US 8,265,984 B2Granted

Method and apparatus for unified optimization model for retail network configuration

AssigneeInternational Business Machines Corporation

InventorsXin Xin Bai, Jin Dong, Ta-Hsin Li, Ming Xie, Wen Jun Yin, Bin Zhang, Cindy Q. Zhang

Life of this patent

Estimating the term…

Loading patent…

Abstract

A method and system for integrating multiple factors into a unified optimization model for retail network configuration, in one aspect, obtains input data for modeling store configuration. The input data may include demand of each merchandise category from each customer segment in each facility, geographic distribution of stores in an area, current revenue of stores, and physical cost of reconfiguring stores. A trade area is generated as a function of store location, store format, and store capacity. The method and system also generates trade area demand summation representing predicted total demand of all stores for all merchandise categories for all customer segments in the trade area, as a function of store location, store format, store capacity, merchandise category, and customer segment associated with the trade area. An objective function is constructed as a function of said trade area demand summation, current revenue of stores, and physical cost of reconfiguring stores.

Claims17

Dependent claims

A computer-implemented method for integrating multiple factors into a unified optimization model for retail network configuration, comprising:

obtaining input data for modeling store configuration, said input data including at least demand of each merchandise category from each customer segment in each facility, geographic distribution of stores in an area, current revenue of stores, and physical cost of reconfiguring stores;
generating a trade area as a function of store location, store format, and store capacity;
generating, by a processor, trade area demand summation representing predicted total demand of all stores for all merchandise categories for all customer segments in the trade area, said predicted total demand determined as a function of store location, store format, store capacity, merchandise category, and customer segment associated with the trade area;
and
constructing, by the processor, an objective function, said objective function being a function of said trade area demand summation, said current revenue of stores, and said physical cost of reconfiguring stores, said objective function for optimizing store network configuration,
wherein the objective function includes,
max
⁢
∑
i
=
1
N
⁢
⁢
{
P
⁡
(
S
i
)
-
V
i
-
L
⁡
(
S
t
,
S
i
⁢
⁢
0
)
}
,
wherein P(Si) represents predicted demand of i-th outlet with configuration, Vi is existing sales volume of i-th outlet, L(Si,Si0) is operation cost of transforming i-th outlet's existing configuration to recommended configuration, wherein
P
⁡
(
S
i
)
=
∑
g
∈
TA
⁡
(
L
i
,
F
i
,
P
i
)
⁢
⁢
∑
k
∈
C
i
⁢
⁢
∑
j
∈
M
i
⁢
⁢
D
⁡
(
g
,
b
k
,
n
j
)
,
wherein D(g,bk,nj) represents predicted demand of merchandise category j from customer segment k in geographic-demographic entity g, TA(Li,Fi,Pi) represents a trade area of i-th outlet determined by its location Li, format Fi, and capacity Pi.

89 more elements

A system for integrating multiple factors into a unified optimization model for retail network configuration, comprising:

a processor;
data input module operable to execute on the processor, said data input module further operable to obtaining input data for modeling store configuration, said input data including at least demand of each merchandise category from each customer segment in each facility, geographic distribution of stores in an area, current revenue of stores, and physical cost of reconfiguring stores;
and optimization objective function integration module operable to execute on the processor and to generate a trade area as a function of store location, store format, and store capacity, said optimization objective function integration module further operable to generate trade area demand summation representing predicted total demand of all stores for all merchandise categories for all customer segments in the trade area, said predicted total demand determined as a function of store location, store format, store capacity, merchandise category, and customer segment associated with the trade area, said optimization objective function integration module further operable to construct an objective function, said objective function being a function of said trade area demand summation, said current revenue of stores, and said physical cost of reconfiguring stores, said objective function for optimizing store network configuration,
wherein the objective function includes
max
⁢
∑
i
=
1
N
⁢
⁢
{
P
⁡
(
S
i
)
-
V
i
-
L
⁡
(
S
t
,
S
i
⁢
⁢
0
)
}
,
wherein P(Si) represents predicted demand of i-th outlet with configuration, Vi is existing sales volume of i-th outlet, L(Si, Si0) is operation cost of transforming i-th outlet's existing configuration to recommended configuration, wherein
P
⁡
(
S
i
)
=
∑
g
∈
TA
⁡
(
L
i
,
F
i
,
P
i
)
⁢
⁢
∑
k
∈
C
i
⁢
⁢
∑
j
∈
M
i
⁢
⁢
D
⁡
(
g
,
b
k
,
n
j
)
,
wherein D(g,bk,nj) represents predicted demand of merchandise category j from customer segment k in geographic-demographic entity g, TA(Li,Fi,Pi) represents a trade area of i-th outlet determined by its location Li, format Fi, and capacity Pi.

87 more elements

A non-transitory program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine to perform a method of integrating multiple factors into a unified optimization model for retail network configuration, comprising:

obtaining input data for modeling store configuration, said input data including at least demand of each merchandise category from each customer segment in each facility, geographic distribution of stores in an area, current revenue of stores, and physical cost of reconfiguring stores;
generating a trade area as a function of store location, store format, and store capacity;
generating trade area demand summation representing predicted total demand of all stores for all merchandise categories for all customer segments in the trade area, said predicted total demand determined as a function of store location, store format, store capacity, merchandise category, and customer segment associated with the trade area;
and
constructing an objective function, said objective function being a function of said trade area demand summation, said current revenue of stores, and said physical cost of reconfiguring stores, said objective function for optimizing store network configuration
wherein the objective function includes
max
⁢
∑
i
=
1
N
⁢
⁢
{
P
⁡
(
S
i
)
-
V
i
-
L
⁡
(
S
t
,
S
i
⁢
⁢
0
)
}
,
wherein P(Si) represents predicted demand of i-th outlet with configuration, Vi is existing sales volume of i-th outlet, L(Si,Si0) is operation cost of transforming i-th outlet's existing configuration to recommended configuration, and wherein
P
⁡
(
S
i
)
=
∑
g
∈
TA
⁡
(
L
i
,
F
i
,
P
i
)
⁢
⁢
∑
k
∈
C
i
⁢
⁢
∑
j
∈
M
i
⁢
⁢
D
⁡
(
g
,
b
k
,
n
j
)
,
wherein D(g,bk,n3) represents predicted demand of merchandise category j from customer segment k in geographic-demographic entity g, TA(Li,Fi,Pi) represents a trade area of i-th outlet determined by its location Li, format Fi, and capacity Pi.

89 more elements

Dependencies are inferred from the claim text.

Facts

Application: 12/117,540Filed 8 May 2008
Published: US 2009/0281869 A112 Nov 2009
Granted: 11 Sep 2012
Term ends: Not estimatedThe source records don’t support an estimate.

Classification3 codes

G06Q 10/04
Administration; Management: forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or…
G06Q 10/0637
Operations research, analysis or management: strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions…
G06Q
Information and communication technology [ict] specially adapted for administrative, commercial, financial, managerial