosswhite in view of Hirst.
Claims 7-10 and 12
With respect to the rejection of independent claim 7, the Appellants
rely on similar arguments as presented supra in regards to the rejection of
claim 1. See Appeal Br. 7-11. Accordingly, for the same reasons as
discussed supra with respect to claim 1, we also sustain the rejection of
independent claim 7 under 35 U.S.C. § 103(a) as being unpatentable over
Crosswhite in view of Hirst.
The Appellants do not make any other substantive argument regarding
the rejection of dependent claims 8-10 and 12. See id. Therefore, we
7
Appeal2014-004647
Application 12/545,263
likewise sustain the rejection of dependent claims 8-10 and 12 under
35 U.S.C. § 103(a) as being unpatentable over Crosswhite in view of Hirst.
Claims 13-16 and 18
With respect to the rejection of independent claim 13, the Appellants
rely on similar arguments as presented supra in regards to the rejection of
claim 1. See Appeal Br. 7-11. Accordingly, for the same reasons as
discussed supra with respect to claim 1, we also sustain the rejection of
independent claim 13 under 35 U.S.C. § 103(a) as being unpatentable over
Crosswhite in view of Hirst.
The Appellants do not make any other substantive argument regarding
the rejection of dependent claims 14--16 and 18. See id. Therefore, we
likewise sustain the rejection of dependent claims 14--16 and 18 under
35 U.S.C. § 103(a) as being unpatentable over Crosswhite in view of Hirst.
Claims 5, 11, and 17-Crosswhite in View of Hirst and Niiyama
Claim 5
With respect to the rejection of dependent claim 5, the Appellants rely
on the arguments presented supra in regards to the rejection of claim 1.
Appeal Br. 7-11. Accordingly, for the same reasons as discussed supra, we
also sustain the rejection of claim 5 under 35 U.S.C. § 103(a) as being
unpatentable over Crosswhite in View of Hirst and Niiyama.
Claim 11
With respect to the rejection of dependent claim 11, the Appellants
rely on the arguments presented supra in regards to the rejection of claim 1.
8
Appeal2014-004647
Application 12/545,263
Appeal Br. 7-11. Accordingly, for the same reasons as discussed supra, we
also sustain the rejection of claim 11 under 35 U.S.C. § 103(a) as being
unpatentable over Crosswhite in view of Hirst and Niiyama.
Claim 17
With respect to the rejection of dependent claim 17, the Appellants
rely on the arguments presented supra in regards to the rejection of claim 1.
Appeal Br. 7-11. Accordingly, for the same reasons as discussed supra, we
also sustain the rejection of claim 17 under 35 U.S.C. § 103(a) as being
unpatentable over Crosswhite in View of Hirst and Niiyama.
DECISION
The Examiner's decision to reject claims 1--4, 6-10, 12-16, and 18
under 35 U.S.C. § 103(a) as being unpatentable over Crosswhite in view of
Hirst is affirmed.
The Examiner's decision to reject claims 5, 11, and 17 under
35 U.S.C. § 103(a) as being unpatentable over Crosswhite in view of Hirst
and Niiyama is affirmed.
No time period for taking any subsequent action in connection with
this appeal may be extended under 37 C.F.R. § 1.136(a)(l )(iv).
AFFIRMED
9