I
n
t
e
r
n
at
io
n
al
Jou
r
n
al
of
A
d
van
c
e
s
i
n
A
p
p
li
e
d
S
c
ie
n
c
e
s
(
I
JA
A
S
)
V
ol
.
14
, N
o.
3
,
S
e
pt
e
m
be
r
20
25
, pp.
945
~
954
I
S
S
N
:
2252
-
8814
,
D
O
I
:
10.11591/
ij
a
a
s
.
v14.
i
3
.
pp945
-
954
945
Jou
r
n
al
h
om
e
page
:
ht
tp
:
//
ij
aas
.i
ae
s
c
or
e
.c
om
O
p
t
i
m
i
z
i
n
g r
e
t
ai
l
sys
t
e
m
s:
u
si
n
g b
i
g
d
at
a an
d
p
ow
e
r
b
u
si
n
e
ss
i
n
t
e
l
l
i
ge
n
c
e
f
or
p
e
r
f
or
m
an
c
e
i
n
si
gh
t
s
H
u
u
D
an
g Q
u
oc
, H
a L
e
V
ie
t
F
a
c
ul
t
y of
E
c
onom
i
c
I
nf
o
r
m
a
t
i
on S
ys
t
e
m
a
nd E
-
c
om
m
e
r
c
e
, T
huongm
a
i
U
ni
ve
r
s
i
t
y, H
a
n
oi
, V
i
e
t
n
am
A
r
t
ic
le
I
n
f
o
A
B
S
T
R
A
C
T
A
r
ti
c
le
h
is
to
r
y
:
R
e
c
e
iv
e
d
D
e
c
12, 2024
R
e
vi
s
e
d
M
a
y 10, 2025
A
c
c
e
pt
e
d
J
un 13, 2025
In
the
rapid
development
of
information
technology,
using
enterprise
data
to
support
timely
management
decisions
is
crucial
in
helping
businesses
operate
effectively
and
improve
competitiveness.
This
study
uses
Mi
crosoft
p
ower
business
intelligence
(MPBI)
to
analyze
data
in
retail
sy
stems,
allowin
g
managers
to
grasp
the
busines
s
situat
ion
in
real
time,
track
advanced
sales,
optimi
ze
invento
ry
control,
and
analyze
customer
be
havior
and
supply
chain
visibility.
From
the
data
generated
by
the
busine
ss,
the
study uses the
streaming
extract tra
nsform
load (
ETL
)
model
to suppo
rt real
-
time
data
aggregation,
then
converts
to
the
MPBI
data
visualization
system
to
convert
data
into
visual
charts,
helping
businesses
easily
monitor,
track,
analyze,
and
make
decision
s
to
promote
busines
s
activit
ies.
The
study
proposes
a
data
structure
to
o
rganize
retail
information
stor
age.
It
pro
poses
a
system
of
calculation
formulas
and
data
synthesis,
making
integra
t
e
and
convert t
abular dat
a into
visual
charts. Th
rough anal
ysis o
f real data
fr
om the
LH83
retail
system,
the
study
shows
the
feasibility
of
implementing
a
data
visualization
system
and
the
d
ifficulties
encounter
ed
when
businesse
s
want
to deploy this mod
el.
K
e
y
w
o
r
d
s
:
B
ig
da
ta
D
e
c
is
io
n
-
m
a
ki
ng i
n t
he
r
e
ta
il
I
ndus
tr
y
D
ig
it
a
l
tr
a
ns
f
or
m
a
ti
on
P
ow
e
r
bus
in
e
s
s
i
nt
e
ll
ig
e
nc
e
V
is
ua
li
z
a
ti
on r
e
por
ts
This is an
open
acce
ss artic
le unde
r the
CC BY
-
SA
license.
C
or
r
e
s
pon
di
n
g A
u
th
or
:
H
a
L
e
V
ie
t
F
a
c
ul
ty
of
E
c
onomi
c
I
nf
or
m
a
ti
on S
ys
te
m
a
nd E
-
c
om
m
e
r
c
e
,
T
huongma
i
U
ni
ve
r
s
it
y
Ha
n
oi
, V
ie
t
n
am
E
m
a
il
:
le
vi
e
th
a
@
tm
u.e
du.vn
1.
I
N
T
R
O
D
U
C
T
I
O
N
T
he
r
a
pi
d
de
ve
lo
pm
e
nt
a
nd
w
id
e
s
pr
e
a
d
de
pl
oym
e
nt
of
di
gi
t
a
l
te
c
hnol
ogy
a
r
e
c
r
e
a
ti
ng
pr
of
ound
c
ha
nge
s
in
m
a
ny
f
ie
ld
s
,
a
nd
th
e
r
e
ta
il
in
dus
tr
y
is
one
of
th
e
m
os
t
s
tr
ongl
y
a
f
f
e
c
te
d.
I
n
a
n
in
c
r
e
a
s
in
gl
y
c
om
pe
ti
ti
ve
m
a
r
ke
t,
th
e
ne
e
d
s
of
c
us
to
m
e
r
s
a
nd c
ons
um
e
r
s
a
r
e
c
ons
ta
nt
ly
c
ha
ngi
ng, a
nd bus
in
e
s
s
e
s
a
ls
o ne
e
d
to
a
dj
us
t
th
e
ir
pr
oduc
ts
a
nd
s
e
r
vi
c
e
s
to
be
tt
e
r
m
e
e
t
c
us
to
m
e
r
n
e
e
ds
.
D
ig
it
a
l
tr
a
ns
f
or
m
a
ti
on,
th
e
r
e
f
or
e
,
is
not
onl
y
a
s
tr
a
te
gy
but
a
ls
o
a
r
e
qui
r
e
m
e
nt
f
or
s
ur
vi
va
l
,
e
s
pe
c
ia
ll
y
in
th
e
r
e
ta
il
s
e
c
to
r
,
w
he
r
e
da
ta
is
ge
ne
r
a
te
d
c
ont
in
uous
ly
a
nd i
n huge
vol
um
e
s
.
M
ode
r
n
te
c
hnol
ogi
e
s
a
ll
ow
bu
s
in
e
s
s
e
s
to
a
ut
om
a
t
e
w
or
k
pr
oc
e
s
s
e
s
,
opt
im
iz
e
s
uppl
y
c
ha
in
s
,
a
nd
c
ol
le
c
t
va
lu
a
bl
e
d
a
ta
f
a
s
te
r
a
nd
m
or
e
a
c
c
ur
a
te
ly
.
A
s
a
r
e
s
ul
t
,
bus
in
e
s
s
e
s
c
a
n
im
pr
ove
th
e
ir
a
na
ly
s
is
a
nd
m
a
na
ge
m
e
nt
c
a
pa
bi
li
ti
e
s
,
f
r
om
tr
a
c
ki
ng
f
in
a
nc
ia
l
in
di
c
a
to
r
s
s
u
c
h
a
s
r
e
ve
nue
,
c
os
t
s
,
a
nd
pr
of
it
s
to
ga
in
in
g
a
de
e
pe
r
unde
r
s
ta
ndi
ng of
ove
r
a
ll
ope
r
a
ti
ona
l
pe
r
f
or
m
a
nc
e
. O
ne
of
t
he
pr
a
c
ti
c
a
l
s
uppor
t
to
ol
s
f
or
t
h
is
pr
oc
e
s
s
i
s
M
ic
r
os
of
t
p
ow
e
r
bus
in
e
s
s
in
te
ll
ig
e
nc
e
(
M
P
B
I
)
[
1]
,
a
da
ta
a
na
ly
s
is
a
nd
vi
s
ua
li
z
a
ti
on
pl
a
tf
or
m
th
a
t
he
lp
s
bus
in
e
s
s
e
s
to
e
xpl
oi
t
c
us
to
m
e
r
be
ha
vi
or
a
nd
gr
a
s
p
m
a
r
ke
t
tr
e
nds
f
ur
th
e
r
,
th
e
r
e
by
m
a
ki
ng
m
or
e
in
f
or
m
e
d
da
ta
-
ba
s
e
d
d
e
c
is
io
n
s
.
T
o
s
uppor
t
da
t
a
pr
oc
e
s
s
in
g,
th
i
s
s
tu
dy
us
e
s
th
e
s
tr
e
a
m
in
g
e
xt
r
a
c
t
tr
a
ns
f
or
m
lo
a
d
(
E
T
L
)
in
a
r
e
a
l
-
ti
m
e
te
c
hni
que
in
pr
oc
e
s
s
in
g
a
nd
c
onve
r
ti
ng
da
ta
f
r
om
di
f
f
e
r
e
nt
s
our
c
e
s
in
to
a
vi
s
ua
li
z
a
ti
on
e
nvi
r
onm
e
nt
,
he
lp
in
g
to
pr
oc
e
s
s
qui
c
kl
y
a
nd
e
f
f
e
c
ti
ve
ly
.
U
nl
ik
e
ba
tc
h
E
T
L
,
s
tr
e
a
m
in
g
E
T
L
a
ll
ow
s
da
ta
to
be
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8814
I
nt
J
A
dv A
ppl
S
c
i
,
V
ol
.
14
, N
o.
3
,
S
e
pt
e
m
be
r
20
25
:
945
-
954
946
pr
oc
e
s
s
e
d
c
ont
in
uou
s
ly
f
r
om
c
ol
le
c
ti
on
a
nd
c
onve
r
s
io
n
to
vi
s
ua
li
z
a
ti
on
a
nd
is
ve
r
y
s
ui
ta
bl
e
f
or
th
e
c
ha
r
a
c
te
r
is
ti
c
s
of
th
e
r
e
ta
il
in
dus
tr
y,
w
he
r
e
tr
a
ns
a
c
ti
ons
,
in
ve
n
to
r
y,
a
nd
c
us
to
m
e
r
be
ha
vi
or
c
ha
nge
a
nd
a
r
is
e
c
ont
in
uous
ly
ove
r
ti
m
e
.
T
hi
s
m
e
th
od
he
lp
s
s
ynt
h
e
s
iz
e
da
ta
in
r
e
a
l
ti
m
e
,
s
uppor
ti
ng
a
na
ly
s
i
s
,
m
oni
to
r
in
g,
a
nd
m
a
ki
ng t
im
e
ly
de
c
is
io
ns
.
T
hi
s
s
tu
dy
a
ls
o
pr
opos
e
s
a
s
ui
ta
bl
e
da
t
a
ba
s
e
s
tr
uc
tu
r
e
f
or
s
to
r
a
ge
or
ga
ni
z
a
ti
on,
w
hi
c
h
c
a
n
be
li
nke
d
to
th
e
e
nt
e
r
pr
is
e
'
s
m
a
na
ge
m
e
nt
in
f
or
m
a
ti
on
s
ys
te
m
s
to
s
to
r
e
c
om
pl
e
te
a
nd
uni
f
ie
d
da
ta
,
f
a
c
il
it
a
ti
ng
th
e
e
xpl
oi
ta
ti
on
a
nd
pr
oc
e
s
s
in
g
pr
oc
e
s
s
.
T
o
s
uppor
t
th
e
c
a
lc
ul
a
ti
o
n
a
nd
s
ynt
he
s
is
of
da
ta
,
th
is
pa
pe
r
bui
ld
s
a
s
e
t
of
f
or
m
ul
a
s
to
c
a
lc
ul
a
te
ke
y
bu
s
in
e
s
s
in
di
c
a
to
r
s
s
uc
h
a
s
c
os
t
s
,
r
e
ve
nue
,
a
nd
pr
of
it
s
.
I
t
a
ppl
ie
s
th
e
m
di
r
e
c
tl
y
to
a
c
tu
a
l
da
ta
f
r
om
th
e
L
H
83
s
ys
te
m
.
T
hi
s
da
ta
s
e
t
c
ont
a
in
s
de
t
a
il
e
d
in
f
or
m
a
ti
on
a
bout
s
a
le
s
a
c
ti
vi
ti
e
s
a
nd
is
or
ga
ni
z
e
d
a
c
c
or
di
ng
to
th
e
da
ta
s
tr
uc
tu
r
e
s
p
r
opos
e
d
in
s
e
c
ti
on
3.
T
hr
ough
pow
e
r
bus
in
e
s
s
in
te
ll
ig
e
nc
e
(
P
B
I
)
,
th
e
da
ta
i
s
vi
s
ua
li
z
e
d i
n m
a
ny f
or
m
s
t
o s
uppor
t
th
e
a
na
ly
s
i
s
a
nd
de
c
is
io
n
-
m
a
ki
ng pr
oc
e
s
s
i
n bu
s
in
e
s
s
.
T
he
s
tr
uc
tu
r
e
of
th
e
r
e
s
t
of
th
e
pa
pe
r
is
a
s
f
ol
lo
w
s
:
s
e
c
ti
on
2
pr
e
s
e
nt
s
a
n
ov
e
r
vi
e
w
of
th
e
li
te
r
a
tu
r
e
a
nd
r
e
la
te
d
r
e
s
e
a
r
c
h
w
or
k
s
.
S
e
c
ti
on
3
de
s
c
r
ib
e
s
th
e
da
ta
s
tr
uc
tu
r
e
,
s
ynt
he
s
is
pr
oc
e
s
s
,
a
nd
da
ta
pr
oc
e
s
s
in
g
m
e
th
od
f
r
om
th
e
L
H
83
de
ta
il
ed
s
ys
te
m
.
S
e
c
ti
on
4
pr
e
s
e
nt
s
th
e
a
ppl
ic
a
ti
on
of
da
ta
vi
s
ua
li
z
a
ti
on
te
c
hnol
ogy
to
c
onve
r
t
da
ta
in
to
vi
s
u
a
l
c
ha
r
ts
,
a
na
ly
z
e
th
e
r
e
s
ul
ts
,
a
nd
gi
ve
im
por
ta
nt
m
a
na
ge
m
e
nt
im
pl
ic
a
ti
ons
.
F
in
a
ll
y,
s
e
c
ti
on
5 c
onc
lu
de
s
a
nd s
ugg
e
s
ts
f
ur
th
e
r
r
e
s
e
a
r
c
h di
r
e
c
ti
on
s
.
2.
R
E
L
A
T
E
D
WORKS
C
ur
r
e
nt
ly
,
m
a
ny
da
ta
a
na
ly
s
is
te
c
hnol
ogi
e
s
a
nd
pr
oc
e
s
s
e
s
ha
ve
be
e
n
de
pl
oye
d
a
nd
s
uppor
te
d
f
or
bus
in
e
s
s
e
s
ve
r
y
e
f
f
e
c
ti
ve
ly
,
he
lp
in
g
bus
in
e
s
s
e
s
s
pe
c
if
ic
a
ll
y
s
y
nt
he
s
iz
e
a
nd
pr
oc
e
s
s
da
ta
f
r
om
m
a
ny
di
f
f
e
r
e
nt
s
our
c
e
s
.
M
P
B
I
is
th
e
l
e
a
di
ng
s
ol
ut
io
n
in
th
is
f
ie
ld
;
th
is
f
le
x
ib
le
a
nd
pow
e
r
f
ul
to
ol
a
ll
ow
s
c
om
pl
e
x
da
ta
pr
oc
e
s
s
in
g
in
r
e
a
l
ti
m
e
,
s
uppor
ti
ng
th
e
c
r
e
a
ti
on
of
vi
s
ua
l
da
ta
c
ha
r
ts
th
r
ough
c
ha
r
ts
,
gr
a
phs
,
a
nd
in
te
r
a
c
ti
ve
da
s
hboa
r
ds
.
T
hi
s
vi
s
ua
li
z
a
ti
on
to
ol
c
onne
c
t
s
ta
bul
a
r
d
a
ta
in
di
f
f
e
r
e
nt
s
our
c
e
s
a
nd
da
ta
b
a
s
e
m
a
na
ge
m
e
nt
s
ys
te
m
s
,
r
e
pr
e
s
e
nt
s
th
e
m
a
s
r
e
la
ti
ona
l
da
ta
m
ode
ls
,
a
nd
th
e
n
us
e
s
th
e
m
f
or
vi
s
ua
li
z
a
ti
on.
A
ppl
yi
ng
M
P
B
I
he
lp
s
bus
in
e
s
s
e
s
r
e
s
pond
f
a
s
te
r
a
nd
m
or
e
a
c
c
ur
a
t
e
ly
to
e
m
e
r
gi
ng
tr
e
nds
a
nd
ope
r
a
ti
ona
l
ne
e
ds
by
pr
e
s
e
nt
in
g
da
ta
i
n a
c
le
a
r
a
nd us
e
r
-
f
r
ie
ndl
y f
or
m
a
t.
2.1.
B
u
s
in
e
s
s
in
t
e
ll
ig
e
n
c
e
ap
p
li
c
at
io
n
s
w
it
h
M
ic
r
os
of
t
p
ow
e
r
b
u
s
in
e
s
s
i
n
t
e
ll
ig
e
n
c
e
2.1.1. S
u
p
p
ly
c
h
ai
n
o
p
t
im
iz
a
t
io
n
an
d
d
e
m
an
d
f
or
e
c
a
s
t
in
g
M
P
B
I
is
in
c
r
e
a
s
in
gl
y
us
e
d
in
s
uppl
y
c
ha
in
m
a
na
g
e
m
e
nt
,
e
s
pe
c
ia
ll
y
in
de
m
a
nd
m
oni
to
r
in
g
a
nd
f
or
e
c
a
s
ti
ng.
N
a
bi
l
e
t
al
.
[
1]
de
ve
lo
pe
d
a
r
e
a
l
-
ti
m
e
da
s
hboa
r
d
ba
s
e
d
on
th
e
a
lt
e
r
na
ti
ve
di
s
put
e
r
e
s
ol
ut
io
n
(
ADR
)
m
e
th
od t
o
i
m
pr
ove
s
uppl
y c
ha
in
ope
r
a
ti
ona
l
e
f
f
ic
ie
nc
y.
T
hi
s
s
tu
dy s
how
s
t
ha
t
vi
s
ua
l
e
le
m
e
nt
s
s
uc
h a
s
ke
y
pe
r
f
or
m
a
nc
e
in
di
c
a
to
r
s
(
K
P
I
s
)
a
nd
in
te
r
a
c
ti
v
e
c
ha
r
ts
c
a
n
s
uppor
t
f
a
s
t
a
nd
a
c
c
ur
a
te
de
c
is
io
n
-
m
a
ki
ng.
B
e
lg
hi
th
e
t
al
.
[
2]
bui
lt
a
pha
r
m
a
c
e
ut
ic
a
l
-
s
pe
c
if
ic
f
lo
w
f
or
e
c
a
s
ti
ng
m
od
e
l
us
in
g
P
B
I
to
im
pr
ove
s
a
le
s
f
or
e
c
a
s
ti
ng
a
nd
s
ync
hr
oni
z
e
s
uppl
y
c
h
a
in
a
c
ti
vi
ti
e
s
.
M
oh
a
m
m
e
d
a
nd
P
a
nd
a
[
3]
c
om
bi
ne
d
a
r
ti
f
ic
ia
l
in
te
ll
ig
e
nc
e
(
A
I
)
m
ode
ls
w
it
h
P
B
I
to
e
nha
nc
e
pr
e
di
c
ti
ve
a
na
l
yt
ic
s
in
lo
gi
s
ti
c
s
pl
a
nni
ng.
A
t
th
e
s
a
m
e
ti
m
e
,
H
os
e
n
e
t
al
.
[
4]
e
m
pha
s
iz
e
d
th
e
r
ol
e
of
m
ode
r
n
bus
in
e
s
s
in
t
e
ll
ig
e
nc
e
(
B
I
)
to
ol
s
in
pr
om
ot
in
g
da
ta
-
dr
iv
e
n
de
c
is
io
n
-
m
a
ki
ng
ha
bi
ts
,
c
ont
r
ib
ut
in
g
to
a
m
or
e
e
f
f
ic
ie
nt
a
nd
f
le
xi
bl
e
s
uppl
y
c
h
a
in
.
T
h
e
s
e
s
tu
di
e
s
s
how
th
a
t
P
B
I
is
a
va
lu
a
bl
e
to
ol
f
or
tr
a
ns
f
or
m
in
g
r
e
a
l
-
ti
m
e
da
ta
in
to
i
nf
or
m
a
ti
on
th
a
t
c
a
n
be
us
e
d
im
m
e
di
a
te
ly
in
pr
a
c
ti
c
e
t
hr
ough int
ui
ti
ve
a
nd a
c
c
e
s
s
ib
le
da
s
hbo
a
r
ds
.
2.1.2.
V
is
u
al
d
at
a an
al
ys
is
i
n
r
e
t
ai
l
an
d
e
-
c
om
m
e
r
c
e
I
n
th
e
c
ont
e
xt
of
th
e
r
a
pi
d
de
ve
lo
pm
e
nt
of
r
e
ta
il
a
nd
e
-
c
om
m
e
r
c
e
,
P
B
I
s
uppor
ts
bus
in
e
s
s
e
s
in
m
a
ki
ng
m
or
e
e
f
f
e
c
ti
ve
s
tr
a
te
gi
c
de
c
is
io
ns
.
M
ur
uga
n
e
t
al
.
[
5]
us
e
d
P
B
I
to
a
na
ly
z
e
c
u
s
to
m
e
r
pr
e
f
e
r
e
nc
e
s
a
nd
r
e
gi
ona
l
s
a
le
s
c
ha
ng
e
s
,
h
e
lp
in
g
bus
in
e
s
s
e
s
a
dj
u
s
t
th
e
ir
s
tr
a
te
g
ie
s
to
e
a
c
h
m
a
r
ke
t.
V
is
ua
l
to
ol
s
s
uc
h
a
s
he
a
t
m
a
ps
or
ba
r
c
ha
r
ts
ha
v
e
a
ls
o
he
lp
e
d
im
pr
ove
th
e
e
f
f
e
c
ti
ve
ne
s
s
of
m
a
r
ke
ti
ng
c
a
m
pa
ig
ns
a
nd
in
v
e
nt
or
y
m
a
na
ge
m
e
nt
.
A
lq
ha
ta
ni
e
t
al
.
[
6
]
pr
e
s
e
nt
a
n
in
te
gr
a
ti
on
a
p
pr
oa
c
h
be
twe
e
n
P
B
I
a
nd
m
a
c
hi
ne
le
a
r
ni
ng,
pr
ovi
di
ng
a
hol
is
ti
c
vi
e
w
of
r
e
ta
il
ope
r
a
ti
ons
a
nd
c
ont
r
ib
ut
in
g
to
im
pr
ovi
ng
c
us
to
m
e
r
s
a
ti
s
f
a
c
ti
on.
S
im
il
a
r
ly
,
B
a
ne
r
je
e
e
t
al
.
[
7]
poi
nt
ou
t
a
P
B
I
im
pl
e
m
e
nt
a
ti
on
th
a
t
s
im
pl
if
ie
s
th
e
a
na
ly
s
is
of
s
a
le
s
a
nd
di
s
tr
ib
ut
io
n
da
ta
,
s
uppor
ti
ng
th
e
de
ve
lo
pm
e
nt
of
m
o
r
e
e
f
f
e
c
ti
ve
m
a
r
ke
ti
ng
s
tr
a
te
gi
e
s
.
C
he
n
e
t
al
.
[
8]
e
xt
e
nd
th
e
a
ppl
ic
a
ti
on
o
f
P
B
I
to
pr
e
di
c
ti
ve
m
ode
ls
,
w
hi
c
h
a
r
e
c
lo
s
e
ly
li
nke
d
to
th
e
I
ndus
tr
y
4.0
t
r
e
nd.
Y
a
da
v
e
t
al
.
[
9
]
e
va
lu
a
te
P
B
I
i
n
e
-
c
om
m
e
r
c
e
pe
r
f
or
m
a
nc
e
a
na
ly
s
is
,
w
hi
le
L
a
nde
e
t
al
.
[
10]
e
m
pha
s
iz
e
th
e
a
bi
li
ty
to
in
te
gr
a
te
r
e
a
l
-
ti
m
e
da
ta
to
pe
r
s
ona
li
z
e
c
ons
um
e
r
e
xpe
r
ie
nc
e
s
.
I
n
a
ddi
ti
on,
R
um
hi
a
nd
S
iv
a
kum
a
r
[
11]
ut
i
li
z
e
d
P
B
I
vi
s
ua
li
z
a
ti
ons
to
a
na
ly
z
e
s
up
e
r
m
a
r
ke
t
s
a
le
s
da
ta
,
id
e
nt
if
yi
ng
ke
y
tr
e
nd
s
in
c
us
to
m
e
r
s
a
ti
s
f
a
c
ti
on,
pr
oduc
t
pe
r
f
or
m
a
nc
e
,
a
nd
pa
ym
e
nt
m
e
th
ods
. T
h
e
s
tu
dy pr
opos
e
d t
a
r
ge
te
d
s
tr
a
te
gi
e
s
t
o i
m
pr
ove
s
a
le
s
a
nd
e
nha
nc
e
c
us
to
m
e
r
e
xpe
r
ie
nc
e
.
2.1.3.
R
e
al
-
t
im
e
an
al
yt
ic
s
w
it
h
m
ac
h
in
e
l
e
ar
n
in
g
W
it
h
m
a
c
hi
ne
le
a
r
ni
ng
in
te
gr
a
te
d
in
to
P
B
I
,
bus
in
e
s
s
e
s
c
a
n
e
nh
a
nc
e
r
e
a
l
-
ti
m
e
a
na
ly
ti
c
s
w
it
h
gr
e
a
te
r
f
le
xi
bi
li
ty
a
nd
a
c
c
ur
a
c
y.
M
oha
m
m
e
d
a
nd
P
a
nda
[
3]
pr
opos
e
d
in
te
gr
a
ti
ng
A
I
m
ode
ls
in
to
P
B
I
da
s
hboa
r
ds
to
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
dv A
ppl
S
c
i
I
S
S
N
:
2252
-
8814
O
pt
imi
z
in
g r
e
ta
il
s
y
s
te
m
s
:
us
in
g bi
g data and pow
e
r
bu
s
in
e
s
s
i
nt
e
ll
ig
e
nc
e
…
(
H
uu D
ang
Q
uoc
)
947
im
pr
ove
pr
e
di
c
ti
ve
f
unc
ti
ona
li
ty
,
s
uppor
ti
ng
bus
in
e
s
s
e
s
in
m
a
ki
ng
qui
c
k
de
c
is
io
n
s
ba
s
e
d
on
s
pe
c
if
ic
da
t
a
.
B
y
c
om
bi
ni
ng
vi
s
ua
l
c
ha
r
ts
a
nd
pr
e
di
c
ti
ve
a
lg
or
it
hm
s
,
bus
in
e
s
s
e
s
c
a
n
gr
a
s
p
m
a
r
ke
t
tr
e
nds
m
or
e
a
c
c
ur
a
te
ly
.
N
ik
it
ha
e
t
al
.
[
12
]
in
tr
oduc
e
a
P
B
I
-
ba
s
e
d
s
ys
te
m
in
te
gr
a
te
d
w
it
h
a
dva
nc
e
d
m
a
c
hi
ne
le
a
r
ni
ng
m
ode
ls
(
a
ut
or
e
gr
e
s
s
iv
e
in
te
gr
a
te
d
m
ovi
ng
a
v
e
r
a
ge
(
A
R
I
M
A
)
,
lo
ng
s
h
or
t
-
te
r
m
m
e
m
or
y
(
L
S
T
M
)
,
a
nd
r
a
ndom
f
or
e
s
t
(
RF
)
)
,
e
na
bl
in
g
r
e
a
l
-
ti
m
e
,
in
te
r
a
c
ti
ve
f
or
e
c
a
s
ti
ng.
T
he
m
ode
ls
a
c
hi
e
ve
d
hi
gh
a
c
c
ur
a
c
y
a
nd
lo
w
e
r
r
or
r
a
te
s
,
of
f
e
r
in
g
a
c
ti
ona
bl
e
in
s
ig
ht
s
f
or
bus
in
e
s
s
de
c
is
io
n
-
m
a
ki
ng.
S
ur
w
a
de
e
t
al
.
[
13]
a
ls
o
e
m
pha
s
i
z
e
d
th
e
r
ol
e
of
a
dva
nc
e
d
pr
e
di
c
ti
ve
a
lg
or
it
hm
s
in
in
c
r
e
a
s
in
g
s
uppl
y
c
ha
in
r
e
s
pons
iv
e
ne
s
s
.
F
in
a
ll
y,
J
a
m
e
s
e
t
al
.
[
14]
di
s
c
us
s
e
d
th
e
c
om
bi
na
ti
on
of
P
B
I
w
it
h
bi
g
da
ta
a
na
ly
ti
c
s
to
s
u
ppor
t
or
ga
ni
z
a
ti
ons
in
m
a
ki
ng
m
or
e
e
f
f
e
c
ti
ve
s
tr
a
te
gi
c
de
c
is
io
n
s
.
2.1.4.
P
ow
e
r
b
u
s
in
e
s
s
i
n
t
e
ll
ig
e
n
c
e
w
it
h
t
h
e
in
t
e
r
n
e
t
of
t
h
in
gs
I
nt
e
gr
a
ti
ng
M
P
B
I
a
nd
th
e
in
te
r
ne
t
of
th
in
gs
(
I
oT
)
o
f
f
e
r
s
n
e
w
a
ppr
oa
c
he
s
to
pr
oc
e
s
s
in
g
la
r
ge
vol
um
e
s
of
da
ta
ge
ne
r
a
te
d by s
e
ns
or
s
ys
te
m
s
. R
a
i
e
t
al
.
[
15]
e
m
pha
s
iz
e
t
he
r
ol
e
of
P
B
I
in
vi
s
ua
li
z
in
g bi
g da
ta
in
th
e
I
oT
e
c
os
y
s
te
m
,
e
s
pe
c
ia
ll
y
f
or
r
e
a
l
-
ti
m
e
m
oni
to
r
in
g
a
nd
de
c
is
io
n
-
m
a
ki
ng.
L
ib
by
e
t
al
.
[
16]
a
ls
o
e
xpl
or
e
how
P
B
I
c
a
n
be
in
te
gr
a
te
d
in
to
lo
gi
s
ti
c
s
ope
r
a
ti
ons
,
us
in
g
I
oT
da
ta
to
im
pr
ove
ope
r
a
ti
ona
l
vi
s
ib
il
i
ty
a
nd
pe
r
f
or
m
a
nc
e
m
oni
to
r
in
g.
2.1.5.
A
p
p
li
c
at
io
n
s
i
n
s
p
e
c
ia
li
z
e
d
i
n
d
u
s
t
r
ie
s
I
n
a
ddi
ti
on
to
tr
a
di
t
io
na
l
da
ta
a
ppl
ic
a
ti
ons
,
M
P
B
I
c
a
n
be
a
ppl
ie
d
to
s
pe
c
ia
li
z
e
d
s
e
c
to
r
s
or
in
dus
tr
ie
s
.
S
e
to
e
t
al
.
[
17]
s
tu
d
ie
d
in
te
gr
a
ti
on
w
it
h
e
nt
e
r
pr
is
e
r
e
s
our
c
e
pl
a
nni
ng
(
E
R
P
)
s
ys
te
m
s
in
th
e
m
in
in
g
in
dus
tr
y
to
m
a
ke
de
c
is
io
ns
a
bout
f
ue
l
c
ons
um
pt
io
n a
nd i
nve
nt
or
y r
e
pl
e
ni
s
hm
e
nt
. A
m
e
e
r
e
t
al
.
[
18]
a
ppl
ie
d P
B
I
t
o huma
n
r
e
s
our
c
e
a
na
ly
s
is
,
ut
il
iz
in
g
da
s
hbo
a
r
ds
to
r
e
duc
e
e
m
pl
oye
e
tu
r
nove
r
a
nd
im
pr
ove
e
v
a
lu
a
ti
on
m
e
tr
ic
s
.
T
h
e
r
e
a
r
e
s
tu
di
e
s
on
th
e
a
ppl
ic
a
ti
on
of
bus
in
e
s
s
da
ta
vi
s
ua
li
z
a
ti
on
c
a
pa
bi
li
ti
e
s
f
or
onl
in
e
bus
in
e
s
s
s
ys
te
m
s
.
A
na
r
da
ni
e
t
al
.
[
19
]
p
r
opos
e
d
us
in
g
P
B
I
to
a
na
ly
z
e
s
a
le
s
tr
e
nds
f
or
f
is
hi
ng
ge
a
r
a
nd
e
nha
nc
e
in
ve
nt
or
y
opt
im
iz
a
ti
on
a
nd
m
a
r
ke
ti
ng.
S
hubho
e
t
al
.
[
20]
de
ta
il
e
d
i
ts
im
p
a
c
t
on
s
m
a
ll
a
nd
m
e
di
um
e
nt
e
r
pr
is
e
s
(
S
M
E
s
)
,
im
pr
ovi
ng
ope
r
a
ti
ons
a
nd
f
in
a
nc
ia
l
pl
a
nni
ng
tr
a
ns
pa
r
e
nc
y.
I
n
a
ddi
ti
on,
da
ta
vi
s
ua
li
z
a
ti
on
c
a
n
be
a
ppl
ie
d
in
s
e
ve
r
a
l
ot
he
r
a
r
e
a
s
.
S
ha
r
m
a
e
t
al
.
[
21]
c
om
pa
r
e
d
PB
I
w
it
h
ot
he
r
B
I
pl
a
tf
or
m
s
,
e
m
pha
s
iz
in
g
th
e
s
upe
r
io
r
it
y
of
vi
s
ua
li
z
a
ti
on
f
or
c
om
pl
e
x
d
a
ta
s
e
ts
.
R
ui
z
e
t
al
.
[
22]
de
m
on
s
tr
a
t
e
d
th
e
tr
e
nd
-
f
or
e
c
a
s
ti
ng
c
a
pa
bi
li
ti
e
s
of
P
B
I
in
th
e
ga
m
in
g
in
dus
tr
y.
S
e
to
e
t
al
.
[
17]
f
ur
th
e
r
de
ve
lo
pe
d
th
e
ir
a
ppl
ic
a
ti
on
in
hum
a
n
r
e
s
our
c
e
a
na
ly
ti
c
s
,
hi
ghl
ig
ht
in
g pr
e
di
c
ti
ve
us
e
c
a
s
e
s
f
or
e
m
pl
oye
e
e
nga
ge
m
e
nt
a
nd
t
ur
nove
r
.
2.2.
D
at
a w
ar
e
h
ou
s
in
g
A
da
t
a
w
a
r
e
hou
s
e
is
a
c
e
nt
r
a
li
z
e
d
da
t
a
s
to
r
a
ge
s
y
s
t
e
m
d
e
s
i
gne
d
to
s
up
por
t
a
na
l
ys
i
s
,
r
e
por
ti
n
g,
a
nd
de
c
i
s
io
n
-
m
a
ki
ng
w
it
hi
n
a
n or
ga
ni
z
a
ti
on. U
nl
ik
e
a
n o
pe
r
a
t
io
na
l
d
a
ta
b
a
s
e
t
h
a
t
pr
oc
e
s
s
e
s
d
a
y
-
to
-
d
a
y t
r
a
ns
a
c
ti
ons
,
a
d
a
ta
w
a
r
e
ho
us
e
s
to
r
e
s
hi
s
to
r
ic
a
l
da
t
a
pr
oc
e
s
s
e
d
a
nd
in
te
gr
a
te
d
f
r
om
v
a
r
io
u
s
s
o
ur
c
e
s
s
u
c
h
a
s
a
n
E
R
P
s
y
s
t
e
m
,
c
us
t
om
e
r
r
e
la
ti
on
s
hi
p
m
a
n
a
ge
m
e
nt
(
C
R
M
)
pl
a
tf
or
m
,
or
E
xc
e
l
s
pr
e
a
d
s
h
e
e
t.
D
a
ta
is
of
te
n
or
g
a
ni
z
e
d
us
in
g
m
ode
l
s
s
uc
h a
s
a
s
ta
r
or
s
n
ow
f
la
ke
s
c
h
e
m
a
to
f
a
c
il
it
a
te
e
f
f
ic
i
e
nt
que
r
yi
n
g
a
n
d
a
n
a
ly
s
is
. T
hi
s
a
ll
o
w
s
bu
s
in
e
s
s
e
s
to
qui
c
kl
y
c
on
s
ol
id
a
te
in
f
or
m
a
ti
on,
a
n
a
ly
z
e
tr
e
nd
s
,
e
va
lu
a
te
pe
r
f
or
m
a
nc
e
,
a
nd
g
e
ne
r
a
te
m
a
n
a
ge
m
e
nt
r
e
por
t
s
.
A
s
a
c
or
e
c
om
pon
e
nt
of
a
B
I
s
y
s
te
m
,
a
d
a
ta
w
a
r
e
hou
s
e
be
c
o
m
e
s
e
s
pe
c
ia
ll
y
pow
e
r
f
ul
w
h
e
n
c
om
bi
n
e
d
w
i
th
to
ol
s
l
ik
e
M
P
B
I
, a
ll
ow
in
g
us
e
r
s
t
o vi
s
u
a
li
z
e
d
a
ta
a
nd m
a
k
e
t
im
e
l
y, da
t
a
-
dr
iv
e
n d
e
c
i
s
io
n
s
.
I
ni
ti
a
ll
y,
da
ta
w
a
r
e
hous
e
s
w
e
r
e
us
e
d
to
m
e
e
t
th
e
ne
e
d
to
s
to
r
e
la
r
ge
a
m
ount
s
of
da
ta
in
va
r
io
us
f
unc
ti
ons
.
T
he
pr
im
a
r
y
pur
pos
e
of
a
da
ta
w
a
r
e
hous
e
is
to
pr
ovi
de
a
s
tr
uc
tu
r
e
d
r
e
po
s
it
or
y
th
a
t
s
uppor
ts
a
na
ly
ti
c
a
l
a
nd
m
a
na
ge
m
e
nt
f
unc
ti
ons
[
10]
.
I
t
a
c
ts
a
s
a
n
e
l
e
c
tr
oni
c
a
ll
y
m
a
na
ge
d
da
ta
c
e
nt
e
r
th
a
t
a
ll
ow
s
or
ga
ni
z
a
ti
ons
to
a
ggr
e
ga
te
in
f
or
m
a
ti
on
f
r
om
va
r
io
us
s
our
c
e
s
,
pr
e
pr
oc
e
s
s
,
a
nd
s
tr
uc
tu
r
e
it
in
a
uni
f
ie
d
m
a
nne
r
f
or
on
-
de
m
a
nd
us
e
,
r
e
por
t
s
ynt
he
s
is
,
a
nd
da
ta
a
n
a
ly
s
is
[
11]
.
F
or
c
or
por
a
ti
ons
ope
r
a
ti
ng
in
m
a
ny
f
ie
ld
s
,
da
ta
w
a
r
e
hous
e
s
he
lp
c
onve
ni
e
nt
ly
or
ga
ni
z
e
a
nd
s
to
r
e
da
ta
f
or
t
he
e
nt
ir
e
bus
in
e
s
s
e
c
o
s
ys
te
m
,
c
r
e
a
ti
ng
la
r
ge
,
c
ont
in
uous
ly
e
m
e
r
gi
ng
da
t
a
w
a
r
e
hou
s
e
s
.
D
a
ta
m
in
in
g
c
a
n
th
e
n
be
a
ppl
ie
d
in
br
oa
de
r
w
a
ys
,
s
uc
h
a
s
or
ga
ni
z
in
g
a
nd
us
in
g
onl
in
e
a
na
ly
ti
c
a
l
p
r
oc
e
s
s
in
g
(
O
L
A
P
)
m
ode
ls
a
nd
a
ppl
yi
ng
a
lg
or
it
hm
s
to
p
r
e
di
c
t
bus
in
e
s
s
s
it
ua
ti
ons
i
n r
e
a
l
ti
m
e
[
23]
, [
24]
.
D
a
ta
w
a
r
e
hous
e
s
a
r
e
vi
ta
l
in
s
uppor
ti
ng
BI
pr
oc
e
s
s
e
s
i
n t
oda
y'
s
or
ga
ni
z
a
ti
ons
. T
he
y f
a
c
il
it
a
te
pa
tt
e
r
n
r
e
c
ogni
ti
on,
tr
e
nd
a
na
ly
s
is
,
f
or
e
c
a
s
ti
ng,
a
nd
s
tr
a
te
gi
c
pl
a
nni
ng
a
c
r
os
s
di
f
f
e
r
e
nt
de
pa
r
tm
e
nt
s
.
W
he
n
in
te
gr
a
te
d
w
it
h
to
ol
s
li
ke
M
P
B
I
,
da
ta
w
a
r
e
hous
e
s
e
na
bl
e
us
e
r
s
to
tr
a
ns
f
or
m
c
om
pl
e
x,
m
ul
ti
di
m
e
ns
io
na
l
da
ta
s
e
ts
in
to
c
le
a
r
,
a
c
ti
ona
bl
e
in
s
ig
ht
s
.
T
hi
s
c
om
bi
na
ti
on
e
nha
nc
e
s
a
n
or
ga
ni
z
a
ti
on'
s
r
e
s
pons
iv
e
ne
s
s
a
nd
c
om
pe
ti
ti
ve
ne
s
s
by
he
lp
in
g
to
opt
im
iz
e
ope
r
a
ti
ons
,
m
a
na
ge
r
is
ks
,
a
nd
c
a
pt
ur
e
gr
ow
th
oppor
tu
ni
ti
e
s
in
a
n
in
c
r
e
a
s
in
gl
y
da
ta
-
dr
iv
e
n m
a
r
ke
tp
la
c
e
.
2.3.
S
t
r
e
am
in
g E
T
L
:
a r
e
al
-
t
im
e
al
t
e
r
n
at
iv
e
t
o t
r
ad
it
io
n
al
ETL
I
n
tr
a
di
ti
o
na
l
d
a
t
a
in
te
gr
a
ti
o
n
w
or
kf
lo
w
s
,
E
T
L
h
a
s
l
ong
b
e
e
n
th
e
d
om
i
na
nt
p
a
r
a
di
gm
.
E
T
L
pr
o
c
e
s
s
e
s
ty
pi
c
a
ll
y
o
pe
r
a
t
e
i
n
b
a
t
c
h m
od
e
,
e
xt
r
a
c
ti
n
g
l
a
r
g
e
v
ol
u
m
e
s
of
d
a
t
a
a
t
s
c
he
dul
e
d
in
te
r
va
ls
(
e
.g
.,
h
our
ly
a
n
d
d
a
il
y)
,
tr
a
ns
f
or
m
in
g
th
e
m
th
r
ough
pr
e
de
f
in
e
d
r
ul
e
s
,
a
nd
lo
a
di
ng
th
e
m
in
to
a
ta
r
ge
t
s
ys
te
m
s
uc
h
a
s
a
da
t
a
w
a
r
e
hou
s
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8814
I
nt
J
A
dv A
ppl
S
c
i
,
V
ol
.
14
, N
o.
3
,
S
e
pt
e
m
be
r
20
25
:
945
-
954
948
or
da
ta
m
a
r
t.
W
hi
le
e
f
f
e
c
ti
ve
f
or
m
a
ny
bus
in
e
s
s
s
c
e
n
a
r
io
s
,
ba
tc
h
-
ba
s
e
d
E
T
L
s
uf
f
e
r
s
f
r
om
la
te
nc
y
a
nd
is
ill
-
s
ui
te
d
f
or
e
nvi
r
onm
e
nt
s
th
a
t
de
m
a
nd
im
m
e
di
a
te
vi
s
ib
il
it
y
in
to
da
ta
.
I
n
c
ont
r
a
s
t,
s
tr
e
a
m
in
g
E
T
L
[
25]
,
[
26
]
is
a
m
ode
r
n
a
lt
e
r
na
ti
ve
de
s
ig
ne
d
f
or
r
e
a
l
-
ti
m
e
or
ne
a
r
-
r
e
a
l
-
ti
m
e
da
ta
pr
oc
e
s
s
in
g.
R
a
th
e
r
th
a
n
w
a
it
in
g
f
or
da
ta
to
a
c
c
um
ul
a
te
in
to
b
a
tc
he
s
,
s
tr
e
a
m
in
g
E
T
L
in
ge
s
ts
a
nd
pr
oc
e
s
s
e
s
e
a
c
h
da
ta
e
ve
nt
a
s
it
oc
c
ur
s
. T
hi
s
s
hi
f
t
f
r
om
ba
tc
h
to
s
tr
e
a
m
pr
oc
e
s
s
in
g
s
ig
ni
f
ic
a
nt
ly
r
e
duc
e
s
d
a
ta
la
te
nc
y
,
e
na
bl
in
g
or
ga
ni
z
a
ti
ons
to
r
e
s
pond
f
a
s
te
r
to
ope
r
a
ti
ona
l
c
ha
nge
s
,
c
u
s
to
m
e
r
be
h
a
vi
or
s
,
a
nd
m
a
r
ke
t
dyn
a
m
ic
s
.
T
he
ke
y
di
f
f
e
r
e
nc
e
s
b
e
twe
e
n
tr
a
di
ti
ona
l
E
T
L
a
nd s
tr
e
a
m
in
g E
T
L
a
r
e
out
li
ne
d i
n T
a
bl
e
1.
S
tr
e
a
m
in
g
E
T
L
of
f
e
r
s
s
e
ve
r
a
l
a
dva
nt
a
ge
s
f
or
bus
in
e
s
s
e
s
th
a
t
ne
e
d
to
a
na
ly
z
e
a
nd
a
c
t
on
ti
m
e
-
s
e
ns
it
iv
e
da
ta
.
F
or
in
s
ta
nc
e
,
in
th
e
r
e
ta
il
in
dus
tr
y,
r
e
a
l
-
ti
m
e
pr
oc
e
s
s
in
g
a
ll
ow
s
f
or
im
m
e
di
a
te
in
ve
nt
or
y
upda
te
s
,
dyna
m
ic
pr
ic
in
g
s
tr
a
te
gi
e
s
,
a
nd
pe
r
s
ona
li
z
e
d
c
u
s
to
m
e
r
e
nga
ge
m
e
nt
ba
s
e
d
on
r
e
c
e
nt
a
c
ti
vi
ty
.
T
he
s
e
c
a
pa
bi
li
ti
e
s
a
r
e
of
te
n
not
f
e
a
s
ib
le
w
it
h
tr
a
di
ti
ona
l
E
T
L
due
to
it
s
in
he
r
e
nt
de
la
ys
.
T
o
im
pl
e
m
e
nt
s
tr
e
a
m
in
g
E
T
L
e
f
f
e
c
ti
ve
ly
,
or
ga
ni
z
a
ti
ons
of
te
n
r
e
ly
on
e
ve
nt
-
d
r
iv
e
n
a
r
c
hi
te
c
tu
r
e
s
a
nd
te
c
hnol
ogi
e
s
th
a
t
s
uppor
t
hi
gh
-
th
r
oughput,
lo
w
-
la
te
nc
y
da
ta
f
lo
w
s
.
T
ool
s
s
uc
h
a
s
A
pa
c
he
K
a
f
ka
s
e
r
ve
a
s
th
e
ba
c
kbone
f
or
m
e
s
s
a
ge
s
tr
e
a
m
in
g,
w
hi
le
pl
a
tf
or
m
s
li
ke
A
pa
c
he
F
li
nk
or
S
pa
r
k
S
tr
uc
tu
r
e
d
S
tr
e
a
m
in
g
pe
r
f
or
m
tr
a
ns
f
or
m
a
ti
ons
on
-
th
e
-
f
ly
.
C
om
bi
ne
d
w
it
h
a
na
ly
ti
c
s
to
ol
s
li
ke
M
P
B
I
,
th
e
s
e
pi
pe
li
ne
s
e
na
bl
e
de
c
is
io
n
-
m
a
ke
r
s
to
m
oni
to
r
K
P
I
s
a
nd
de
r
iv
e
in
s
ig
ht
s
in
r
e
a
l
ti
m
e
.
W
hi
le
tr
a
di
ti
ona
l
E
T
L
r
e
m
a
in
s
us
e
f
ul
f
or
m
a
ny
s
c
e
na
r
io
s
in
vol
vi
ng
s
tr
uc
tu
r
e
d,
s
ta
bl
e
da
ta
s
e
ts
a
nd
pe
r
io
di
c
a
na
ly
s
is
,
it
is
in
c
r
e
a
s
in
gl
y
in
a
de
qua
te
f
or
to
da
y'
s
dyna
m
ic
,
d
a
ta
-
in
te
ns
iv
e
e
nvi
r
onm
e
nt
s
.
S
tr
e
a
m
in
g
E
T
L
f
il
ls
th
is
ga
p
by
of
f
e
r
in
g
a
lo
w
-
la
te
nc
y,
c
ont
in
uous
pr
oc
e
s
s
in
g
a
lt
e
r
na
ti
ve
th
a
t
a
li
gns
w
it
h
m
ode
r
n
bus
in
e
s
s
de
m
a
nds
f
or
r
e
a
l
-
t
im
e
in
s
ig
ht
s
a
nd
r
e
s
pons
iv
e
ne
s
s
.
A
s
di
gi
ta
l
tr
a
ns
f
or
m
a
ti
on
a
c
c
e
le
r
a
te
s
a
c
r
os
s
i
ndus
tr
ie
s
, t
he
a
dopt
io
n of
s
tr
e
a
m
in
g E
T
L
i
s
be
c
om
in
g a
ke
y e
na
bl
e
r
f
or
da
ta
-
dr
iv
e
n a
gi
li
ty
a
nd c
om
pe
ti
ti
ve
a
dva
nt
a
ge
.
T
a
bl
e
1. K
e
y
di
f
f
e
r
e
nc
e
s
be
twe
e
n
E
T
L
a
nd
s
tr
e
a
m
in
g
E
T
L
A
s
pe
c
t
T
r
a
di
t
i
ona
l
E
T
L
S
t
r
e
a
m
i
ng E
T
L
P
r
oc
e
s
s
i
ng m
ode
B
a
t
c
h
R
e
a
l
-
t
i
m
e
(
e
ve
nt
-
by
-
e
ve
nt
)
L
a
t
e
nc
y
H
i
gh (
m
i
nut
e
s
t
o
hour
s
)
L
ow
(
m
i
l
l
i
s
e
c
onds
t
o s
e
c
onds
)
D
a
t
a
f
r
e
s
hne
s
s
P
e
r
i
odi
c
upda
t
e
s
C
ont
i
nuous
upda
t
e
s
U
s
e
c
a
s
e
s
H
i
s
t
or
i
c
a
l
r
e
por
t
i
ng, r
e
gul
a
t
or
y c
om
pl
i
a
nc
e
R
e
a
l
-
t
i
m
e
a
na
l
yt
i
c
s
, f
r
a
ud de
t
e
c
t
i
on, pe
r
s
ona
l
i
z
e
d of
f
e
r
s
I
nf
r
a
s
t
r
uc
t
ur
e
r
e
qui
r
e
m
e
nt
s
S
i
m
pl
e
r
;
s
ui
t
a
bl
e
f
or
pe
r
i
odi
c
j
obs
R
e
qui
r
e
s
a
s
c
a
l
a
bl
e
, f
a
ul
t
-
t
ol
e
r
a
nt
s
t
r
e
a
m
i
ng a
r
c
hi
t
e
c
t
ur
e
T
ool
s
T
a
l
e
nd,
I
nf
or
m
a
t
i
c
a
, S
S
I
S
A
pa
c
he
K
a
f
ka
, S
pa
r
k S
t
r
e
a
m
i
ng, F
l
i
nk, D
e
be
z
i
um
3.
M
O
D
E
L
I
N
G
A
N
D
A
G
G
R
E
G
A
T
I
N
G
R
E
T
A
I
L
D
A
T
A
F
O
R
D
E
C
I
S
I
O
N
S
U
P
P
O
R
T
I
n
a
m
a
na
ge
m
e
nt
in
f
or
m
a
ti
on
s
ys
t
e
m
,
w
hi
c
h
is
u
s
e
d
in
r
e
ta
i
l
s
ys
te
m
s
,
bui
ld
in
g
a
good
d
a
ta
ba
s
e
s
tr
uc
tu
r
e
pl
a
ys
a
f
unda
m
e
nt
a
l
r
ol
e
in
s
to
r
in
g,
m
a
na
gi
ng,
a
n
d
e
xpl
oi
ti
ng
da
ta
.
T
he
la
r
ge
a
nd
c
ont
in
uous
vol
um
e
of
da
ta
f
r
om
s
a
le
s
tr
a
ns
a
c
ti
ons
,
in
ve
nt
or
y
m
a
na
ge
m
e
nt
,
de
bt
,
pr
om
ot
io
n
pr
og
r
a
m
s
,
a
nd
c
ons
um
e
r
be
ha
vi
or
r
e
qui
r
e
s
a
s
c
ie
nt
if
ic
a
ll
y
de
s
ig
ne
d,
uni
f
ie
d
s
to
r
a
ge
a
r
c
hi
te
c
tu
r
e
to
or
ga
ni
z
e
a
nd
r
e
tr
ie
ve
in
f
or
m
a
ti
on
e
f
f
e
c
ti
ve
ly
.
A
w
e
ll
-
de
s
ig
ne
d
da
ta
ba
s
e
s
tr
uc
tu
r
e
he
lp
s
e
ns
ur
e
d
a
ta
c
ons
is
te
nc
y
a
nd
in
te
gr
it
y
w
hi
le
f
a
c
il
it
a
ti
ng
da
ta
in
te
gr
a
ti
on
f
r
om
m
a
ny s
our
c
e
s
. T
hi
s
i
s
e
s
pe
c
i
a
ll
y
im
por
ta
nt
i
n t
he
r
e
ta
il
e
nvi
r
on
m
e
nt
, w
he
r
e
i
n
f
or
m
a
ti
on
ne
e
ds
to
be
pr
oc
e
s
s
e
d
qui
c
kl
y
to
m
a
ke
ti
m
e
ly
de
c
is
io
ns
.
O
r
ga
ni
z
in
g
da
ta
a
c
c
or
di
ng
to
a
c
le
a
r
r
e
la
ti
ona
l
m
ode
l
a
ls
o
he
lp
s
to
m
in
im
iz
e
dupl
ic
a
ti
on,
im
pr
ove
qu
e
r
y
pe
r
f
or
m
a
nc
e
,
a
nd
s
uppor
t
m
or
e
s
ta
bl
e
a
na
ly
s
i
s
to
ol
s
.
F
ur
th
e
r
m
or
e
,
a
w
e
ll
-
s
tr
uc
tu
r
e
d
da
ta
ba
s
e
is
th
e
f
ounda
ti
o
n
f
or
a
dva
nc
e
d
a
na
ly
ti
c
s
a
ppl
ic
a
ti
ons
s
uc
h
a
s
de
m
a
nd
f
or
e
c
a
s
ti
ng,
in
ve
nt
or
y
opt
im
iz
a
ti
on,
a
nd
c
u
s
to
m
e
r
be
h
a
vi
or
a
na
ly
s
is
.
W
he
n
c
om
bi
ne
d
w
it
h
BI
to
ol
s
s
uc
h a
s
P
B
I
, a
c
le
a
r
da
ta
s
tr
uc
tu
r
e
he
lp
s
vi
s
ua
li
z
e
i
nf
or
m
a
ti
on f
l
e
xi
bl
y a
nd s
uppor
ts
s
tr
a
te
gi
c
de
c
i
s
io
n
-
m
a
ki
ng
a
t
th
e
m
a
na
ge
m
e
nt
l
e
ve
l.
3.1.
R
e
la
t
io
n
al
d
at
ab
as
e
T
o
m
e
e
t
th
e
r
e
qui
r
e
m
e
nt
s
of
da
ta
s
to
r
a
ge
a
nd
m
a
na
g
e
m
e
nt
in
th
e
r
e
ta
il
s
ys
t
e
m
,
w
e
d
e
s
ig
ne
d
a
r
e
la
ti
ona
l
da
ta
ba
s
e
m
od
e
l
c
ons
i
s
ti
ng
of
s
e
ve
n
c
or
e
e
nt
it
ie
s
.
T
he
s
e
e
nt
it
ie
s
r
e
pr
e
s
e
nt
ke
y
c
om
pone
nt
s
of
bus
in
e
s
s
ope
r
a
ti
ons
,
pl
a
yi
ng
a
c
e
nt
r
a
l
r
ol
e
in
c
ol
le
c
ti
ng,
s
to
r
in
g,
a
nd
or
ga
ni
z
in
g
in
f
or
m
a
ti
on.
E
a
c
h
da
ta
ta
bl
e
r
e
f
le
c
ts
a
s
e
pa
r
a
te
a
s
pe
c
t
of
pr
oduc
ts
,
c
us
to
m
e
r
s
,
tr
a
ns
a
c
ti
ons
,
a
nd
e
m
pl
oye
e
s
,
but
th
e
y
a
r
e
s
im
ul
ta
ne
ous
ly
ti
ght
ly
l
in
ke
d t
o e
ns
ur
e
t
he
da
ta
f
lo
w
i
s
c
onne
c
te
d t
hr
oughout t
he
s
ys
te
m
.
B
ui
ld
in
g
lo
gi
c
a
l
r
e
la
ti
ons
hi
ps
be
twe
e
n
ta
bl
e
s
he
lp
s
e
ns
ur
e
da
ta
in
te
gr
it
y
w
hi
le
a
ll
ow
in
g
f
o
r
m
or
e
e
f
f
ic
ie
nt
a
nd
f
le
xi
bl
e
que
r
ie
s
dur
in
g
in
f
or
m
a
ti
on
m
in
in
g.
T
hi
s
r
e
la
ti
ona
l
de
s
ig
n
a
ls
o
he
lp
s
th
e
s
ys
te
m
a
c
c
ur
a
te
ly
r
e
f
le
c
t
th
e
a
c
tu
a
l
ope
r
a
ti
ng
pr
oc
e
s
s
e
s
in
th
e
r
e
ta
il
e
nvi
r
onm
e
nt
,
f
r
om
in
ve
nt
or
y
m
a
na
ge
m
e
nt
to
s
a
le
s
tr
a
c
ki
ng
a
nd
c
ons
um
e
r
be
ha
vi
or
a
na
ly
s
i
s
.
T
h
a
nks
to
th
i
s
s
tr
uc
tu
r
e
,
da
ta
i
s
s
to
r
e
d
s
y
s
te
m
a
ti
c
a
ll
y
a
nd
r
e
a
dy
to
s
e
r
ve
a
na
ly
s
is
,
r
e
por
ti
ng,
a
nd
de
c
i
s
io
n
s
uppor
t
a
c
t
iv
it
ie
s
.
F
ig
ur
e
1
il
lu
s
tr
a
te
s
th
e
r
e
la
ti
ons
hi
ps
be
twe
e
n
da
ta
e
nt
it
ie
s
in
th
e
s
ys
te
m
,
s
how
in
g
how
th
e
y
in
te
r
a
c
t
a
nd
f
or
m
a
n
in
te
gr
a
te
d,
un
if
ie
d
da
ta
m
ode
l
.
T
hi
s
s
tr
uc
tu
r
e
is
th
e
f
ounda
ti
on
f
or
de
ve
lo
pi
ng
a
dva
nc
e
d
a
na
ly
ti
c
a
l
f
unc
ti
ons
,
th
e
r
e
by
im
pr
ovi
ng
m
a
na
ge
m
e
nt
e
f
f
ic
ie
nc
y a
nd quic
kl
y r
e
s
ponding t
o m
a
r
ke
t
f
lu
c
t
ua
ti
ons
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
dv A
ppl
S
c
i
I
S
S
N
:
2252
-
8814
O
pt
imi
z
in
g r
e
ta
il
s
y
s
te
m
s
:
us
in
g bi
g data and pow
e
r
bu
s
in
e
s
s
i
nt
e
ll
ig
e
nc
e
…
(
H
uu D
ang
Q
uoc
)
949
F
ig
ur
e
1. R
e
la
ti
ona
l
da
ta
ba
s
e
s
to
r
in
g da
ta
3.2.
F
or
m
u
la
s
f
or
d
at
a c
o
m
p
u
t
at
io
n
an
d
aggr
e
gat
io
n
I
n t
hi
s
a
n
a
l
ys
i
s
, w
e
pr
op
o
s
e
t
o b
ui
l
d m
a
th
e
m
a
ti
c
a
l
f
or
m
ul
a
s
t
o
c
a
lc
u
la
te
bu
s
in
e
s
s
r
e
s
ul
t
s
b
a
s
e
d o
n d
a
il
y
ge
n
e
r
a
t
e
d
da
t
a
,
w
h
ic
h
w
il
l
be
r
e
n
de
r
e
d
a
s
i
npu
t
f
or
M
P
B
I
t
o
b
ui
ld
vi
s
u
a
l
c
h
a
r
t
s
.
T
h
e
s
e
f
o
r
m
u
la
s
a
r
e
th
e
m
a
in
c
on
s
tr
a
in
t
s
i
n
im
pl
e
m
e
nt
i
ng
r
e
t
a
il
da
ta
c
a
lc
ul
a
ti
on
a
nd
s
y
nt
he
s
i
s
pr
o
c
e
s
s
e
s
.
T
hr
o
ug
h
th
is
,
th
e
d
a
t
a
i
s
g
ua
r
a
n
te
e
d
to
be
a
c
c
ur
a
t
e
w
h
e
n
s
y
nt
h
e
s
i
z
in
g
a
n
d
a
n
a
l
yz
in
g
d
a
t
a
a
c
r
o
s
s
th
e
e
nt
ir
e
r
e
ta
i
l
s
ys
te
m
,
e
ns
ur
i
ng
c
on
s
i
s
t
e
n
c
y
a
nd
tr
a
n
s
pa
r
e
n
c
y
i
n t
he
bu
s
in
e
s
s
o
pe
r
a
ti
on
s
of
r
e
t
a
i
l
e
nt
e
r
p
r
i
s
e
s
.
T
h
e
c
on
s
tr
a
in
t
s
a
r
e
s
how
n
in
T
a
b
le
2.
T
a
bl
e
2.
T
he
c
ons
tr
a
in
ts
i
n t
he
r
e
t
a
il
s
ys
te
m
F
or
m
ul
a
D
e
s
c
r
i
pt
i
on
=
∑
=
0
D
e
t
e
r
m
i
ni
ng t
he
num
be
r
of
pr
oduc
t
s
l
i
s
t
e
d i
n a
n i
nvoi
c
e
.
=
∑
=
0
C
a
l
c
ul
a
t
i
ng t
he
t
ot
a
l
pa
ya
bl
e
a
m
ount
f
or
a
n i
nvoi
c
e
.
=
∑
=
0
.
.
∀
T
i
:
∊
{
0.08;
0.1
}
C
om
put
i
ng t
he
t
a
x a
m
ount
on a
n i
nvoi
c
e
, us
i
ng e
i
t
he
r
a
0, 5, 8, or
10%
.
=
∑
=
0
.
.
∀
∊
ℝ
A
ppl
yi
ng a
di
s
c
ount
t
o t
he
t
ot
a
l
i
nvoi
c
e
va
l
ue
.
=
∑
+
−
2
=
1
,
∀
l
=
20
S
um
m
i
ng up t
he
t
ot
a
l
r
e
ve
nue
ge
ne
r
a
t
e
d w
i
t
hi
n a
s
pe
c
i
f
i
e
d da
t
e
r
a
nge
.
=
∑
2
=
1
∑
2
=
1
,
∀
l
=
10
F
i
ndi
ng t
he
a
ve
r
a
ge
pur
c
ha
s
e
c
o
s
t
of
s
e
l
l
e
d pr
oduc
t
s
.
=
∑
∑
.
.
=
1
2
=
1
,
∀
l
=
20
C
a
l
c
ul
a
t
i
ng t
he
t
ot
a
l
pur
c
ha
s
e
e
xp
e
ns
e
s
a
s
s
oc
i
a
t
e
d w
i
t
h
s
e
l
l
e
d pr
oduc
t
s
.
=
−
M
e
a
s
ur
i
ng t
he
ove
r
a
l
l
pr
of
i
t
e
a
r
ne
d dur
i
ng a
gi
ve
n pe
r
i
od.
W
he
r
e
Sₖ
is
to
ta
l
num
be
r
of
i
te
m
s
l
is
te
d i
n
in
voi
c
e
k
,
Sᵢ
is
qua
nt
it
y
of
t
he
pr
oduc
t
in
e
nt
r
y i
of
a
i
nvoi
c
e
,
Mₖ
is
to
ta
l
pa
ya
bl
e
a
m
ount
f
or
in
voi
c
e
k
,
Mᵢ
is
c
os
t
a
s
s
o
c
ia
te
d
w
it
h
e
nt
r
y
i
in
th
e
in
vo
ic
e
,
Pᵢ
is
uni
t
pr
ic
e
of
th
e
pr
oduc
t
in
e
nt
r
y
I
,
Tₖ
is
to
ta
l
ta
x
a
ppl
ie
d
to
in
voi
c
e
k
,
Tᵢ
is
ta
x
a
m
ount
c
a
lc
ul
a
te
d
f
or
e
nt
r
y
i
,
D
is
to
ta
l
di
s
c
ount
a
ppl
ie
d
to
th
e
in
voi
c
e
,
Dᵢ
is
di
s
c
ount
va
lu
e
f
or
e
nt
r
y
i,
R
is
to
ta
l
r
e
ve
nue
ge
ne
r
a
te
d
,
l
is
ty
pe
o
f
tr
a
ns
a
c
ti
on
(
l=
10
f
or
pur
c
ha
s
e
,
l=
20
f
or
s
a
le
)
,
A
is
a
ve
r
a
ge
pur
c
ha
s
e
pr
ic
e
of
im
por
te
d
goods
,
r
is
num
b
e
r
of
li
ne
it
e
m
s
in
a
bi
ll
,
n
1
,
n
2
is
ti
m
e
r
a
nge
us
e
d
f
or
c
a
lc
ul
a
ti
on
(
f
r
om
da
te
n
1
to
da
te
n
2
)
,
a
nd
N
is
ne
t
pr
of
it
e
a
r
ne
d dur
in
g t
he
pe
r
io
d.
3.3.
D
at
a c
ol
le
c
t
e
d
f
r
o
m
t
h
e
L
H
83 r
e
t
ai
l
s
ys
t
e
m
T
o
e
xpe
r
im
e
nt
w
it
h
da
t
a
pr
oc
e
s
s
in
g
a
nd
vi
s
ua
li
z
a
ti
on,
th
is
s
tu
dy
c
ol
le
c
te
d
d
a
ta
f
r
om
th
e
r
e
ta
il
s
ys
te
m
of
L
H
83
,
one
of
th
e
la
r
ge
r
e
ta
il
e
nt
e
r
pr
is
e
s
in
th
e
H
a
n
oi
a
r
e
a
;
th
e
bus
in
e
s
s
uni
t'
s
pr
oduc
ts
a
r
e
w
a
t
e
r
f
il
tr
a
ti
on
e
qui
pm
e
nt
.
T
he
c
ol
le
c
te
d
da
ta
in
c
lu
de
s
r
e
ta
il
in
voi
c
e
s
,
r
e
c
e
ip
ts
,
a
nd
im
por
t
r
e
c
e
ip
ts
f
or
th
e
f
is
c
a
l
ye
a
r
2024.
T
h
e
c
us
to
m
e
r
c
la
s
s
if
ie
s
th
is
da
ta
a
t
a
s
pe
c
if
ic
ti
m
e
;
th
e
da
ta
a
l
s
o
s
how
s
th
e
bus
in
e
s
s
p
e
r
f
or
m
a
nc
e
of
e
a
c
h
s
a
le
s
s
ta
f
f
m
e
m
be
r
of
th
e
c
om
pa
ny.
O
n
th
a
t
ba
s
is
,
in
f
or
m
a
ti
on
on
im
por
t
p
r
ic
e
s
is
a
ls
o
c
ol
le
c
te
d
to
c
a
lc
ul
a
te
th
e
pr
of
it
s
of
th
e
c
om
pa
ny'
s
pr
oduc
ts
.
T
hr
ough
pr
oc
e
s
s
in
g
w
it
h
f
or
m
ul
a
s
a
nd
s
ynt
he
s
i
z
in
g
by
m
ont
h, t
he
s
tu
dy ha
s
s
ynt
he
s
iz
e
d t
he
e
nt
e
r
pr
is
e
'
s
bus
in
e
s
s
d
a
ta
i
n T
a
bl
e
3.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8814
I
nt
J
A
dv A
ppl
S
c
i
,
V
ol
.
14
, N
o.
3
,
S
e
pt
e
m
be
r
20
25
:
945
-
954
950
T
he
da
ta
c
ol
le
c
te
d
f
r
om
th
e
L
H
83
r
e
ta
il
s
ys
te
m
is
s
to
r
e
d
in
a
n
e
xpor
t
da
ta
s
tr
uc
tu
r
e
,
a
s
s
how
n
in
F
ig
ur
e
1,
th
e
n
a
ggr
e
ga
te
d
a
nd
c
a
lc
ul
a
te
d
f
or
2024
r
e
ve
nue
a
nd
pr
of
it
.
I
nvoi
c
e
s
a
r
e
c
la
s
s
if
ie
d
by
c
us
to
m
e
r
a
nd
pe
r
io
d,
pr
ovi
di
ng
a
c
le
a
r
vi
e
w
of
pur
c
ha
s
in
g
be
ha
vi
or
th
r
ougho
ut
th
e
ye
a
r
.
E
a
c
h
tr
a
ns
a
c
ti
on
in
c
lu
de
s
d
e
ta
il
e
d
in
f
or
m
a
ti
on
on
pr
oduc
t
ty
pe
,
qua
nt
it
y,
s
e
ll
in
g
pr
ic
e
,
a
nd
c
os
t
pr
ic
e
,
a
ll
ow
in
g
a
c
c
ur
a
te
r
e
ve
nue
a
nd
pr
of
it
c
a
lc
ul
a
ti
ons
a
nd t
ot
a
l
s
by c
us
to
m
e
r
, pr
oduc
t,
m
ont
h, qua
r
te
r
, a
nd ye
a
r
.
T
a
bl
e
3. L
H
83’
s
r
e
ve
nue
da
t
a
s
e
t
in
2024
N
a
m
e
M
ont
h
Y
e
a
r
R
e
ve
nue
P
r
of
i
t
V
a
l
ue
%
/
ye
a
r
V
a
l
ue
%
/
ye
a
r
L
H
83.01.24
1
2024
11,931,906,000
9.42
1,185,245,595
10.16
L
H
83.02.24
2
2024
6,663,160,000
5.26
655,615,165
5.62
L
H
83.03.24
3
2024
12,522,444,000
9.88
1,205,437,735
10.33
L
H
83.04.24
4
2024
10,281,690,000
8.11
888,722,475
7.62
L
H
83.05.24
5
2024
12,097,281,000
9.55
1,140,505,320
9.78
L
H
83.06.24
6
2024
10,142,084,080
8.00
863,673,775
7.40
L
H
83.07.24
7
2024
11,878,659,000
9.37
651,930,385
5.59
L
H
83.08.24
8
2024
11,096,585,480
8.76
1,119,062,425
9.59
L
H
83.09.24
9
2024
10,718,791,600
8.46
902,866,460
7.74
L
H
83.10.24
10
2024
9,479,322,000
7.48
1,022,341,480
8.76
L
H
83.11.24
11
2024
8,975,844,000
7.08
953,588,895
8.17
L
H
83.12.24
12
2024
10,931,256,000
8.63
1,075,968,860
9.22
T
ot
a
l
126,719,023,160
100.00
11,664,958,570
100.00
4.
A
N
A
L
Y
T
I
C
A
L
R
E
S
U
L
T
S
A
N
D
D
E
C
I
S
I
O
N
-
M
A
K
I
N
G
S
U
P
P
O
R
T
V
I
A
V
I
S
U
A
L
I
Z
A
T
I
O
N
T
he
c
ol
le
c
te
d d
a
ta
i
s
s
to
r
e
d i
n a
s
tr
uc
tu
r
e
d da
ta
ba
s
e
b
a
s
e
d on th
e
pr
opos
e
d s
c
he
m
a
, t
he
n t
r
a
ns
f
or
m
e
d
a
nd
in
te
gr
a
te
d
in
to
th
e
M
P
B
I
s
y
s
te
m
f
or
vi
s
ua
li
z
a
ti
on
th
r
ough
c
ha
r
ts
a
nd
gr
a
phi
c
a
l
r
e
por
ts
.
T
hi
s
pr
oc
e
s
s
not
onl
y
e
nha
nc
e
s
da
t
a
r
e
a
da
bi
li
ty
a
nd
a
c
c
e
s
s
ib
il
it
y
but
a
l
s
o
he
lp
s
us
e
r
s
qui
c
kl
y
id
e
nt
if
y
tr
e
nds
a
nd
f
lu
c
tu
a
ti
ons
in
bus
in
e
s
s
pe
r
f
or
m
a
nc
e
.
I
n
p
a
r
ti
c
ul
a
r
,
s
tr
e
a
m
in
g
E
T
L
te
c
hn
iq
ue
s
a
ll
ow
d
a
ta
f
r
om
s
our
c
e
s
y
s
te
m
s
to
be
e
xt
r
a
c
te
d,
tr
a
ns
f
or
m
e
d,
a
nd
c
ont
in
uous
ly
upd
a
te
d
in
r
e
a
l
-
ti
m
e
in
M
P
B
I
.
A
s
a
r
e
s
ul
t,
th
e
vi
s
ua
li
z
a
ti
ons
a
nd
da
s
hboa
r
ds
a
lwa
y
s
r
e
f
le
c
t
th
e
c
ur
r
e
nt
ope
r
a
ti
ona
l
s
ta
tu
s
of
t
he
b
us
in
e
s
s
.
T
hi
s
r
e
a
l
-
ti
m
e
c
a
pa
bi
li
ty
i
s
e
s
pe
c
i
a
ll
y
va
lu
a
bl
e
f
or
m
a
na
ge
r
s
w
ho
n
e
e
d
to
m
oni
to
r
a
c
ti
vi
ti
e
s
c
ont
in
uo
us
ly
a
nd
m
a
k
e
ti
m
e
ly
d
e
c
is
io
ns
ba
s
e
d
on
up
-
to
-
da
te
i
nf
or
m
a
ti
on.
T
he
vi
s
ua
l
e
l
e
m
e
nt
s
a
r
e
or
ga
ni
z
e
d
in
to
dyna
m
ic
da
s
hboa
r
ds
a
nd
ove
r
vi
e
w
s
c
r
e
e
n
s
,
w
hi
c
h
c
a
n
be
di
s
pl
a
ye
d
di
r
e
c
tl
y
w
it
hi
n
th
e
M
P
B
I
pl
a
tf
or
m
or
e
m
be
dde
d
in
to
in
te
r
na
l
m
a
na
ge
m
e
nt
s
of
twa
r
e
.
I
n
a
ddi
ti
on
to
vi
s
ua
li
z
in
g
da
ta
a
c
c
or
di
ng
to
th
e
pr
e
de
f
in
e
d
s
tr
uc
tu
r
e
,
M
P
B
I
a
ls
o
s
uppor
ts
in
te
r
a
c
ti
ve
f
il
te
r
in
g
di
r
e
c
tl
y
o
n
c
ha
r
ts
a
nd
da
s
hboa
r
ds
.
T
hi
s
e
na
bl
e
s
us
e
r
s
to
vi
e
w
in
f
or
m
a
ti
on
ba
s
e
d
on
va
r
io
us
c
r
it
e
r
ia
s
uc
h
a
s
ti
m
e
,
r
e
gi
on,
c
us
to
m
e
r
s
e
gm
e
nt
,
or
pr
oduc
t
c
a
te
gor
y
,
th
e
r
e
by
m
a
ki
n
g
bus
in
e
s
s
pe
r
f
or
m
a
nc
e
e
va
lu
a
ti
on
m
or
e
c
om
pr
e
he
ns
iv
e
a
nd a
c
c
ur
a
te
.
F
ig
ur
e
2 i
ll
us
tr
a
te
s
a
n e
xa
m
pl
e
of
th
e
bus
in
e
s
s
ove
r
vi
e
w
da
s
hbo
a
r
d of
t
he
L
H
83
r
e
ta
il
s
ys
te
m
, w
it
h da
ta
c
ont
in
uous
ly
upd
a
te
d a
nd vis
u
a
li
z
e
d t
hr
ough the
s
tr
e
a
m
in
g
E
T
L
pr
oc
e
s
s
.
F
ig
ur
e
2.
P
B
I
da
s
hboa
r
d ove
r
vi
e
w
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
dv A
ppl
S
c
i
I
S
S
N
:
2252
-
8814
O
pt
imi
z
in
g r
e
ta
il
s
y
s
te
m
s
:
us
in
g bi
g data and pow
e
r
bu
s
in
e
s
s
i
nt
e
ll
ig
e
nc
e
…
(
H
uu D
ang
Q
uoc
)
951
T
hi
s
da
s
hboa
r
d
is
de
s
ig
ne
d
to
he
lp
m
a
na
g
e
r
s
m
oni
to
r
th
e
ov
e
r
a
ll
bus
in
e
s
s
s
it
ua
ti
on
of
th
e
L
H
83
r
e
ta
il
s
ys
te
m
.
I
n
2024,
th
e
c
om
pa
ny'
s
to
ta
l
r
e
ve
nue
r
e
a
c
he
d
V
N
D
126.7
bi
ll
io
n,
b
r
in
gi
ng
in
a
pr
of
i
t
o
f
V
N
D
11.66
bi
ll
io
n,
c
or
r
e
s
ponding
to
a
pr
of
it
m
a
r
gi
n
of
9.21%
.
T
he
in
tu
it
iv
e
in
te
r
f
a
c
e
h
e
lp
s
m
a
n
a
ge
r
s
e
a
s
il
y
obs
e
r
ve
r
e
ve
nue
f
lu
c
tu
a
ti
ons
by
m
ont
h.
N
ot
a
bl
y,
F
e
br
ua
r
y
r
e
c
or
de
d
th
e
lo
w
e
s
t
r
e
ve
nue
,
m
a
in
ly
due
t
o
c
oi
nc
id
in
g
w
it
h
th
e
L
una
r
N
e
w
Y
e
a
r
hol
id
a
y. T
o
ge
t
hi
gh
r
e
ve
nue
a
t
th
is
ti
m
e
,
m
a
r
ke
ti
ng
c
a
m
pa
ig
n
s
m
us
t
b
e
de
pl
oye
d
m
or
e
s
tr
ongl
y
to
boos
t
d
e
m
a
nd
or
f
oc
u
s
on
th
e
c
ons
um
pt
io
n
of
s
ta
pl
e
pr
oduc
ts
w
it
h
s
ta
bl
e
pur
c
ha
s
in
g powe
r
.
F
ig
ur
e
s
3 a
nd 4
di
s
pl
a
y a
l
is
t
o
f
t
he
10
pr
oduc
ts
w
it
h
t
he
hi
ghe
s
t
r
e
ve
nue
a
nd t
he
10
w
it
h t
he
hi
ghe
s
t
pr
of
it
in
th
e
ye
a
r
,
p
r
ovi
di
ng
a
ba
s
is
f
or
m
a
na
ge
r
s
to
p
r
io
r
it
iz
e
de
ve
lo
pi
ng
e
f
f
e
c
ti
ve
c
ons
um
pt
io
n
pr
om
o
ti
on
pr
ogr
a
m
s
.
A
t
th
e
s
a
m
e
ti
m
e
,
th
e
da
s
hboa
r
d
a
ls
o
s
ho
w
s
a
li
s
t
of
e
m
pl
oye
e
s
w
it
h
out
s
ta
ndi
ng
a
c
hi
e
v
e
m
e
nt
s
,
f
a
c
il
it
a
ti
ng
th
e
pr
opos
a
l
of
a
ppr
opr
ia
te
s
a
la
r
y
a
nd
bonus
pol
ic
ie
s
to
e
nc
our
a
ge
a
nd
m
a
in
ta
in
w
or
k
pe
r
f
or
m
a
nc
e
.
T
hi
s
vi
s
ua
li
z
a
ti
on
s
y
s
te
m
gi
ve
s
m
a
n
a
ge
r
s
a
c
om
pr
e
he
ns
iv
e
vi
e
w
of
L
H
83'
s
bus
in
e
s
s
pe
r
f
or
m
a
nc
e
, m
a
ki
ng t
im
e
ly
a
nd r
e
a
li
s
ti
c
de
c
is
io
ns
t
o i
m
pr
ove
ope
r
a
ti
ona
l
e
f
f
ic
ie
nc
y i
n t
he
f
ol
lo
w
in
g s
ta
ge
s
.
F
ig
ur
e
3. T
op 10 c
us
to
m
e
r
s
ha
ve
t
h
e
hi
ghe
s
t
r
e
ve
nue
(
in
bi
ll
io
n
VND
)
F
ig
ur
e
4. T
op 10 c
us
to
m
e
r
s
ha
ve
t
h
e
hi
ghe
s
t
pr
of
it
(
in
bi
ll
io
n
V
N
D
)
I
n
th
e
r
e
ta
il
s
e
c
to
r
,
e
m
pl
oye
e
s
a
r
e
th
e
di
r
e
c
t
f
or
c
e
th
a
t
g
e
ne
r
a
te
s
r
e
ve
nu
e
a
nd
m
a
in
ta
in
s
c
us
to
m
e
r
r
e
la
ti
ons
hi
ps
.
T
he
pe
r
f
or
m
a
nc
e
of
e
a
c
h
in
di
vi
dua
l
ha
s
a
s
ig
ni
f
ic
a
nt
im
pa
c
t
on
bus
in
e
s
s
r
e
s
ul
ts
a
s
w
e
ll
a
s
s
e
r
vi
c
e
qua
li
ty
.
T
he
r
e
f
or
e
,
m
oni
to
r
in
g
a
nd
e
va
lu
a
ti
ng
w
or
k
p
e
r
f
or
m
a
nc
e
is
a
n
im
por
ta
nt
f
a
c
to
r
th
a
t
he
lp
s
m
a
na
ge
r
s
i
de
nt
if
y outs
ta
ndi
ng e
m
pl
oye
e
s
, t
he
r
e
by buil
di
ng a
ppr
opr
ia
te
r
e
w
a
r
d, t
r
a
in
in
g,
a
nd j
ob a
r
r
a
nge
m
e
nt
pol
ic
ie
s
to
im
pr
ove
m
ot
iv
a
ti
on
a
nd
w
or
k
e
f
f
ic
ie
nc
y.
F
ig
ur
e
5
s
how
s
th
e
to
p
5
e
m
pl
oye
e
s
w
it
h
th
e
hi
ghe
s
t
r
e
ve
nue
a
nd
pr
of
it
f
or
th
e
L
H
83
s
ys
te
m
.
T
he
s
e
c
h
a
r
ts
a
s
s
is
t
th
e
m
a
na
ge
m
e
nt
in
vi
s
u
a
li
z
in
g
e
a
c
h
in
di
vi
dua
l'
s
c
ont
r
ib
ut
io
n
le
ve
l,
s
e
r
vi
ng
a
s
a
ba
s
i
s
f
or
m
a
ki
ng
pe
r
s
onne
l
d
e
c
is
io
ns
a
nd
im
pl
e
m
e
nt
in
g
te
a
m
de
ve
lo
pm
e
nt
s
tr
a
te
gi
e
s
, t
he
r
e
by i
m
pr
ovi
ng t
he
bus
in
e
s
s
e
f
f
ic
ie
nc
y of
t
he
e
nt
i
r
e
s
ys
te
m
.
D
e
pl
oyi
ng
a
da
ta
vi
s
ua
li
z
a
ti
on
s
ys
te
m
in
th
e
e
nt
e
r
pr
is
e
e
n
vi
r
onm
e
nt
c
ont
r
ib
ut
e
s
to
th
e
di
gi
ta
l
tr
a
ns
f
or
m
a
ti
on
pr
oc
e
s
s
a
nd
th
e
im
pl
e
m
e
nt
a
ti
on
o
f
s
c
ie
nc
e
a
nd
te
c
hnol
ogy
a
ppl
ic
a
ti
ons
,
but
a
ls
o
s
e
r
ve
s
a
s
a
f
ounda
ti
on
to
s
uppor
t
e
f
f
e
c
ti
ve
a
nd
ti
m
e
ly
da
ta
-
ba
s
e
d
de
c
is
io
n
-
m
a
ki
ng.
T
hr
ough
r
e
s
e
a
r
c
h a
nd
e
xpe
r
im
e
nt
s
in
th
is
a
r
ti
c
le
w
it
h
r
e
ta
il
s
ys
te
m
s
,
de
pl
oyi
ng
s
ta
nda
r
di
z
e
d
da
ta
ba
s
e
a
ppl
ic
a
ti
ons
(
e
s
p
e
c
ia
ll
y
w
it
h
bi
g
da
ta
)
,
a
ppl
yi
ng
da
ta
c
ons
tr
a
in
ts
,
a
nd
c
onve
r
ti
ng
da
ta
in
to
vi
s
ua
li
z
a
t
io
n
r
e
por
ts
br
in
g
s
e
xc
e
ll
e
nt
e
f
f
ic
ie
nc
y
to
th
e
e
nt
e
r
pr
is
e
. H
ow
e
ve
r
, w
he
n de
pl
oyi
ng, e
nt
e
r
pr
is
e
s
ne
e
d t
o note
t
he
f
ol
lo
w
in
g point
s
:
i)
P
r
io
r
it
iz
e
r
e
a
l
-
ti
m
e
da
ta
upda
te
s
t
o i
m
pr
ove
t
he
a
bi
li
ty
t
o m
oni
t
or
a
nd
ha
ndl
e
s
it
ua
ti
ons
pr
om
pt
ly
I
n
th
e
m
ode
r
n
bus
in
e
s
s
e
nvi
r
onm
e
nt
,
ti
m
e
ly
de
c
is
io
n
-
m
a
ki
ng
ba
s
e
d
on
th
e
la
te
s
t
da
ta
is
ne
c
e
s
s
a
r
y.
A
ppl
yi
ng
s
tr
e
a
m
in
g
E
T
L
te
c
hni
que
s
in
da
ta
vi
s
ua
li
z
a
ti
on
s
ys
t
e
m
s
a
ll
ow
s
bus
in
e
s
s
e
s
to
c
ont
in
uous
ly
upda
te
da
ta
in
r
e
a
l
ti
m
e
,
he
lp
in
g
m
a
na
ge
r
s
qui
c
kl
y
d
e
te
c
t
unu
s
ua
l
r
e
ve
nue
,
in
ve
nt
or
y,
or
e
m
pl
oye
e
pe
r
f
or
m
a
nc
e
f
lu
c
tu
a
ti
ons
.
T
he
a
bi
li
ty
to
c
lo
s
e
ly
m
oni
to
r
ope
r
a
ti
ona
l
in
di
c
a
to
r
s
in
r
e
a
l
-
ti
m
e
pr
ovi
de
s
a
s
ig
ni
f
ic
a
nt
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8814
I
nt
J
A
dv A
ppl
S
c
i
,
V
ol
.
14
, N
o.
3
,
S
e
pt
e
m
be
r
20
25
:
945
-
954
952
a
dva
nt
a
ge
in
f
le
xi
bl
y
r
e
s
ponding
to
r
a
pi
dl
y
c
ha
ngi
ng
m
a
r
ke
t
s
it
ua
ti
ons
,
e
s
pe
c
ia
ll
y
in
th
e
r
e
ta
il
a
nd
e
-
c
om
m
e
r
c
e
i
ndus
tr
ie
s
.
ii)
D
e
s
ig
ni
ng a
r
e
a
s
on
a
bl
e
, uni
f
ie
d, a
nd c
le
a
r
da
ta
b
a
s
e
s
tr
uc
tu
r
e
i
s
th
e
f
ounda
ti
on f
or
pr
a
c
ti
c
a
l
a
na
ly
s
is
A
uni
f
ie
d,
c
le
a
r
ly
s
tr
uc
tu
r
e
d
da
ta
ba
s
e
a
r
c
hi
te
c
tu
r
e
w
il
l
e
ns
u
r
e
da
ta
in
te
gr
it
y,
c
om
pl
e
te
n
e
s
s
,
a
nd
s
ync
hr
oni
z
a
ti
on
be
twe
e
n
de
pa
r
tm
e
nt
s
a
nd
th
e
bu
s
in
e
s
s
e
c
os
ys
te
m
.
T
hi
s
he
lp
s
s
t
a
nda
r
di
z
e
da
t
a
f
lo
w
s
th
r
oughout
th
e
s
ys
te
m
a
nd
opt
im
iz
e
s
th
e
e
f
f
ic
ie
nc
y
of
da
ta
r
e
tr
ie
va
l,
a
ggr
e
ga
ti
on,
a
nd
vi
s
u
a
li
z
a
ti
on.
E
s
pe
c
ia
ll
y
in
r
e
ta
il
s
ys
te
m
s
,
w
he
r
e
da
ta
i
s
c
ont
in
uous
ly
ge
n
e
r
a
te
d
f
r
om
in
voi
c
e
s
,
or
de
r
s
,
in
ve
nt
or
y,
a
nd
c
us
to
m
e
r
tr
a
ns
a
c
ti
ons
,
bui
ld
in
g a
r
e
a
s
ona
bl
e
r
e
la
ti
ona
l
da
ta
m
o
de
l
f
r
om
th
e
be
gi
nni
ng w
il
l
be
a
ke
y
f
a
c
to
r
f
or
th
e
r
e
por
ti
ng s
ys
te
m
t
o ope
r
a
te
a
c
c
ur
a
te
ly
a
nd s
te
a
di
ly
i
n t
he
l
o
ng t
e
r
m
.
iii)
I
de
nt
if
y a
nd e
f
f
e
c
ti
ve
ly
e
xpl
oi
t
lo
ya
l
c
us
to
m
e
r
gr
oups
,
a
s
w
e
ll
a
s
e
nc
our
a
ge
ke
y
e
m
pl
oye
e
s
U
s
in
g
da
ta
vi
s
ua
li
z
a
ti
on
he
lp
s
bus
in
e
s
s
e
s
e
a
s
il
y
id
e
nt
if
y
c
us
to
m
e
r
s
w
it
h
hi
gh
pu
r
c
ha
s
e
f
r
e
que
nc
y
a
nd
e
m
pl
oye
e
s
w
ho
br
in
g
in
out
s
t
a
ndi
ng
r
e
ve
nue
or
pr
of
it
.
F
r
om
th
e
r
e
,
m
a
na
ge
r
s
c
a
n
bui
ld
c
u
s
to
m
e
r
c
a
r
e
pr
ogr
a
m
s
or
a
ppr
opr
ia
te
r
e
w
a
r
ds
a
nd
in
c
e
nt
iv
e
s
f
or
e
m
pl
oye
e
s
to
m
a
in
ta
in
a
nd
m
a
xi
m
iz
e
th
e
va
lu
e
of
th
e
s
e
ke
y
gr
oups
.
T
hi
s
is
a
s
tr
a
te
gi
c
di
r
e
c
ti
on
th
a
t
he
lp
s
bus
in
e
s
s
e
s
gr
ow
in
s
a
le
s
a
nd
in
c
r
e
a
s
e
th
e
e
nga
ge
m
e
nt
a
nd
lo
ya
lt
y of
c
us
to
m
e
r
s
a
nd e
m
pl
oye
e
s
.
iv
)
B
ui
ld
a
f
le
xi
bl
e
da
s
hboa
r
d t
ha
t
c
a
n i
nt
e
r
a
c
t
w
it
h m
ul
ti
pl
e
a
na
ly
s
is
c
r
it
e
r
ia
A
n
e
f
f
e
c
ti
ve
r
e
por
ti
ng
s
ys
te
m
is
not
ju
s
t
a
bout
pr
e
s
e
nt
in
g
da
ta
,
but
a
ls
o
a
ll
ow
s
us
e
r
s
to
f
r
e
e
ly
in
te
r
a
c
t
a
nd
a
na
ly
z
e
in
m
a
ny
di
f
f
e
r
e
nt
di
m
e
ns
io
ns
,
s
uc
h
a
s
ti
m
e
,
pr
oduc
t,
pe
r
s
onne
l,
a
nd
ge
ogr
a
phi
c
a
r
e
a
.
P
B
I
pr
ovi
de
s
f
il
te
r
in
g,
dr
il
l
-
dow
n,
a
nd
r
e
a
l
-
ti
m
e
s
e
le
c
ti
on
to
ol
s
,
a
ll
ow
in
g
m
a
na
ge
m
e
nt
a
nd
s
ta
f
f
us
e
r
s
to
a
na
ly
z
e
da
ta
a
c
c
or
di
ng
to
th
e
ir
pe
r
s
pe
c
ti
ve
.
D
e
s
ig
ni
ng a
hi
e
r
a
r
c
hi
c
a
l
da
s
hboa
r
d,
f
r
om
ove
r
vi
e
w
to
d
e
ta
il
,
w
il
l
he
lp
bus
in
e
s
s
e
s
s
e
r
ve
s
tr
a
te
gi
c
m
a
n
a
ge
m
e
nt
a
nd da
il
y op
e
r
a
ti
ona
l
ne
e
ds
.
v)
D
a
ta
vi
s
ua
li
z
a
ti
on mus
t
b
e
l
in
ke
d t
o s
pe
c
if
ic
a
c
ti
ons
T
he
ul
ti
m
a
te
goa
l
of
vi
s
ua
li
z
a
ti
on
i
s
not
onl
y
to
pr
ovi
de
a
n
ove
r
vi
e
w
but
a
ls
o
to
s
uppor
t
c
le
a
r
a
c
ti
on
de
c
is
io
ns
.
C
h
a
r
ts
a
nd
da
s
hboa
r
ds
s
houl
d
b
e
de
s
ig
ne
d
a
r
ound
s
pe
c
if
ic
m
a
na
ge
m
e
nt
que
s
ti
ons
,
s
uc
h
a
s
:
“
W
hy
is
r
e
ve
nue
dow
n
th
is
m
ont
h?
”
,
“
W
ho
is
e
xc
e
e
di
ng
ta
r
ge
ts
?
”
,
“
W
hi
c
h
pr
oduc
ts
ne
e
d
to
be
pr
om
ot
e
d
m
or
e
?
”
.
W
he
n
da
ta
vi
s
ua
li
z
a
ti
on
is
li
nke
d
to
K
P
I
s
a
nd
a
c
ti
on
pl
a
ns
,
bu
s
in
e
s
s
e
s
w
il
l
im
pr
ove
m
a
na
ge
m
e
nt
e
f
f
ic
ie
nc
y
w
hi
le
i
nc
r
e
a
s
in
g t
he
ir
i
ni
ti
a
ti
ve
i
n opti
m
iz
in
g pr
oc
e
s
s
e
s
a
nd e
xp
lo
it
in
g gr
ow
th
oppor
tu
ni
t
ie
s
.
M
or
e
ove
r
,
C
hr
is
to
doul
ou
e
t
al
.
[
27]
de
ve
lo
pi
ng
a
nd
m
a
in
ta
in
in
g
a
c
us
to
m
e
r
ne
twor
k
i
s
a
c
r
uc
ia
l
f
a
c
to
r
th
a
t
he
lp
s
bus
in
e
s
s
e
s
ov
e
r
c
om
e
c
ha
ll
e
ng
e
s
w
it
hi
n
th
e
in
dus
tr
y
a
nd
in
c
r
e
a
s
e
th
e
ir
c
om
pe
ti
ti
ve
ne
s
s
.
B
y
bui
ld
in
g
e
f
f
e
c
ti
ve
c
us
to
m
e
r
e
nga
ge
m
e
nt
s
tr
a
te
gi
e
s
a
nd
m
a
in
ta
i
ni
ng
s
us
ta
in
a
bl
e
r
e
la
ti
ons
hi
ps
,
bu
s
in
e
s
s
e
s
c
a
n
le
ve
r
a
ge
c
ol
le
c
te
d
da
ta
to
im
pr
ove
th
e
ir
unde
r
s
ta
ndi
ng
of
c
us
to
m
e
r
s
,
th
e
r
e
by
de
ve
lo
pi
ng
be
tt
e
r
c
us
to
m
e
r
a
c
qui
s
it
io
n
s
tr
a
te
gi
e
s
a
nd
e
nha
nc
in
g
s
tr
a
te
gi
c
de
c
is
io
n
-
m
a
ki
ng.
A
s
s
how
n
in
th
is
r
e
s
e
a
r
c
h,
th
e
in
te
gr
a
ti
on
o
f
te
c
hnol
ogy
a
nd
c
u
s
to
m
e
r
s
tr
a
te
gi
e
s
c
a
n
he
lp
bu
s
in
e
s
s
e
s
bui
ld
a
s
tr
onge
r
c
us
to
m
e
r
ne
twor
k,
e
na
bl
in
g
th
e
m
to
a
da
pt
t
o t
he
r
a
pi
d c
ha
nge
s
i
n t
he
m
od
e
r
n r
e
ta
il
m
a
r
ke
t.
F
ig
ur
e
5. T
op 5 e
m
pl
oye
e
s
w
it
h t
he
hi
ghe
s
t
s
a
le
s
r
e
ve
nue
a
nd p
r
of
it
(
in
bi
ll
io
n
VND
)
5.
C
O
N
C
L
U
S
I
O
N
A
N
D
F
U
T
U
R
E
WORKS
T
hi
s
p
a
p
e
r
in
v
e
s
ti
ga
t
e
s
th
e
a
ppl
i
c
a
ti
on
of
M
P
B
I
in
vi
s
u
a
li
z
in
g
da
ta
f
r
om
a
m
a
na
ge
m
e
nt
in
f
or
m
a
ti
on
s
ys
te
m
ta
il
or
e
d
f
or
th
e
r
e
t
a
il
s
e
c
to
r
.
I
t
pr
opo
s
e
s
a
s
tr
uc
tu
r
e
d
da
ta
m
od
e
l
f
or
or
g
a
ni
z
in
g
r
e
t
a
il
in
f
or
m
a
ti
on
c
ol
le
c
te
d f
r
o
m
ope
r
a
ti
on
a
l
s
ys
t
e
m
s
, e
n
a
bl
in
g s
m
oot
h i
nt
e
gr
a
t
io
n
w
it
h
P
B
I
t
o
ge
n
e
r
a
t
e
i
nt
e
r
a
c
ti
v
e
a
nd i
n
s
ig
ht
f
ul
vi
s
u
a
l
r
e
p
or
ts
.
A
d
di
ti
on
a
ll
y,
a
s
e
t
of
m
a
th
e
m
a
ti
c
a
l
f
or
m
ul
a
s
f
o
r
da
ta
a
g
gr
e
g
a
ti
on
a
nd
m
e
tr
i
c
c
om
put
a
ti
on
is
pr
e
s
e
nt
e
d
to
s
uppor
t
r
e
ta
il
m
a
n
a
ge
r
s
in
e
xt
r
a
c
ti
ng
m
e
a
ni
ngf
ul
in
s
i
ght
s
f
or
m
oni
to
r
in
g,
s
upe
r
v
is
io
n,
a
nd
s
tr
a
t
e
gi
c
de
c
i
s
io
n
-
m
a
ki
ng.
T
he
da
t
a
s
e
t
ut
il
iz
e
d
in
th
i
s
s
tu
d
y
i
s
d
e
r
iv
e
d
f
r
om
L
H
8
3'
s
r
e
ta
i
l
op
e
r
a
ti
ons
. T
hi
s
d
a
ta
is
tr
a
n
s
f
or
m
e
d
in
to
a
n
a
na
l
yt
ic
a
l
f
or
m
a
t
a
nd
in
te
gr
a
te
d
in
to
P
B
I
th
r
ough
a
w
e
l
l
-
de
f
in
e
d
pi
p
e
li
n
e
.
T
o
e
nha
nc
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
dv A
ppl
S
c
i
I
S
S
N
:
2252
-
8814
O
pt
imi
z
in
g r
e
ta
il
s
y
s
te
m
s
:
us
in
g bi
g data and pow
e
r
bu
s
in
e
s
s
i
nt
e
ll
ig
e
nc
e
…
(
H
uu D
ang
Q
uoc
)
953
th
e
r
e
s
po
ns
i
ve
n
e
s
s
a
nd
ti
m
e
l
in
e
s
s
of
a
na
ly
ti
c
s
,
th
e
s
t
udy
a
l
s
o
i
nc
or
por
a
te
s
s
tr
e
a
m
in
g
E
T
L
t
e
c
h
ni
qu
e
s
.
U
nl
i
ke
tr
a
di
ti
on
a
l
ba
tc
h
pr
o
c
e
s
s
in
g,
s
tr
e
a
m
in
g
E
T
L
e
n
a
bl
e
s
c
ont
in
uou
s
in
ge
s
ti
on a
nd
tr
a
ns
f
or
m
a
ti
on of
da
t
a
a
s
e
v
e
nt
s
oc
c
ur
,
th
e
r
e
b
y
e
n
s
ur
in
g
th
a
t
da
s
h
boa
r
d
s
r
e
f
le
c
t
ne
a
r
r
e
a
l
-
t
im
e
bus
in
e
s
s
a
c
ti
vi
ti
e
s
.
T
h
is
a
ppr
oa
c
h
s
ig
ni
f
ic
a
nt
l
y
im
pr
ove
s
de
c
is
i
on
-
m
a
ki
ng
c
a
pa
bi
li
ti
e
s
by
pr
ovi
di
ng
up
-
to
-
d
a
te
in
s
ig
ht
s
on
K
P
I
s
a
nd
o
pe
r
a
t
io
na
l
m
e
tr
ic
s
.
T
he
vi
s
u
a
l
o
ut
put
s
,
in
t
he
f
or
m
of
dyn
a
m
ic
c
h
a
r
ts
a
nd
d
a
s
hbo
a
r
ds
,
a
ll
ow
m
a
na
ge
r
s
to
in
tu
i
ti
ve
l
y
in
t
e
r
pr
e
t
bu
s
in
e
s
s
pe
r
f
or
m
a
n
c
e
a
nd
m
a
ke
ti
m
e
ly
a
dj
us
tm
e
nt
s
.
I
n
f
ut
ur
e
w
or
k
,
w
e
pl
a
n
to
e
xpa
nd
th
i
s
f
r
a
m
e
w
or
k
by
i
nt
e
gr
a
ti
ng
pr
e
di
c
ti
ve
a
lg
or
it
hm
s
a
nd
f
or
e
c
a
s
ti
ng
m
od
e
ls
w
it
h
in
t
he
P
B
I
e
n
vi
r
onm
e
nt
, c
om
bi
ni
ng t
he
m
w
it
h
r
e
a
l
-
ti
m
e
d
a
ta
pi
pe
li
n
e
s
v
ia
s
tr
e
a
m
in
g
E
T
L
.
T
hi
s
w
il
l
of
f
e
r
a
n
e
ve
n
m
or
e
c
o
m
pr
e
he
n
s
iv
e
de
c
i
s
io
n
-
s
uppor
t
s
y
s
te
m
to
a
s
s
i
s
t
m
a
na
g
e
r
s
i
n pr
o
a
c
ti
ve
ly
ove
r
s
e
e
in
g
a
nd
opt
im
i
z
in
g r
e
ta
il
ope
r
a
ti
ons
.
F
U
N
D
I
N
G
I
N
F
O
R
M
A
T
I
O
N
T
hi
s
r
e
s
e
a
r
c
h i
s
f
unde
d by T
huongm
a
i
U
ni
ve
r
s
it
y, H
a
n
oi
, V
ie
t
n
a
m
.
A
U
T
H
O
R
C
O
N
T
R
I
B
U
T
I
O
N
S
S
T
A
T
E
M
E
N
T
T
hi
s
jo
ur
na
l
us
e
s
th
e
C
ont
r
ib
ut
or
R
ol
e
s
T
a
xonomy
(
C
R
e
d
iT
)
to
r
e
c
ogni
z
e
in
di
vi
dua
l
a
ut
hor
c
ont
r
ib
ut
io
ns
, r
e
duc
e
a
ut
hor
s
hi
p di
s
put
e
s
,
a
nd f
a
c
il
it
a
te
c
ol
la
bo
r
a
ti
on.
N
am
e
o
f
A
u
t
h
or
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
H
uu D
a
ng Q
uoc
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
H
a
L
e
V
ie
t
✓
✓
✓
✓
✓
✓
✓
✓
C
:
C
onc
e
pt
ua
l
i
z
a
t
i
on
M
:
M
e
t
hodol
ogy
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
da
t
i
on
Fo
:
Fo
r
m
a
l
a
na
l
ys
i
s
I
:
I
nve
s
t
i
ga
t
i
on
R
:
R
e
s
our
c
e
s
D
:
D
a
t
a
C
ur
a
t
i
on
O
:
W
r
i
t
i
ng
-
O
r
i
gi
na
l
D
r
a
f
t
E
:
W
r
i
t
i
ng
-
R
e
vi
e
w
&
E
di
t
i
ng
Vi
:
Vi
s
ua
l
i
z
a
t
i
on
Su
:
Su
pe
r
vi
s
i
on
P
:
P
r
oj
e
c
t
a
dm
i
ni
s
t
r
a
t
i
on
Fu
:
Fu
ndi
ng a
c
qui
s
i
t
i
on
C
O
N
F
L
I
C
T
O
F
I
N
T
E
R
E
S
T
S
T
A
T
E
M
E
N
T
T
he
a
ut
hor
s
de
c
la
r
e
t
ha
t
th
e
r
e
a
r
e
no c
onf
li
c
ts
of
i
nt
e
r
e
s
t
r
e
ga
r
d
in
g t
he
publi
c
a
ti
on of
t
hi
s
pa
pe
r
.
D
A
T
A
A
V
A
I
L
A
B
I
L
I
T
Y
T
he
da
ta
th
a
t
s
uppor
t
th
e
f
in
di
ngs
of
th
is
s
tu
dy
a
r
e
a
va
il
a
bl
e
f
r
om
th
e
c
or
r
e
s
ponding
a
ut
hor
,
[
H
L
V
]
,
upon r
e
a
s
ona
bl
e
r
e
que
s
t.
R
E
F
E
R
E
N
C
E
S
[
1]
D
.
H
.
N
a
bi
l
,
M
.
H
.
R
a
hm
a
n,
A
.
H
.
C
how
dhur
y,
a
nd
B
.
C
.
M
e
ne
z
e
s
,
“
M
a
n
a
gi
ng
s
uppl
y
c
ha
i
n
pe
r
f
or
m
a
nc
e
us
i
ng
a
r
e
a
l
t
i
m
e
M
i
c
r
os
of
t
P
ow
e
r
B
I
da
s
hboa
r
d
by
a
c
t
i
on
de
s
i
gn
r
e
s
e
a
r
c
h
(
ADR
)
m
e
t
hod,”
C
oge
nt
E
ngi
ne
e
r
i
ng
,
vol
.
10,
no.
2,
D
e
c
.
2023,
doi
:
10.1080/
23311916.2023.2257924.
[
2]
M
.
B
e
l
ghi
t
h,
H
.
B
.
A
m
m
a
r
,
A
.
E
l
l
oum
i
,
a
nd
W
.
H
a
c
hi
c
ha
,
“
A
ne
w
r
ol
l
i
ng
f
or
e
c
a
s
t
i
ng
f
r
a
m
e
w
or
k
us
i
ng
M
i
c
r
os
of
t
P
ow
e
r
B
I
f
or
da
t
a
vi
s
ua
l
i
z
a
t
i
on:
a
c
a
s
e
s
t
udy
i
n
a
pha
r
m
a
c
e
ut
i
c
a
l
i
ndu
s
t
r
y,”
A
nnal
e
s
P
har
m
ac
e
ut
i
que
s
F
r
anç
ai
s
e
s
,
vol
.
82,
no.
3,
pp.
493
–
506
,
M
a
y 2024, doi
:
10.1016/
j
.pha
r
m
a
.2023.10.013.
[
3]
A
.
K
.
M
oha
m
m
e
d
a
nd
N
.
P
a
nda
,
“
E
nha
nc
e
m
e
nt
of
pr
e
di
c
t
i
ve
a
na
l
yt
i
c
s
us
i
ng
AI
m
ode
l
s
:
a
f
r
a
m
e
w
or
k
f
or
r
e
a
l
-
t
i
m
e
de
c
i
s
i
on
s
uppor
t
s
ys
t
e
m
s
,”
I
nt
e
r
nat
i
onal
J
our
nal
of
A
dv
anc
e
d
R
e
s
e
ar
c
h
i
n
C
om
put
e
r
and
C
om
m
uni
c
at
i
on
E
ngi
ne
e
r
i
ng
,
vol
.
13,
no.
11,
D
e
c
. 2024, doi
:
10.17148/
I
J
A
R
C
C
E
.2024.131108.
[
4]
M
.
S
.
H
os
e
n
e
t
al
.
,
“
D
a
t
a
-
dr
i
ve
n
de
c
i
s
i
on
m
a
ki
ng:
a
dva
n
c
e
d
da
t
a
b
a
s
e
s
ys
t
e
m
s
f
or
bus
i
ne
s
s
i
nt
e
l
l
i
ge
nc
e
,”
N
anot
e
c
hnol
og
y
P
e
r
c
e
pt
i
ons
, vol
. 20, no. S
3, M
a
y 2024, doi
:
10.62441/
na
no
-
nt
p.v20i
S
3.51.
[
5]
S
.
M
ur
uga
n,
K
.
L
.
D
a
ni
e
l
,
D
.
M
.
A
na
nt
hi
,
D
.
P
.
R
a
j
kum
a
r
,
a
nd
S
.
S
.
J
e
ni
t
ha
,
“
R
e
t
a
i
l
s
t
or
e
s
a
l
e
s
a
na
l
ys
i
s
:
unve
i
l
i
ng
i
ns
i
ght
s
t
hr
ough
P
ow
e
r
B
I
bus
i
ne
s
s
a
na
l
yt
i
c
s
,”
i
n
P
r
oc
e
e
di
ngs
of
t
he
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
I
nnov
at
i
v
e
C
om
put
i
ng
&
C
om
m
uni
c
at
i
on 2024
, 2024
, pp. 1
-
7, doi
:
10.2139/
s
s
r
n.5039793.
[
6]
A
.
A
l
qha
t
a
ni
e
t
al
.
,
“
360°
r
e
t
a
i
l
bus
i
n
e
s
s
a
na
l
yt
i
c
s
by
a
dopt
i
ng
hybr
i
d
m
a
c
hi
ne
l
e
a
r
ni
ng
a
nd
a
bu
s
i
ne
s
s
i
nt
e
l
l
i
ge
nc
e
a
ppr
oa
c
h,
”
Sus
t
ai
nabi
l
i
t
y
, vol
. 14, no. 19, S
e
p. 2022, doi
:
10.3390/
s
u141911942.
[
7]
D
.
K
.
B
a
ne
r
j
e
e
,
S
. D
a
s
,
a
n
d S
.
N
a
t
h,
“
D
a
t
a
v
i
s
ua
l
i
z
a
t
i
o
n
a
pp
r
oa
c
h
f
or
b
us
i
ne
s
s
s
t
r
a
t
e
gy
r
e
c
o
m
m
e
n
da
t
i
o
n
us
i
n
g
P
o
w
e
r
B
I
da
s
h
boa
r
d
,”
I
n
t
e
r
n
at
i
on
al
J
o
ur
na
l
of
R
e
s
e
ar
c
h
i
n
M
ana
ge
m
e
nt
,
vo
l
.
6,
no
.
1,
pp
. 1
68
–
17
5,
20
2
4,
do
i
:
10
.33
54
5/
266
48
792
.2
024
.v
6.i
1b
.13
8.
[
8]
Z
.
C
he
n,
J
.
Z
ha
o,
a
nd
C
.
J
i
n,
“
B
us
i
ne
s
s
i
nt
e
l
l
i
ge
nc
e
f
or
I
ndus
t
r
y
4.0:
p
r
e
di
c
t
i
v
e
m
ode
l
s
f
or
r
e
t
a
i
l
a
nd
di
s
t
r
i
bu
t
i
on,”
I
nt
e
r
nat
i
onal
J
our
nal
of
R
e
t
ai
l
&
D
i
s
t
r
i
but
i
on M
anage
m
e
nt
, vol
. 53, no. 3, pp. 1
–
16, F
e
b. 2025, doi
:
10.1108/
I
J
R
D
M
-
02
-
2023
-
0101.
[
9]
L
.
S
.
Y
a
da
v
,
T
.
V
.
L
a
ks
h
m
i
,
a
nd
V
.
A
l
e
kya
,
“
R
e
t
a
i
l
i
ns
i
g
ht
s
:
u
nve
i
l
i
n
g
e
-
c
om
m
e
r
c
e
d
yna
m
i
c
s
w
i
t
h
P
ow
e
r
B
I
,”
I
n
t
e
r
n
at
i
o
nal
R
e
s
e
ar
c
h
J
our
nal
on
A
dv
a
nc
e
d
E
ng
i
ne
e
r
i
n
g
a
nd
M
a
nag
e
m
e
n
t
,
vol
.
2
,
n
o.
5
,
p
p.
168
0
–
168
2,
202
4,
doi
:
10.
47
392
/
I
R
J
A
E
M
.
202
4.
024
1.
[
10]
O
. B
. S
.
-
L
a
nde
,
E
. J
ohns
on, G
. S
. A
de
l
e
ke
, C
.
P
. A
m
a
j
uoyi
, a
nd
B
. D
. S
i
m
ps
on
, “
E
nha
nc
i
ng bus
i
ne
s
s
i
nt
e
l
l
i
ge
nc
e
i
n e
-
c
om
m
e
r
c
e
:
ut
i
l
i
z
i
ng
a
dva
nc
e
d
da
t
a
i
nt
e
gr
a
t
i
on
f
or
r
e
a
l
-
t
i
m
e
i
ns
i
ght
s
,”
I
nt
e
r
nat
i
onal
J
our
nal
of
M
anage
m
e
nt
&
E
nt
r
e
pr
e
ne
ur
s
hi
p
R
e
s
e
ar
c
h
,
vol
. 6, no. 6, pp. 1936
–
1953, J
un. 2024, doi
:
10.51594/
i
j
m
e
r
.v6
i
6.1207.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8814
I
nt
J
A
dv A
ppl
S
c
i
,
V
ol
.
14
, N
o.
3
,
S
e
pt
e
m
be
r
20
25
:
945
-
954
954
[
11]
S
. A
.
R
um
hi
a
nd J
. S
i
va
kum
a
r
, “
S
a
l
e
s
a
na
l
y
s
i
s
-
r
e
vi
e
w
a
nd r
e
c
om
m
e
nda
t
i
ons
o
n bus
i
ne
s
s
i
nt
e
l
l
i
ge
nc
e
,”
i
n
2023 24t
h I
nt
e
r
nat
i
ona
l
A
r
ab
C
onf
e
r
e
nc
e
on I
nf
or
m
at
i
on T
e
c
hnol
ogy
, I
E
E
E
, D
e
c
. 2023, pp. 1
–
10
, doi
:
10.1109/
A
C
I
T
58888.2023.10453770.
[
12]
D
.
N
i
ki
t
ha
,
S
.
I
.
H
us
s
a
i
n,
a
nd
M
.
P
oor
ni
m
a
,
“
I
nt
e
gr
a
t
i
ng
P
ow
e
r
B
I
w
i
t
h
m
a
c
hi
ne
l
e
a
r
ni
ng
m
ode
l
s
f
or
pr
e
di
c
t
i
ve
a
na
l
yt
i
c
s
,”
i
n
2024
7t
h
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
C
ont
e
m
po
r
ar
y
C
om
put
i
ng
and
I
nf
or
m
at
i
c
s
,
I
E
E
E
,
S
e
p.
2024,
pp.
1245
–
1250
,
doi
:
10.1109/
I
C
3I
61595.2024.10828685.
[
13]
N
.
B
.
S
ur
w
a
de
,
B
.
S
hi
r
a
ga
pur
,
a
nd
A
.
H
us
s
a
i
n,
“
D
a
t
a
vi
s
ua
l
i
z
a
t
i
on
a
nd
da
s
hboa
r
d
de
s
i
gn
f
or
e
nt
e
r
pr
i
s
e
i
nt
e
l
l
i
ge
nc
e
,”
i
n
M
e
t
ahe
ur
i
s
t
i
c
s
f
o
r
E
nt
e
r
pr
i
s
e
D
at
a I
nt
e
l
l
i
ge
nc
e
, 1s
t
e
d.,
C
R
C
P
r
e
s
s
, 2024, p. 2
1.
[
14]
G
.
G
.
J
a
m
e
s
,
G
.
P
.
O
i
s
e
,
E
.
G
.
C
hukw
u
,
N
.
A
.
M
i
c
ha
e
l
,
W
.
F
.
E
kpo
,
a
nd
P
.
E
.
O
ka
f
or
,
“
O
pt
i
m
i
z
i
ng
bus
i
ne
s
s
i
nt
e
l
l
i
ge
n
c
e
s
ys
t
e
m
us
i
ng
bi
g
da
t
a
a
nd
m
a
c
hi
ne
l
e
a
r
ni
ng,”
J
our
nal
of
I
nf
or
m
at
i
on
S
y
s
t
e
m
s
and
I
nf
or
m
at
i
c
s
,
vol
.
6,
no.
2,
pp.
1215
–
1236,
J
un.
2024,
doi
:
10.51519/
j
our
na
l
i
s
i
.v6i
2.631.
[
15]
A
.
R
a
i
,
M
.
M
i
s
r
a
,
a
nd
S
.
K
.
S
a
r
,
“
A
n
e
xpl
or
a
t
or
y
s
t
udy
on
vi
s
ua
l
i
z
i
ng
bi
g
da
t
a
i
n
t
he
i
nt
e
r
ne
t
of
t
hi
ngs
,”
i
n
A
I
P
C
onf
e
r
e
n
c
e
P
r
oc
e
e
di
ngs
, 2024
, doi
:
10.1063/
5.0221663.
[
16]
T
.
L
i
bby,
J
.
M
.
S
c
hw
e
bke
,
a
nd
P
.
M
.
G
ol
dw
a
t
e
r
,
“
U
s
i
ng
da
t
a
a
na
l
yt
i
c
s
t
o
e
va
l
ua
t
e
t
he
dr
i
ve
r
s
of
r
e
ve
nue
:
a
n
i
nt
r
oduc
t
or
y
c
a
s
e
s
t
udy
us
i
ng
M
i
c
r
os
of
t
P
ow
e
r
P
i
vot
a
nd
P
ow
e
r
B
I
,”
I
s
s
ue
s
i
n
A
c
c
ount
i
ng
E
duc
at
i
on
,
vol
.
37,
no.
4,
pp.
97
–
105,
N
ov.
2022,
doi
:
10.2308/
I
S
S
U
E
S
-
2021
-
057.
[
17]
F
.
C
.
P
.
S
e
t
o,
Y
.
D
a
r
ya
nt
o,
a
nd
R
.
D
.
A
s
t
a
nt
i
,
“
B
us
i
ne
s
s
i
nt
e
l
l
i
ge
nc
e
f
or
de
c
i
s
i
on
s
uppor
t
s
y
s
t
e
m
f
or
r
e
pl
e
ni
s
hm
e
nt
pol
i
c
y
i
n
m
i
ni
ng
i
ndus
t
r
y,”
I
nt
e
r
nat
i
onal
J
our
nal
of
I
ndus
t
r
i
al
E
ngi
ne
e
r
i
ng
and
E
ngi
ne
e
r
i
ng
M
anage
m
e
nt
,
vol
.
5,
no.
1,
pp.
51
–
60,
J
un.
2023, doi
:
10.24002/
i
j
i
e
e
m
.v5i
1.7245.
[
18]
M
.
A
m
e
e
r
,
S
.
P
.
R
a
h
u
l
,
a
n
d
S
.
M
a
nn
e
,
“
H
um
a
n
r
e
s
o
u
r
c
e
a
n
a
l
y
t
i
c
s
u
s
i
ng
P
ow
e
r
B
I
vi
s
u
a
l
i
z
a
t
i
on
t
o
o
l
,
”
i
n
2
02
0
4
t
h
I
n
t
e
r
n
at
i
on
al
C
on
f
e
r
e
nc
e
on
I
n
t
e
l
l
i
g
e
n
t
C
o
m
pu
t
i
n
g
a
nd
C
on
t
r
ol
Sy
s
t
e
m
s
,
20
20
,
p
p.
11
84
–
11
89
,
do
i
:
1
0.
1
10
9
/
I
C
I
C
C
S
48
26
5
.2
02
0
.9
12
0
89
7.
[
19]
S
.
A
na
r
da
ni
,
M
.
N
.
L
.
A
z
i
s
,
a
nd
M
.
Y
.
A
s
yh
a
r
i
,
“
T
he
i
m
pl
e
m
e
nt
a
t
i
on
of
b
us
i
ne
s
s
i
nt
e
l
l
i
ge
nc
e
t
o
a
na
l
yz
e
s
a
l
e
s
t
r
e
nds
i
n
t
h
e
i
ndof
i
s
hi
ng
onl
i
ne
s
t
or
e
us
i
ng
P
ow
e
r
B
I
,”
B
r
i
l
l
i
anc
e
:
R
e
s
e
ar
c
h
of
A
r
t
i
f
i
c
i
al
I
nt
e
l
l
i
ge
nc
e
,
vol
.
3,
no.
2,
pp.
300
–
305,
D
e
c
.
2023,
doi
:
10.47709/
br
i
l
l
i
a
nc
e
.v3i
2.3232.
[
20]
O
. Q
. S
hubho, Z
. N
.
T
um
pa
, W
. I
.
R
. D
i
pt
o,
a
nd M
.
R
.
A
l
a
m
, “
R
e
a
l
-
t
i
m
e
da
t
a
vi
s
ua
l
i
z
a
t
i
on us
i
ng
bus
i
ne
s
s
i
nt
e
l
l
i
ge
n
c
e
t
e
c
hni
qu
e
s
i
n
s
m
a
l
l
a
nd
m
e
di
um
e
nt
e
r
pr
i
s
e
s
f
or
m
a
ki
ng
a
f
a
s
t
e
r
de
c
i
s
i
on
on
s
a
l
e
s
da
t
a
,”
i
n
D
e
c
i
s
i
on
I
nt
e
l
l
i
ge
nc
e
A
nal
y
t
i
c
s
and
t
he
I
m
pl
e
m
e
nt
at
i
on of
St
r
at
e
gi
c
B
us
i
ne
s
s
M
anage
m
e
nt
, S
pr
i
nge
r
, C
ha
m
, 2022, pp.
189
–
198
, doi
:
10.1007/
978
-
3
-
030
-
82763
-
2_17.
[
21]
K
. S
ha
r
m
a
, A
. S
he
t
t
y, A
. J
a
i
n, a
nd R
. K
.
D
ha
na
r
e
, “
A
c
om
pa
r
a
t
i
ve
a
na
l
y
s
i
s
on
va
r
i
ous
bus
i
ne
s
s
i
nt
e
l
l
i
ge
nc
e
(
BI
)
, da
t
a
s
c
i
e
nc
e
a
n
d
da
t
a
a
na
l
yt
i
c
s
t
ool
s
,”
i
n
2021
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
C
om
put
e
r
C
om
m
un
i
c
at
i
on
and
I
nf
or
m
at
i
c
s
(
I
C
C
C
I
)
,
I
E
E
E
,
J
a
n.
2021,
pp. 1
–
11
, doi
:
10.1109/
I
C
C
C
I
50826.2021.9402226.
[
22]
J
.
M
. P
.
-
R
u
i
z
, A
.
T
.
-
T
o
uk
ou
m
i
di
s
, S
. E
.
G
.
-
M
o
r
e
no
,
a
n
d
H
. G
.
V
.
-
B
a
c
a
,
“
A
n
ov
e
r
vi
e
w
o
f
t
h
e
ga
m
i
n
g i
n
du
s
t
r
y
a
c
r
o
s
s
n
a
t
i
o
ns
:
us
i
ng
a
na
l
yt
i
c
s
w
i
t
h
P
ow
e
r
B
I
t
o
f
o
r
e
c
a
s
t
a
n
d
i
de
nt
i
f
y
ke
y
i
n
f
l
ue
nc
e
r
s
,
”
H
e
l
i
y
on
,
v
ol
.
8
,
no
.
2
,
F
e
b
.
2
02
2
,
do
i
:
1
0.
10
1
6/
j
.h
e
l
i
yo
n.
2
02
2.
e
0
8
95
9.
[
23]
T
.
T
ha
l
ha
m
m
e
r
,
M
.
S
c
hr
e
f
l
,
a
nd
M
.
M
oha
ni
a
,
“
A
c
t
i
ve
da
t
a
w
a
r
e
hous
e
s
:
c
o
m
pl
e
m
e
nt
i
ng
O
L
A
P
w
i
t
h
a
na
l
ys
i
s
r
ul
e
s
,”
D
at
a
&
K
now
l
e
dge
E
ngi
ne
e
r
i
ng
, vol
. 39, no. 3, pp. 241
–
269, D
e
c
. 2001, doi
:
10.1016/
S
0169
-
023X
(
01)
00042
-
8.
[
24]
A
.
C
uz
z
oc
r
e
a
,
L
.
B
e
l
l
a
t
r
e
c
he
,
a
nd
I
.
-
Y
.
S
ong,
“
D
a
t
a
w
a
r
e
hou
s
i
ng
a
nd
O
L
A
P
ove
r
bi
g
da
t
a
,”
i
n
D
O
L
A
P
'
13:
P
r
oc
e
e
di
ngs
of
t
h
e
s
i
x
t
e
e
nt
h i
nt
e
r
nat
i
onal
w
o
r
k
s
hop on D
at
a
w
ar
e
hou
s
i
ng and O
L
A
P
, O
c
t
. 2013, pp. 67
–
70
, doi
:
10.1145/
2513190.2517828.
[
25]
M
.
G
or
a
w
s
ki
a
nd
A
.
G
or
a
w
s
ka
,
“
R
e
s
e
a
r
c
h
on
t
he
s
t
r
e
a
m
ETL
pr
oc
e
s
s
,
”
i
n
B
e
y
ond
D
at
abas
e
s
,
A
r
c
hi
t
e
c
t
u
r
e
s
,
and
St
r
uc
t
ur
e
s
,
S
pr
i
nge
r
, C
ha
m
, 2014, pp. 61
–
71
, doi
:
10.1007/
978
-
3
-
319
-
06932
-
6_7.
[
26]
A
.
P
a
r
e
e
k,
B
.
K
ha
l
a
dka
r
,
R
.
S
e
n,
B
.
O
na
t
,
V
.
N
a
di
m
pa
l
l
i
,
a
nd
M
.
L
a
ks
hm
i
na
r
a
ya
na
n,
“
R
e
a
l
-
t
i
m
e
E
T
L
i
n
S
t
r
i
i
m
,”
i
n
B
I
R
T
E
'
18:
P
r
oc
e
e
di
ngs
of
t
he
I
nt
e
r
nat
i
onal
W
or
k
s
hop
on
R
e
al
-
T
i
m
e
B
us
i
ne
s
s
I
nt
e
l
l
i
ge
nc
e
and
A
nal
y
t
i
c
s
,
A
ug.
2018,
pp.
1
–
10
,
doi
:
10.1145/
3242153.3242157.
[
27]
I
.
C
hr
i
s
t
odoul
ou,
S
.
U
.
P
ut
r
a
nt
o,
M
.
H
.
Y
ous
s
e
f
,
A
.
S
i
m
i
l
l
i
dou,
a
nd
J
.
C
hova
nc
ová
,
“
S
t
r
a
t
e
gi
c
s
c
a
l
i
ng
i
ni
t
i
a
t
i
ve
s
a
nd
c
l
i
e
nt
ne
t
w
or
ki
ng
dyna
m
i
c
s
f
or
s
m
a
l
l
a
nd
m
e
di
um
-
s
i
z
e
d
e
nt
e
r
p
r
i
s
e
s
gr
ow
t
h:
a
c
om
pr
e
he
ns
i
ve
c
a
s
e
s
t
udy
a
na
l
ys
i
s
,”
J
our
nal
of
T
r
ade
Sc
i
e
nc
e
, vol
. 13, no. 1, pp. 3
–
22, M
a
r
. 2025, doi
:
10.1108/
J
T
S
-
03
-
2024
-
0012.
B
I
O
G
R
A
P
H
I
E
S
O
F
A
U
T
H
O
R
S
Huu
Dang
Quoc
received
a
Ba
chelor
's
and
M.S.
degree
in
the
School
of
Information
Technology,
Vietnam
National
University,
Ha
n
oi,
Viet
n
a
m,
in
2000
and
2015.
He
received
a
Ph.D.
degree
from
the
Military
Institute
of
Science
and
Technology,
Ha
n
oi,
Vietnam,
in
2023.
He
worked
at
Thuong
Mai
University,
Ha
n
oi,
Viet
n
am
,
from
2006.
His
research
interests
include
AI,
Io
T
s
ystem
s
,
manageme
nt
information
systems
in
manufactu
ring,
software
engineering,
evolution
ary
algorit
hm
s
,
and
optimization
algorithm
s
.
He
can
be
contact
ed
at email
:
huudq@
tmu.edu.vn
.
Ha
Le
Viet
graduated
with
a
Bachelor'
s
and
Master'
s
degree
in
Information
Technology,
Hanoi
National
University
in
2000
and
2024,
and
a
Ph
.
D
.
in
Management
Information
Systems
from
National
Economics
University
in
2019.
S
he
is
currently
working
at
the
Thuongmai
University.
Her
research
interests
include
management
information
systems,
fuzzy
systems,
big
data
analytics,
machine
learning,
artificial
inte
lligence,
and
blockchain
technology
applied
in
the
fields
of
economics,
financ
e,
accounting
,
b
usiness,
and
science
.
She
can
be
contact
ed
at email
: leviet
ha@
tmu.edu
.vn.
Evaluation Warning : The document was created with Spire.PDF for Python.