I
AE
S
I
nte
rna
t
io
na
l J
o
urna
l o
f
Art
if
icia
l
I
nte
llig
ence
(
I
J
-
AI
)
Vo
l.
9
,
No
.
1
,
Ma
r
ch
2
0
2
0
,
p
p
.
18
~
24
I
SS
N:
2252
-
8938
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ai.
v
9
.i
1
.
p
p
18
-
24
18
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Ex
plo
ra
tion o
n digi
tal
m
a
r
k
e
ting a
s busi
ness
stra
tegy
m
o
del
a
m
o
ng
Ma
la
y
sia
n
ent
re
preneu
rs v
i
a
neuroco
m
p
utin
g
H
a
zr
it
a
Ab R
a
hi
m
1
,
Sh
a
f
a
f
I
bra
hi
m
2
,
Sa
a
di B
in Ah
m
a
d K
a
m
a
rud
din
3
,
No
r
Azura
M
d.
G
ha
ni
4
,
I
s
m
a
il
M
us
irin
5
1
,3
F
a
c
u
lt
y
o
f
Bu
sin
e
ss
,
Eco
n
o
m
ic
s a
n
d
A
c
c
o
u
n
ti
n
g
,
HEL
P
U
n
iv
e
rsity
,
S
u
b
a
n
g
2
Ca
m
p
u
s.
S
u
b
a
n
g
B
e
sta
ri,
S
h
a
h
A
lam
,
S
e
lan
g
o
r,
M
a
lay
sia
2
F
a
c
u
lt
y
o
f
Co
m
p
u
ter an
d
M
a
th
e
m
a
ti
c
a
l
S
c
ien
c
e
s,
Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
A
RA
,
Ja
sin
,
M
e
lak
a
,
M
a
la
y
si
a
4
F
a
c
u
lt
y
o
f
Co
m
p
u
ter an
d
M
a
th
e
m
a
ti
c
a
l
S
c
ien
c
e
s,
Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
A
RA
,
S
h
a
h
A
la
m
,
S
e
lan
g
o
r,
M
a
lay
sia
5
F
a
c
u
lt
y
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
A
RA
,
S
h
a
h
A
la
m
,
S
e
lan
g
o
r
Da
ru
l
E
h
sa
n
,
M
a
lay
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
3
,
2
0
1
9
R
ev
i
s
ed
Dec
2
0
,
2
0
1
9
A
cc
ep
ted
J
an
3
,
2
0
20
A
rti
f
icia
l
In
telli
g
e
n
c
e
is
g
re
a
t
wh
e
n
it
c
o
m
e
s
to
ro
u
ti
n
e
a
c
ti
v
it
ies
a
n
d
v
a
st
a
m
o
u
n
ts
o
f
d
a
ta
a
re
a
n
a
l
y
z
e
d
.
T
h
is
c
a
n
b
e
d
o
n
e
m
o
re
q
u
ick
l
y
a
n
d
e
ff
ici
e
n
tl
y
th
a
n
m
e
n
.
In
th
e
w
o
rld
o
f
d
ig
it
a
l
m
a
rk
e
ti
n
g
,
A
rti
f
icia
l
In
telli
g
e
n
c
e
is
q
u
ick
ly
c
o
m
in
g
in
to
p
lay
.
W
it
h
A
rti
f
i
c
ia
l
In
telli
g
e
n
c
e
jo
in
i
n
g
th
e
d
ig
it
a
l
m
a
rk
e
ti
n
g
e
n
v
iro
n
m
e
n
t,
p
re
d
icti
n
g
u
se
r
b
e
h
a
v
io
r,
se
a
rc
h
c
y
c
l
e
s,
a
n
d
m
u
c
h
m
o
re
w
il
l
b
e
e
a
sie
r.
T
h
is
c
a
n
su
p
p
o
r
t
w
e
b
sites
th
a
t
a
re
h
ig
h
ly
u
se
r
-
f
r
ien
d
ly
f
o
r
o
rg
a
n
iza
ti
o
n
s.
M
o
re
o
v
e
r,
w
it
h
t
h
e
a
id
o
f
A
rti
f
icia
l
In
tel
li
g
e
n
c
e
,
c
o
n
ten
t
c
re
a
ti
o
n
h
a
s
b
e
c
o
m
e
a
fa
ste
r
a
n
d
e
a
sie
r
tas
k
f
o
r
b
ra
n
d
s.
P
ra
c
ti
c
a
ll
y
,
a
c
o
m
p
a
n
y
'
s
d
e
g
re
e
o
f
e
n
terp
rise
m
a
rk
e
ti
n
g
c
a
n
h
a
v
e
a
n
e
ff
e
c
t
o
n
it
s
o
v
e
ra
ll
b
u
sin
e
ss
e
ff
icie
n
c
y
.
En
trep
re
n
e
u
rial
m
a
rk
e
ti
n
g
is
d
riv
e
n
b
y
e
n
trep
re
n
e
u
rial
o
p
p
o
rt
u
n
it
ies
w
h
ich
in
v
o
lv
e
s
th
e
p
ro
a
c
ti
v
e
id
e
n
ti
f
ica
ti
o
n
a
n
d
e
x
p
l
o
it
a
ti
o
n
o
f
o
p
p
o
rt
u
n
it
ies
f
o
r
a
c
q
u
iri
n
g
a
n
d
re
tain
in
g
p
r
o
f
it
a
b
le cu
sto
m
e
rs t
h
ro
u
g
h
Dig
it
a
l
a
p
p
ro
a
c
h
e
s
t
o
risk
m
a
n
a
g
e
m
e
n
t,
re
so
u
rc
e
lev
e
ra
g
in
g
a
n
d
v
a
lu
e
c
re
a
ti
o
n
.
T
h
is
re
se
a
rc
h
wa
s
d
o
n
e
b
y
c
o
ll
e
c
ti
n
g
d
a
ta
u
s
in
g
se
m
i
stru
c
tu
re
q
u
e
stio
n
n
a
ire
d
istri
b
u
ted
t
o
1
6
9
sta
rt
u
p
o
w
n
e
rs
in
Kla
n
g
V
a
ll
e
y
a
re
a
.
U
sin
g
t
w
o
-
la
y
e
r
6
-
3
-
1
w
it
h
h
y
p
e
rb
o
li
c
tan
g
e
n
t
-
p
u
re
li
n
c
o
n
f
ig
u
ra
ti
o
n
s
n
e
u
ra
l
n
e
tw
o
rk
m
o
d
e
l,
it
w
a
s
f
o
u
n
d
th
a
t
p
r
o
a
c
ti
v
e
n
e
ss
,
risk
ta
k
in
g
,
re
so
u
rc
e
le
v
e
ra
g
in
g
,
o
p
p
o
rtu
n
it
y
f
o
c
u
s,
in
ten
sity
a
n
d
v
a
lu
e
a
d
d
a
re
th
e
sig
n
if
ic
a
n
t
f
a
c
to
rs
to
wa
rd
s
d
ig
it
a
l
m
a
rk
e
ti
n
g
re
sp
e
c
ti
v
e
l
y
.
It
is
e
x
p
e
c
ted
th
a
t
t
h
e
f
in
d
in
g
s
w
o
u
ld
g
iv
e
so
m
e
in
p
u
ts t
o
th
e
M
a
lay
sia
n
e
n
trep
re
n
e
u
rs o
n
in
n
o
v
a
ti
v
e
d
ig
it
a
l
m
a
rk
e
ti
n
g
in
th
e
ir
b
u
sin
e
ss
e
s,
re
g
a
rd
les
s th
e
siz
e
s
.
K
ey
w
o
r
d
s
:
A
r
ti
f
icial
Ne
u
r
al
Net
w
o
r
k
B
u
s
i
n
ess
P
er
f
o
r
m
a
n
ce
Dig
ital M
ar
k
eti
n
g
E
n
tr
ep
en
eu
r
s
h
ip
Klan
g
Valle
y
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Haz
r
ita
A
b
.
R
a
h
i
m
,
Dep
ar
t
m
en
t o
f
B
u
s
i
n
es
s
St
u
d
i
es,
Facu
lt
y
o
f
B
u
s
i
n
es
s
,
E
co
n
o
m
ics a
n
d
A
cc
o
u
n
ti
n
g
,
HE
L
P
Un
i
v
er
s
it
y
,
S
u
b
an
g
2
C
a
m
p
u
s
.
P
er
s
iar
an
C
ak
er
a
w
ala,
Su
b
an
g
B
estar
i,
Sek
s
y
en
U4
,
4
0
1
5
0
Sh
ah
A
la
m
,
Sela
n
g
o
r
D
ar
u
l E
h
s
a
n
,
Ma
la
y
s
ia
.
Em
ail:
h
az
r
ita.
ar
@
h
elp
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
A
r
ti
f
icial
I
n
tell
ig
e
n
ce
a
n
d
d
ig
i
tal
m
ar
k
eti
n
g
ar
e
b
e
g
in
n
i
n
g
to
g
o
h
a
n
d
in
h
a
n
d
.
A
r
ti
f
icial
I
n
tellig
e
n
c
e
tr
an
s
f
o
r
m
s
d
i
g
ital
s
tr
ate
g
y
with
t
h
e
ab
ilit
y
to
co
llect
d
ata,
in
ter
p
r
et
it,
ap
p
ly
it,
an
d
th
en
lear
n
f
r
o
m
it.
As
it
co
n
ti
n
u
es
to
ad
v
a
n
ce
,
s
o
w
il
l
th
e
ca
p
ab
ilit
ie
s
to
u
s
e
it
to
i
m
p
r
o
v
e
d
ig
ital
m
ar
k
etin
g
s
tr
ate
g
ies
a
n
d
v
alu
ab
le
cu
s
to
m
er
in
s
i
g
h
ts
f
o
r
co
m
p
an
ies.
T
o
b
e
a
s
u
cc
ess
f
u
l
e
n
tr
ep
r
en
eu
r
in
to
d
a
y
's
h
ig
h
l
y
d
e
m
a
n
d
in
g
b
u
s
i
n
ess
w
o
r
ld
,
all
th
e
i
n
f
o
r
m
atio
n
n
ee
d
ed
is
i
m
p
o
r
tan
t
as
t
o
o
ls
to
s
ta
y
r
ele
v
a
n
t,
co
m
p
etit
iv
e
a
n
d
p
r
o
f
itab
le.
E
v
er
y
lar
g
e
o
r
s
m
al
l
co
m
p
an
y
'
s
s
u
cc
e
s
s
is
d
eter
m
in
ed
b
y
t
wo
f
ac
to
r
s
th
at
ar
e
th
e
v
o
lu
m
e
o
f
r
ev
en
u
e
an
d
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
A
r
ti
f
I
n
tell
I
SS
N:
2252
-
8938
E
xp
lo
r
a
tio
n
o
n
d
ig
ita
l m
a
r
ke
tin
g
a
s
b
u
s
in
ess
s
tr
a
teg
y
mo
d
el
a
mo
n
g
.
.
.
(
Ha
z
r
ita
A
b
R
a
h
im
)
19
ab
ilit
y
to
ex
p
an
d
p
h
y
s
icall
y
in
ter
m
s
o
f
d
iv
er
s
i
f
icatio
n
o
f
s
ize
an
d
g
o
o
d
s
o
r
s
er
v
ices.
No
n
et
h
ele
s
s
,
a
n
ich
e
m
ar
k
eti
n
g
s
tr
ateg
y
n
ee
d
s
to
b
e
d
ev
elo
p
ed
f
o
r
Sm
al
l
an
d
Me
d
iu
m
E
n
ter
p
r
is
e
(
SME
)
in
o
r
d
er
to
r
em
ai
n
v
iab
le
a
n
d
co
m
p
etiti
v
e
i
n
t
h
e
h
i
g
h
l
y
v
o
latile
b
u
s
in
e
s
s
e
n
v
ir
o
n
m
en
t.
T
h
er
e
ar
e
s
ev
e
n
ele
m
e
n
ts
w
it
h
in
t
h
e
s
co
p
e
o
f
en
tr
ep
r
en
eu
r
ial
m
ar
k
etin
g
th
at
ca
n
b
e
u
s
ed
as
an
in
d
ep
en
d
en
t
b
u
s
in
e
s
s
s
tr
ate
g
y
o
r
as
a
c
o
m
b
i
n
atio
n
a
m
o
n
g
o
th
er
s
.
I
n
Ma
la
y
s
ia
e
x
p
lo
r
atio
n
o
n
d
ig
i
tal
m
ar
k
eti
n
g
a
n
d
ar
tif
ic
ial
i
n
telli
g
en
ce
as
b
u
s
i
n
es
s
s
tr
ate
g
y
m
o
d
el
is
s
t
ill
li
m
ited
,
ex
p
ec
iall
y
a
m
o
n
g
s
m
al
l
an
d
m
ed
iu
m
e
n
tr
ep
r
en
eu
r
s
.
T
h
er
ef
o
r
e,
in
th
is
r
esear
ch
,
th
e
s
i
g
n
if
ican
ce
a
m
o
n
g
i
m
p
o
r
tan
t
p
r
ed
icto
r
s
to
w
ar
d
s
in
n
o
v
ativ
e
d
ig
i
tal
m
ar
k
eti
n
g
i
s
ex
p
l
o
r
ed
at
m
u
lti
-
s
ize
s
o
f
b
u
s
i
n
ess
e
s
ar
o
u
n
d
Klan
g
V
alle
y
,
Ma
la
y
s
ia.
T
h
is
r
esear
ch
p
ap
er
is
d
iv
id
ed
in
to
f
iv
e
co
m
p
o
n
en
ts
w
h
ich
ar
e
in
t
r
o
d
u
ctio
n
,
r
elate
d
liter
at
u
r
es,
m
et
h
o
d
o
lo
g
y
,
r
es
u
lts
a
n
d
d
is
cu
s
s
s
io
n
s
,
last
b
u
t
n
o
t
least
co
u
n
clu
s
io
n
s
an
d
r
ec
o
m
m
e
n
d
atio
n
s
.
2.
RE
L
AT
E
D
L
I
T
E
RA
T
UR
E
S
Usu
al
l
y
,
m
ar
k
eti
n
g
th
eo
r
ies
ar
e
tau
g
h
t
f
r
o
m
tr
ad
itio
n
al
t
ex
tb
o
o
k
s
[
1
-
3
]
w
h
ic
h
co
n
ce
n
tr
ate
o
n
m
ar
k
et
in
g
ac
t
iv
it
ies
s
u
ch
as
s
c
h
ed
u
l
in
g
,
m
ar
k
et
in
g
an
al
y
s
is
a
n
d
m
ar
k
eti
n
g
m
i
x
(
4
P
s
an
d
7
P
s
)
i
m
p
le
m
en
ta
tio
n
.
S
u
ch
co
n
ce
p
ts
ar
e
d
esig
n
ed
f
o
r
lar
g
e
co
m
p
a
n
ie
s
w
h
er
e
t
h
er
e
ar
e
m
o
r
e
r
ea
d
ily
a
v
ailab
le
f
i
n
an
cia
l
r
eso
u
r
ce
s
an
d
m
ar
k
e
tin
g
ex
p
er
ien
ce
.
B
ec
au
s
e
o
f
t
h
e
u
n
iq
u
e
ch
ar
ac
ter
is
tics
an
d
co
n
s
tr
ain
ts
o
f
s
m
all
an
d
m
ed
iu
m
-
s
ized
en
ter
p
r
is
e
s
,
in
cl
u
d
in
g
th
e
i
n
h
er
en
t
c
h
a
r
ac
ter
is
tics
o
f
SME
o
w
n
er
s
an
d
m
a
n
ag
er
s
,
t
h
e
co
m
p
eti
tiv
e
b
u
s
i
n
es
s
en
v
ir
o
n
m
en
t
an
d
t
h
e
lack
o
f
r
eso
u
r
c
es
in
s
id
e
SME
s
[
4
-
5
]
,
it
is
u
n
r
ea
lis
tic
to
p
r
esu
m
e
th
at
SME
s
m
a
y
f
o
llo
w
t
h
e
s
a
m
e
o
r
s
i
m
ilar
ap
p
r
o
ac
h
es
to
m
ar
k
et
in
g
a
s
lar
g
e
en
ter
p
r
is
e
s
[
6
-
7
]
.
I
t
is
t
h
er
ef
o
r
e
n
ec
es
s
ar
y
to
d
e
v
elo
p
an
d
s
tr
en
g
t
h
e
n
c
u
r
r
en
t
m
ar
k
eti
n
g
m
o
d
els
t
h
at
ca
n
b
e
u
s
ed
to
p
r
o
f
ile
m
ar
k
et
in
g
p
r
ac
tices
in
s
m
all
b
u
s
i
n
es
s
es [
8
]
.
On
t
h
e
o
th
er
h
an
d
,
a
m
o
r
e
r
e
v
o
lu
tio
n
ar
y
in
ter
p
r
etatio
n
o
f
E
n
tr
ep
r
en
eu
r
ial
Ma
r
k
et
in
g
(
E
M)
is
t
h
at
it
co
n
s
id
er
s
th
at
E
M
is
a
co
m
p
lete
co
n
v
er
g
e
n
ce
o
f
m
ar
k
eti
n
g
an
d
en
tr
ep
r
en
eu
r
s
h
ip
.
E
M'
s
f
r
a
m
e
w
o
r
k
is
n
o
t
m
er
el
y
t
h
e
i
n
ter
f
ac
e
b
et
w
ee
n
m
ar
k
et
in
g
s
ets
an
d
e
n
tr
ep
r
en
e
u
r
ial
p
r
o
ce
s
s
e
s
t
h
at
e
m
er
g
ed
as
E
M
'
s
tr
ad
itio
n
al
co
n
ce
p
tu
aliza
tio
n
,
b
u
t
i
n
co
r
p
o
r
ates
en
tire
l
y
all
asp
ec
t
s
o
f
A
M
(
ad
m
in
is
tr
ati
v
e
ad
v
er
ti
s
i
n
g
)
e
n
tr
ep
r
en
eu
r
s
h
ip
[9
-
1
0
]
it
th
u
s
b
ec
o
m
es
a
s
tr
at
eg
ic
o
r
ien
tatio
n
th
at
g
o
es
b
e
y
o
n
d
th
e
r
o
le
o
f
m
ar
k
et
in
g
[
1
1
]
.
A
lter
n
at
iv
el
y
,
t
h
e
o
th
er
co
n
ce
p
ts
f
in
d
E
M
as
an
alter
n
ati
v
e
to
tr
ad
itio
n
al
m
ar
k
eti
n
g
an
d
ass
o
ciate
it
w
it
h
"
th
is
w
o
r
d
(
E
M)
i
s
u
s
ed
as
an
i
n
teg
r
ati
v
e
co
n
ce
p
tu
aliza
tio
n
t
h
at
r
ep
r
ese
n
ts
a
lte
r
n
ativ
e
p
er
s
p
ec
tiv
e
s
s
u
c
h
as
g
u
er
r
illa
m
ar
k
eti
n
g
,
r
ev
o
lu
tio
n
ar
y
m
ar
k
eti
n
g
,
ex
p
e
d
itio
n
ar
y
m
ar
k
eti
n
g
,
d
is
r
u
p
ti
v
e
m
ar
k
eti
n
g
an
d
o
th
er
s
"
[
1
2
]
.
T
h
e
o
th
er
ty
p
e
o
f
d
ef
in
i
tio
n
o
f
E
M
h
as
a
d
i
f
f
er
en
t
p
er
s
p
ec
tiv
e
an
d
i
s
b
ased
o
n
th
e
li
f
e
c
y
c
le
o
f
th
e
co
m
p
an
y
.
[
3
]
C
la
i
m
s
t
h
at
w
h
e
n
th
e
b
u
s
in
e
s
s
is
s
m
all,
v
e
r
s
atile
an
d
ab
le
to
ex
p
er
ien
ce
n
e
w
th
i
n
g
s
as
a
n
in
f
o
r
m
al
m
et
h
o
d
o
f
ad
v
er
tis
in
g
,
it
is
p
r
ac
ticed
i
n
it
s
ea
r
l
y
s
ta
g
es
a
n
d
t
h
is
w
o
u
ld
b
e
d
escr
ib
ed
b
y
E
M
a
s
m
a
n
y
b
u
s
i
n
ess
e
s
ar
e
s
tar
ted
b
y
p
eo
p
le
w
h
o
li
v
e
b
y
t
h
eir
w
it.
As
t
h
e
co
m
p
an
y
g
r
o
w
s
a
n
d
m
atu
r
es,
m
ar
k
eti
n
g
p
r
ac
tices
ar
e
m
o
r
e
r
i
g
o
r
o
u
s
[
1
3
]
,
p
r
ep
ar
atio
n
is
n
ec
e
s
s
ar
y
an
d
t
h
e
co
m
p
a
n
y
h
i
ts
t
h
e
s
ec
o
n
d
s
tag
e,
ca
lled
f
o
r
m
alize
d
m
ar
k
e
tin
g
:
"
W
h
en
s
m
al
l
b
u
s
i
n
ess
e
s
e
x
p
an
d
,
th
e
y
i
n
ev
i
tab
l
y
m
o
v
e
to
w
ar
d
s
m
o
r
e
o
r
g
an
ized
m
ar
k
eti
n
g
.
"
T
h
e
th
ir
d
s
tag
e
i
s
w
h
en
th
e
f
o
r
m
alize
d
ap
p
r
o
ac
h
is
ex
ce
s
s
i
v
e
an
d
ca
u
s
e
s
a
ch
an
g
e
is
r
eq
u
ir
ed
,
an
o
th
er
f
o
r
m
o
f
m
ar
k
eti
n
g
ca
lled
I
n
tr
ap
r
en
eu
r
ial
Ma
r
k
eti
n
g
(
I
M
)
th
at
co
u
ld
b
e
th
e
f
o
c
u
s
o
f
f
u
r
th
er
s
t
u
d
y
.
A
co
n
s
e
n
s
u
s
ar
o
s
e
o
n
h
o
w
co
m
p
a
n
ies
th
i
n
k
a
n
d
m
ak
e
m
ar
k
eti
n
g
-
r
elate
d
d
ec
is
io
n
s
.
T
h
er
e
a
r
e
f
iv
e
m
aj
o
r
d
if
f
er
en
ce
s
b
et
w
ee
n
h
o
w
n
o
n
-
en
tr
ep
r
en
eu
r
s
t
h
i
n
k
w
h
ic
h
lo
g
i
c
is
p
r
ed
ictiv
e
an
d
h
o
w
en
tr
ep
r
en
eu
r
s
t
h
i
n
k
t
h
at
lo
g
ic
is
s
u
cc
ess
f
u
l [
1
4
-
1
5
]
:
1.
Fu
t
u
r
e
v
i
s
io
n
.
I
t
is
p
r
ed
ictiv
e
f
o
r
th
e
lo
g
ic
o
f
p
r
ed
ictio
n
an
d
i
m
ag
in
ati
v
e
f
o
r
th
e
lo
g
ic
o
f
i
n
f
lu
e
n
ce
.
T
h
e
f
u
tu
r
e
i
s
s
ee
n
as
a
ca
u
s
al
co
n
ti
n
u
at
io
n
o
f
th
e
p
ast
in
t
h
e
f
ir
s
t
ca
s
e
an
d
ca
n
th
er
e
f
o
r
e
b
e
ex
p
ec
ted
[
1
6
]
.
I
n
th
e
s
ec
o
n
d
ca
s
e,
th
e
f
u
t
u
r
e
i
s
f
o
r
m
ed
,
at
least
in
p
ar
t,
b
y
a
g
en
ts
'
v
o
lu
n
tar
y
ac
tio
n
s
a
n
d
it
s
p
r
ed
ictio
n
i
s
th
er
ef
o
r
e
n
o
t p
o
s
s
ib
le;
2.
T
h
e
f
o
u
n
d
atio
n
o
f
d
ec
is
io
n
-
m
ak
in
g
.
A
ctio
n
s
ar
e
d
eter
m
in
ed
b
y
in
te
n
tio
n
in
p
r
ed
icti
v
e
lo
g
i
c.
A
ctio
n
s
ar
e
d
eter
m
in
ed
b
y
av
ailab
le
m
ea
n
s
o
f
ac
ti
v
e
r
ea
s
o
n
i
n
g
[
1
7
]
.
"
B
o
r
n
"
p
u
r
p
o
s
es
b
y
i
m
a
g
i
n
in
g
co
u
r
s
es
o
f
ac
tio
n
b
ased
o
n
th
e
m
ea
n
s
av
a
ilab
le;
3.
A
tt
itu
d
e
to
r
is
k
.
I
n
s
tati
s
tical
l
o
g
ic,
a
to
tal
b
e
n
ef
i
t
o
p
tio
n
i
s
s
elec
ted
w
h
ile
i
n
ac
t
u
al
lo
g
ic
an
al
ter
n
ati
v
e
is
s
elec
ted
b
ased
o
n
h
o
w
m
u
c
h
th
e
b
u
s
i
n
es
s
m
a
n
ca
n
af
f
o
r
d
to
lo
s
e
b
y
s
elec
t
in
g
it [
1
8
]
;
4.
A
tt
itu
d
e
to
t
h
e
o
u
ts
id
er
s
.
C
o
m
p
eti
tio
n
a
s
i
n
t
h
e
ca
s
e
o
f
p
r
ed
ictiv
e
lo
g
ic
a
n
d
co
o
p
er
atio
n
-
w
h
er
e
r
atio
n
alit
y
is
e
f
f
ec
t
iv
e
[
1
9
]
;
5.
A
tt
itu
d
e
to
w
ar
d
s
u
n
f
o
r
eseen
co
n
tin
g
en
c
ies:
a
v
o
id
an
ce
as
in
t
h
e
ca
s
e
o
f
p
r
ed
ictiv
e
lo
g
ic
a
n
d
f
r
u
cti
f
ica
tio
n
a
s
in
th
e
lo
g
ic
o
f
i
m
p
ac
t.
P
r
ec
is
e
f
o
r
ec
ast
s
,
d
ili
g
en
t
p
r
ep
ar
atio
n
an
d
e
m
p
h
asi
s
o
n
p
r
io
r
ities
th
at
ar
e
u
n
iq
u
e
to
p
r
ed
icti
v
e
r
ea
s
o
n
i
n
g
a
n
d
m
ak
e
co
n
ti
n
g
en
cies
k
n
o
w
n
a
s
b
ar
r
ier
s
to
av
o
id
.
E
v
it
in
g
p
r
ed
ictio
n
s
,
i
m
a
g
i
n
ati
v
e
t
h
i
n
k
in
g
,
co
n
ti
n
u
o
u
s
tr
an
s
f
o
r
m
atio
n
o
f
g
o
als
t
h
at
ar
e
s
p
ec
i
f
ic
to
ef
f
ec
tiv
e
lo
g
ic
an
d
m
ak
i
n
g
co
n
tin
g
e
n
cies
p
er
ce
iv
ed
as
o
p
p
o
r
tu
n
i
ties
f
o
r
cr
ea
tin
g
s
o
m
eth
in
g
n
e
w
an
d
ar
e
th
er
e
f
o
r
e
ap
p
r
ec
ia
ted
[
2
0
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SSN
:
2
2
5
2
-
8938
I
n
t J
A
r
ti
f
I
n
tell
,
Vo
l.
9
,
No
.
1
,
Ma
r
ch
20
20
:
18
–
2
4
20
3.
M
E
T
H
O
DO
L
O
G
Y
T
h
is
r
esear
ch
w
a
s
d
o
n
e
b
y
co
l
lectin
g
d
ata
u
s
i
n
g
s
e
m
i
s
tr
u
ctu
r
e
q
u
esti
o
n
n
air
e
d
is
tr
ib
u
ted
to
1
6
9
s
tar
t
u
p
o
w
n
er
s
i
n
Klan
g
Valle
y
ar
ea
(
k
in
d
l
y
co
n
tact
th
e
co
r
r
esp
o
n
d
in
g
au
t
h
o
r
u
p
o
n
th
e
d
etails
o
f
d
ata
an
d
q
u
esti
o
n
n
air
es).
T
h
e
r
es
u
lt
w
a
s
later
an
a
l
y
s
ed
u
s
in
g
I
B
M
S
P
SS
Statis
tics
v
er
s
io
n
2
5
s
o
f
t
w
ar
e.
T
h
e
f
lo
w
c
h
ar
t
o
f
th
i
s
r
esear
ch
ca
n
b
e
b
e
r
ef
e
r
r
ed
in
Fig
u
r
e
1
.
T
ab
le
1
an
d
Fig
u
r
e
2
s
h
o
w
s
th
e
d
ep
en
d
e
n
t
an
d
th
e
i
n
d
ep
en
d
en
t
v
ar
iab
les in
v
o
led
in
t
h
i
s
r
esear
ch
.
Start
Construct
Questionn
aire
Stratif
ied
Sampling
Data
Key
in
SPSS
Reliability
Analysis
Diagnostic
Checking
Regress
ion
Analysis
Data
Normalization
using
MA
TLAB
Data
Partitioning
Neural
Network
Settings
Data
Preprocessing
MSE=
0?
Finish
Network
Settings
Adjustment
Fig
u
r
e
1
.
R
esear
ch
f
lo
w
ch
ar
t
T
ab
le
1
.
Var
iab
les
in
v
o
lv
ed
in
th
is
r
esear
c
h
N
o
.
V
a
r
i
a
b
l
e
N
o
t
a
t
i
o
n
D
e
scri
p
t
i
o
n
1
I
M
e
a
n
Y
D
i
g
i
t
a
l
n
e
ss
2
S
M
e
a
n
X
1
R
e
so
u
r
c
e
L
e
v
e
r
a
g
i
n
g
3
P
M
e
a
n
X
2
P
r
o
a
c
t
i
v
e
n
e
ss
4
O
M
e
a
n
X
3
O
p
p
o
r
t
u
n
i
t
y
F
o
c
u
s
5
I
N
T
M
e
a
n
X
4
I
n
t
e
n
si
t
y
6
V
M
e
a
n
X
5
V
a
l
u
e
A
d
d
7
R
M
e
a
n
X
6
R
i
s
k
T
a
k
i
n
g
Fig
u
r
e
2
.
I
n
d
ep
en
d
en
t
v
ar
iab
le
s
an
d
d
ep
en
d
en
t
v
ar
iab
le
o
f
th
i
s
r
esear
ch
I
n
d
e
p
e
n
d
e
n
t
V
a
r
i
a
b
l
e
s
S
M
e
a
n
P
M
e
a
n
O
M
e
a
n
I
N
T
M
e
a
n
V
M
e
a
n
R
M
e
a
n
D
e
p
e
n
d
e
n
t
V
a
r
i
a
b
l
e
I
M
e
a
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
A
r
ti
f
I
n
tell
I
SS
N:
2252
-
8938
E
xp
lo
r
a
tio
n
o
n
d
ig
ita
l m
a
r
ke
tin
g
a
s
b
u
s
in
ess
s
tr
a
teg
y
mo
d
el
a
mo
n
g
.
.
.
(
Ha
z
r
ita
A
b
R
a
h
im
)
21
T
h
e
g
en
er
al
f
o
r
m
o
f
th
e
m
o
d
el
ca
n
b
e
w
r
itte
n
as
6
5
5
4
4
3
3
2
2
1
1
0
*
*
*
*
*
*
1
X
X
X
X
X
X
Y
,
w
h
er
e
R
M
e
a
n
V
M
e
a
n
I
N
T
M
e
a
n
O
M
e
a
n
P
M
e
a
n
S
M
e
a
n
I
M
e
a
n
*
*
*
*
*
*
1
5
4
3
3
2
1
0
4.
RE
SU
L
T
S
AND
D
I
SCU
SS
I
O
NS
T
ab
le
2
s
h
o
w
s
th
e
d
ata
p
ar
titi
o
n
i
n
g
d
u
r
i
n
g
t
h
e
p
r
e
-
p
r
o
ce
s
s
i
n
g
s
tag
e.
Fro
m
T
ab
le
3
,
h
y
p
er
b
o
lic
tan
g
e
n
t
w
a
s
u
s
ed
i
n
th
e
f
ir
s
t
la
y
er
(
in
p
u
t
la
y
er
to
h
id
d
en
la
y
e
r
)
in
th
e
n
et
w
o
r
k
,
an
d
p
u
r
eli
n
in
th
e
s
ec
o
n
d
la
y
er
(
h
id
d
en
la
y
er
to
o
u
tp
u
t
la
y
er
)
.
T
h
is
ca
n
b
e
p
r
o
v
en
b
y
th
e
n
et
w
o
r
k
ar
c
h
itect
u
r
e
in
Fi
g
u
r
e
3
.
Mo
r
eo
v
er
,
T
ab
le
4
s
h
o
w
s
t
h
e
m
o
d
el
s
u
m
m
ar
y
f
o
r
b
o
th
tr
ain
i
n
g
a
n
d
test
in
g
s
ets.
Fig
u
r
e
4
(
a
)
ill
u
s
tr
ate
s
t
h
e
s
ca
tter
p
lo
t
o
f
s
tan
d
ar
d
ized
r
ed
is
u
al
s
v
er
s
u
s
th
e
d
ep
en
d
en
t
v
ar
iab
le.
Fu
r
t
h
er
m
o
r
e,
Fig
u
r
e
4
(
b
)
d
em
o
s
tr
ates
t
h
e
P
-
P
P
lo
t
o
f
th
e
s
ta
n
d
ar
d
ized
r
ed
is
u
als.
T
ab
le
2
.
C
ase
p
r
o
ce
s
s
in
g
s
u
m
m
ar
y
N
P
e
r
c
e
n
t
S
a
mp
l
e
T
r
a
i
n
i
n
g
1
1
8
6
9
.
8
%
T
e
st
i
n
g
51
3
0
.
2
%
V
a
l
i
d
1
6
9
1
0
0
.
0
%
Ex
c
l
u
d
e
d
0
T
o
t
a
l
1
6
9
T
ab
le
3
.
Netw
o
r
k
i
n
f
o
r
m
atio
n
I
n
p
u
t
L
a
y
e
r
C
o
v
a
r
i
a
t
e
s
1
S
M
e
a
n
2
P
M
e
a
n
3
O
M
e
a
n
4
I
N
T
M
e
a
n
5
V
M
e
a
n
6
R
M
e
a
n
N
u
mb
e
r
o
f
U
n
i
t
s
a
6
R
e
sca
l
i
n
g
M
e
t
h
o
d
f
o
r
C
o
v
a
r
i
a
t
e
s
S
t
a
n
d
a
r
d
i
z
e
d
H
i
d
d
e
n
L
a
y
e
r
(
s)
N
u
mb
e
r
o
f
H
i
d
d
e
n
L
a
y
e
r
s
1
N
u
mb
e
r
o
f
U
n
i
t
s
i
n
H
i
d
d
e
n
L
a
y
e
r
1
a
3
A
c
t
i
v
a
t
i
o
n
F
u
n
c
t
i
o
n
H
y
p
e
r
b
o
l
i
c
t
a
n
g
e
n
t
O
u
t
p
u
t
L
a
y
e
r
D
e
p
e
n
d
e
n
t
V
a
r
i
a
b
l
e
s
1
I
M
e
a
n
N
u
mb
e
r
o
f
U
n
i
t
s
1
R
e
sca
l
i
n
g
M
e
t
h
o
d
f
o
r
S
c
a
l
e
D
e
p
e
n
d
e
n
t
s
S
t
a
n
d
a
r
d
i
z
e
d
A
c
t
i
v
a
t
i
o
n
F
u
n
c
t
i
o
n
I
d
e
n
t
i
t
y
Er
r
o
r
F
u
n
c
t
i
o
n
S
u
m o
f
S
q
u
a
r
e
s
a
.
Ex
c
l
u
d
i
n
g
t
h
e
b
i
a
s
u
n
i
t
T
ab
le
4
.
Mo
d
el
s
u
m
m
ar
y
T
r
a
i
n
i
n
g
S
u
m o
f
S
q
u
a
r
e
s E
r
r
o
r
2
8
.
1
6
6
R
e
l
a
t
i
v
e
Er
r
o
r
.
4
8
1
S
t
o
p
p
i
n
g
R
u
l
e
U
se
d
1
c
o
n
se
c
u
t
i
v
e
st
e
p
(
s)
w
i
t
h
n
o
d
e
c
r
e
a
s
e
i
n
e
r
r
o
r
a
T
r
a
i
n
i
n
g
T
i
me
0
:
0
0
:
0
0
.
0
9
T
e
st
i
n
g
S
u
m o
f
S
q
u
a
r
e
s E
r
r
o
r
2
2
.
1
9
1
R
e
l
a
t
i
v
e
Er
r
o
r
.
7
0
6
D
e
p
e
n
d
e
n
t
V
a
r
i
a
b
l
e
:
I
M
e
a
n
a
.
Er
r
o
r
c
o
m
p
u
t
a
t
i
o
n
s
a
r
e
b
a
se
d
o
n
t
h
e
t
e
st
i
n
g
s
a
m
p
l
e
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SSN
:
2
2
5
2
-
8938
I
n
t J
A
r
ti
f
I
n
tell
,
Vo
l.
9
,
No
.
1
,
Ma
r
ch
20
20
:
18
–
2
4
22
Fig
u
r
e
3
.
Net
w
o
r
k
a
r
c
h
itect
u
r
e
T
ab
le
5
.
P
ar
am
eter
e
s
ti
m
ate
s
P
r
e
d
i
c
t
o
r
P
r
e
d
i
c
t
e
d
H
i
d
d
e
n
L
a
y
e
r
1
O
u
t
p
u
t
L
a
y
e
r
H
(
1
:
1
)
H
(
1
:
2
)
H
(
1
:
3
)
I
M
e
a
n
I
n
p
u
t
L
a
y
e
r
(
B
i
a
s)
-
.
3
5
7
.
0
4
0
.
6
9
6
S
M
e
a
n
.
3
1
8
.
7
2
7
.
7
3
4
P
M
e
a
n
-
.
0
3
9
.
1
2
3
-
.
6
6
2
O
M
e
a
n
.
8
3
9
-
1
.
2
8
3
-
.
4
6
4
I
N
T
M
e
a
n
-
.
3
0
8
.
7
6
9
-
.
0
0
6
V
M
e
a
n
.
1
0
5
.
0
7
5
-
.
0
6
1
R
M
e
a
n
-
.
2
7
7
-
.
3
6
1
-
.
1
2
2
H
i
d
d
e
n
L
a
y
e
r
1
(
B
i
a
s)
.
6
5
2
H
(
1
:
1
)
1
.
1
8
8
H
(
1
:
2
)
1
.
1
3
3
H
(
1
:
3
)
-
.
9
5
8
T
ab
le
6
s
h
o
w
s
th
e
n
o
r
m
alize
d
i
m
p
o
r
tan
ce
r
esp
ec
tin
g
to
in
n
o
v
ativ
e
d
ig
ital
m
ar
k
eti
n
g
.
I
n
Fig
u
r
e
5
,
it
w
a
s
f
o
u
n
d
th
at
p
r
o
ac
tiv
en
e
s
s
,
r
is
k
tak
in
g
,
r
eso
u
r
ce
lev
er
ag
i
n
g
,
o
p
p
o
r
tu
n
it
y
f
o
c
u
s
,
in
te
n
s
it
y
an
d
v
alu
e
ad
d
ar
e
th
e
s
ig
n
i
f
ica
n
t
f
ac
to
r
s
to
w
ar
d
s
d
ig
ital
m
ar
k
e
ti
n
g
r
esp
ec
ti
v
el
y
.
P
r
o
ac
tiv
en
e
s
s
a
n
d
r
is
k
tak
i
n
g
ar
e
p
r
o
v
en
to
b
e
v
er
y
i
m
p
o
r
tan
t
to
w
ar
d
s
in
n
o
v
ativ
e
d
ig
i
tal
m
ar
k
eti
n
g
f
o
r
b
u
s
in
es
s
es.
Fro
m
t
h
is
b
r
ie
f
r
esear
ch
co
n
d
u
cted
,
th
e
s
e
ar
e
th
e
b
asic
s
k
ill
t
h
at
e
n
tr
ep
r
en
eu
r
s
n
ee
d
to
h
av
e
a
n
i
m
p
ac
t
o
n
a
m
ar
k
e
t
an
d
s
u
b
s
ta
n
ti
ate
th
eir
s
u
cc
es
s
is
cr
u
cial
to
e
n
s
u
r
i
n
g
t
h
e
s
u
r
v
i
v
al
o
f
co
m
p
a
n
ie
s
[
2
1
]
.
W
ith
i
n
t
h
e
co
n
te
x
t
o
f
e
n
tr
ep
r
en
eu
r
ial
ad
v
er
ti
s
in
g
,
t
h
e
m
u
ltit
u
d
e
o
f
s
p
ec
if
ics
ca
n
b
e
u
s
ed
as
a
b
u
s
i
n
ess
s
tr
ate
g
y
t
h
at
is
s
p
ec
if
ica
ll
y
tailo
r
ed
to
c
er
tain
ca
te
g
o
r
ies
o
f
in
d
u
s
t
y
o
r
cu
s
to
m
er
s
eg
m
e
n
ts
[
2
2
]
.
E
x
ce
llen
t
c
u
s
to
m
er
s
er
v
ice
i
s
t
h
e
m
o
s
t
i
m
p
o
r
tan
t
as
p
ec
t
o
f
an
e
f
f
ec
t
iv
e
d
ig
ital
m
ar
k
eti
n
g
ca
m
p
aig
n
[
2
3
]
.
C
u
s
to
m
er
s
’
d
ec
is
io
n
s
ar
e
m
o
r
e
li
k
el
y
to
co
n
v
er
t
an
d
b
ec
o
m
e
r
ep
ea
t
u
s
er
s
an
d
h
av
e
b
r
an
d
lo
y
alt
y
w
h
e
n
th
e
co
n
ten
t
is
i
m
p
o
r
tan
t
to
th
e
co
n
s
u
m
er
.
C
u
s
to
m
er
s
’
d
ec
is
io
n
s
w
i
ll
al
w
a
y
s
ef
f
ec
t
th
e
b
u
s
in
e
s
s
d
ec
is
io
n
s
[
2
4
]
.
T
h
e
p
ar
am
eter
s
etti
n
g
s
o
f
n
eu
r
al
n
et
w
o
r
k
m
o
d
els
u
s
ed
in
th
i
s
r
esear
ch
ca
n
b
e
f
u
r
th
er
i
m
p
r
o
v
ed
as s
u
g
g
es
ted
b
y
[
2
5
-
2
6
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
A
r
ti
f
I
n
tell
I
SS
N:
2252
-
8938
E
xp
lo
r
a
tio
n
o
n
d
ig
ita
l m
a
r
ke
tin
g
a
s
b
u
s
in
ess
s
tr
a
teg
y
mo
d
el
a
mo
n
g
.
.
.
(
Ha
z
r
ita
A
b
R
a
h
im
)
23
(
a
)
(
b
)
Fig
u
r
e
4
.
(
a
)
S
ca
tter
p
lo
t
o
f
s
ta
n
d
ar
d
ized
r
ed
is
u
als
v
s
I
Me
an
,
an
d
(
b
)
P
-
P P
lo
t
o
f
th
e
s
ta
n
d
ar
d
ized
r
ed
is
u
als
T
ab
le
6
.
I
n
d
ep
en
d
en
t
v
ar
iab
le
i
m
p
o
r
tan
ce
I
mp
o
r
t
a
n
c
e
N
o
r
mal
i
z
e
d
I
mp
o
r
t
a
n
c
e
S
M
e
a
n
.
1
8
5
8
5
.
6
%
P
M
e
a
n
.
2
1
6
1
0
0
.
0
%
O
M
e
a
n
.
1
8
4
8
5
.
1
%
I
N
T
M
e
a
n
.
1
1
5
5
3
.
4
%
V
M
e
a
n
.
1
0
2
4
7
.
1
%
R
M
e
a
n
.
1
9
8
9
1
.
9
%
Fig
u
r
e
5.
B
ar
C
h
ar
t
o
f
th
e
n
o
r
m
alize
d
i
m
p
o
r
tan
ce
5.
CO
NCLU
SI
O
N
AND
SU
G
G
E
S
T
I
O
N
F
O
R
F
UT
U
RE
R
E
SE
ARCH
As
a
co
n
clu
s
io
n
,
th
e
o
b
j
ec
tiv
e
o
f
th
is
r
esear
ch
i
s
s
u
cc
e
s
s
f
u
ll
y
ac
h
ie
v
ed
.
Fo
r
f
u
t
u
r
e
r
esear
ch
,
w
e
r
ec
o
m
m
e
n
d
m
o
r
e
w
o
r
k
w
it
h
v
ar
io
u
s
h
y
p
o
t
h
ese
s
an
d
test
in
g
p
ar
a
m
eter
s
f
o
r
ea
ch
o
f
t
h
e
s
e
s
k
ills
.
I
t
is
al
s
o
s
u
g
g
e
s
ted
th
at
t
h
e
r
esp
o
n
s
e
g
r
o
u
p
b
ey
o
n
d
th
e
Kla
n
g
Val
le
y
ar
ea
.
W
ith
t
h
e
aid
o
f
th
e
n
e
u
r
al
n
et
w
o
r
k
a
s
an
en
h
a
n
ce
m
en
t
ag
en
t,
th
e
co
m
b
in
at
io
n
o
f
th
e
to
p
th
r
ee
co
m
p
o
n
e
n
ts
w
it
h
i
n
en
tr
ep
r
en
eu
r
s
h
ip
m
ar
k
eti
n
g
ele
m
e
n
ts
ca
n
b
e
u
s
ed
to
f
o
r
m
a
n
e
w
s
tr
ate
g
y
.
I
t
is
ex
p
ec
ted
th
at
th
e
f
i
n
d
in
g
s
w
o
u
ld
g
iv
e
s
o
m
e
in
p
u
ts
to
th
e
Ma
la
y
s
ia
n
e
n
tr
ep
r
en
eu
r
s
o
n
in
n
o
v
ati
v
e
d
ig
i
tal
m
ar
k
eti
n
g
i
n
t
h
eir
b
u
s
i
n
es
s
es,
r
eg
ar
d
les
s
th
e
s
izes.
ACK
NO
WL
E
D
G
E
M
E
NT
T
h
e
r
esear
ch
w
a
s
s
u
p
p
o
r
ted
b
y
Mi
n
is
tr
y
o
f
E
d
u
ca
tio
n
Ma
la
y
s
ia
(
Mo
E
)
,
an
d
Un
iv
er
s
i
ti
T
ek
n
o
lo
g
i
MA
R
A
t
h
r
o
u
g
h
t
h
e
F
u
n
d
a
m
e
n
tal
R
e
s
ea
r
ch
Gr
a
n
t Sc
h
e
m
e
(
FR
GS)
(
6
0
0
-
I
R
MI
/F
R
GS 5
/3
(
2
1
5
/2
0
1
9
)
)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SSN
:
2
2
5
2
-
8938
I
n
t J
A
r
ti
f
I
n
tell
,
Vo
l.
9
,
No
.
1
,
Ma
r
ch
20
20
:
18
–
2
4
24
RE
F
E
R
E
NC
E
S
[1
]
L
.
C.
Ne
il
so
n
,
“
T
h
e
n
e
w
to
o
ls
b
r
ief
in
g
:
T
e
a
c
h
in
g
n
e
w
m
a
r
k
e
ti
n
g
p
ra
c
ti
c
e
s
a
n
d
tec
h
n
o
l
o
g
y
to
stu
d
e
n
ts”
,
M
a
rk
e
ti
n
g
Ed
u
c
a
ti
o
n
Rev
iew
,
1
9
(1
)
,
p
p
.
4
3
-
4
7
,
2
0
0
9
.
[2
]
D.
M
c
Co
rk
le
&
J.
F
.
A
lex
a
n
d
e
r,
“
Us
in
g
a
Dig
it
a
l
P
e
rso
n
a
l
L
e
a
rn
in
g
Ne
tw
o
rk
A
ss
i
g
n
m
e
n
t
to
T
e
a
c
h
S
o
c
ial
C
u
ra
ti
o
n
a
n
d
L
if
e
lo
n
g
L
e
a
rn
in
g
in
M
a
rk
e
ti
n
g
,
”
J
o
u
rn
a
l
o
f
A
d
v
e
rtisin
g
Ed
u
c
a
ti
o
n
,
2
3
(
2
),
1
0
8
-
1
2
0
,
2
0
1
9
.
[3
]
N.
G
.
Ko
tl
e
r,
P
.
Ko
tl
e
r
&
W
.
I.
Ko
tl
e
r,
M
u
se
u
m
ma
rk
e
ti
n
g
a
n
d
s
tra
teg
y
:
d
e
sig
n
in
g
miss
io
n
s,
b
u
il
d
in
g
a
u
d
ie
n
c
e
s,
g
e
n
e
ra
ti
n
g
re
v
e
n
u
e
a
n
d
re
so
u
rc
e
s
,
Jo
h
n
W
il
e
y
&
S
o
n
s,
2
0
0
8
.
[4
]
M
.
O’D
wy
e
r,
A
.
G
il
m
o
re
&
D.
Ca
rso
n
,
“
Dig
it
a
l
M
a
rk
e
ti
n
g
in
S
M
Es:
A
n
E
m
p
iri
c
a
l
S
tu
d
y
”
,
J
o
u
rn
a
l
o
f
S
tr
a
teg
ic
M
a
rk
e
ti
n
g
,
V
o
l.
1
7
,
Iss
u
e
5
,
p
p
.
3
8
3
-
3
9
6
,
2
0
0
9.
[5
]
M
.
O’D
wy
e
r,
A
.
G
il
m
o
re
&
D.
Ca
rso
n
,
“
Dig
it
a
l
M
a
rk
e
ti
n
g
in
S
M
Es
–
Do
e
s
I
t
Ex
ist?”
Eu
r
o
p
e
a
n
J
o
u
rn
a
l
o
f
M
a
rk
e
ti
n
g
,
V
o
l.
4
3
,
p
p
.
4
6
-
6
1
,
2
0
0
9
.
[6
]
J.
Hill
,
“
A
M
u
lt
id
im
e
n
sio
n
a
l
S
t
u
d
y
o
f
th
e
Ke
y
De
ter
m
in
a
n
ts
o
f
E
ff
e
c
ti
v
e
S
M
E
M
a
rk
e
ti
n
g
A
c
t
iv
it
y
:
P
a
rt
1
”
,
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
E
n
tre
p
re
n
e
u
ria
l
Beh
a
v
i
o
u
r
a
n
d
Res
e
a
rc
h
,
V
o
l
.
7
,
No
.
5
,
p
p
.
1
7
1
-
2
0
4
,
2
0
0
1
.
[7
]
J.
Hill
,
“
A
M
u
lt
id
im
e
n
sio
n
a
l
S
t
u
d
y
o
f
th
e
Ke
y
De
ter
m
in
a
n
ts
o
f
E
ff
e
c
ti
v
e
S
M
E
M
a
rk
e
ti
n
g
A
c
t
iv
it
y
:
P
a
rt
1
”
,
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
E
n
tre
p
re
n
e
u
ria
l
Beh
a
v
i
o
u
r
a
n
d
Res
e
a
rc
h
,
V
o
l
.
7
,
No
.
6
,
p
p
.
2
1
1
-
3
5
,
2
0
0
1
.
[8
]
J.
M
o
riarty
,
R.
Jo
n
e
s,
J.
Ro
w
le
y
&
B.
Ku
p
iec
-
T
e
a
h
a
n
,
“
M
a
rk
e
ti
n
g
In
S
m
a
ll
Ho
tels:
A
Qu
a
li
tativ
e
S
tu
d
y
”
,
M
a
rk
e
ti
n
g
In
telli
g
e
n
c
e
a
n
d
P
la
n
n
i
n
g
,
V
o
l.
2
6
,
N
o
.
3
,
p
p
.
2
9
3
-
3
1
5
,
2
0
0
8
.
[9
]
S
.
M
o
r
rish
&
J.
De
a
c
o
n
,
“
A
T
a
l
e
o
f
Tw
o
S
p
iri
t
s:
En
tre
p
re
n
e
u
ria
l
M
a
rk
e
ti
n
g
a
t
4
2
b
e
lo
w
V
o
d
k
a
a
n
d
P
e
n
d
e
ry
n
W
h
isk
y
”
,
J
o
u
rn
a
l
o
f
S
m
a
ll
B
u
sin
e
ss
a
n
d
En
tre
p
re
n
e
u
rs
h
ip
,
V
o
l.
2
4
,
No
.
1
,
p
p
.
1
1
3
-
2
4
,
2
0
1
1
.
[1
0
]
M
.
P
.
M
il
e
s
&
J.
Da
rro
c
h
,
“
L
a
rg
e
F
ir
m
s,
En
trep
re
n
e
u
rial
M
a
rk
e
ti
n
g
P
r
o
c
e
ss
e
s,
a
n
d
th
e
Cy
c
le
o
f
Co
m
p
e
ti
ti
v
e
A
d
v
a
n
ta
g
e
”
,
Eu
ro
p
e
a
n
J
o
u
r
n
a
l
o
f
M
a
rk
e
ti
n
g
,
Vo
l.
4
0
No
.
5
/
6
,
p
p
.
4
8
5
-
5
0
1
,
2
0
0
6
.
[1
1
]
M
.
S
c
h
i
n
d
e
h
u
tt
e
,
M
.
H.
M
o
r
ris
&
A
.
Ko
c
a
k
,
“
Un
d
e
rsta
n
d
in
g
M
a
rk
e
t
-
Driv
in
g
Be
h
a
v
io
r:
T
h
e
Ro
le
o
f
En
trep
re
n
e
u
rsh
ip
”
,
J
o
u
r
n
a
l
o
f
S
m
a
ll
B
u
sin
e
ss
M
a
n
a
g
e
me
n
t
,
V
o
l.
4
6
,
Iss
u
e
(
1
),
p
p
.
4
-
2
6
,
2
0
0
8
.
[1
2
]
M
.
S
c
h
i
n
d
e
n
h
u
tt
e
&
H.
M
.
M
o
rri
s,
"
Un
d
e
rsta
n
d
in
g
S
trate
g
ic
A
d
a
p
tatio
n
I
n
S
m
a
ll
F
irms
"
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
En
tre
p
re
n
e
u
ri
a
l
Beh
a
v
io
r
a
n
d
Re
se
a
rc
h
,
Vo
l.
7
,
No
.
3
,
p
p
.
8
4
-
1
0
7
,
2
0
0
1
.
[1
3
]
A
.
M
o
u
ss
a
v
i
&
A
.
Ke
r
m
a
n
sh
a
h
,
“
In
n
o
v
a
ti
o
n
sy
ste
m
s
a
p
p
ro
a
c
h
:
A
p
h
il
o
s
o
p
h
ica
l
a
p
p
ra
isa
l”,
Ph
il
o
so
p
h
y
o
f
M
a
n
a
g
e
me
n
t
,
1
7
(1
)
,
5
9
-
7
7
,
2
0
1
8
.
[1
4
]
S
.
G
h
e
ra
rd
i,
Ho
w
t
o
c
o
n
d
u
c
t
a
p
r
a
c
ti
c
e
-
b
a
se
d
st
u
d
y
:
Pr
o
b
lem
s a
n
d
me
th
o
d
s
,
Ed
w
a
rd
El
g
a
r
P
u
b
li
sh
in
g
,
2
0
1
9
.
[1
5
]
F
.
Ş
a
h
in
,
H.
Ka
ra
d
a
ğ
&
B.
T
u
n
c
e
r,
“
Big
f
iv
e
p
e
rso
n
a
li
ty
traits,
e
n
trep
re
n
e
u
rial
se
lf
-
e
ff
ica
c
y
a
n
d
e
n
trep
re
n
e
u
ria
l
in
ten
ti
o
n
:
A
c
o
n
f
ig
u
ra
ti
o
n
a
l
a
p
p
r
o
a
c
h
”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
E
n
tre
p
re
n
e
u
ria
l
Beh
a
v
io
r &
Res
e
a
rc
h
, 1
-
2
5
,
2
0
1
9
.
[1
6
]
A
.
L
a
s
k
o
v
a
ia,
L
.
M
a
rin
o
,
G
.
S
h
iro
k
o
v
a
&
W
.
W
a
le
s,
“
Ex
p
e
c
t
t
h
e
u
n
e
x
p
e
c
ted
:
e
x
a
m
in
in
g
th
e
sh
a
p
in
g
ro
le
o
f
e
n
tr
e
p
re
n
e
u
rial
o
rien
tati
o
n
o
n
c
a
u
sa
l
a
n
d
e
ff
e
c
tu
a
l
d
e
c
isio
n
-
m
a
k
in
g
lo
g
ic
d
u
rin
g
e
c
o
n
o
m
ic
c
risis”
,
En
tre
p
re
n
e
u
rs
h
i
p
&
Reg
i
o
n
a
l
De
v
e
lo
p
me
n
t
,
3
1
(5
-
6
),
4
5
6
-
4
7
5
,
2
0
1
9
.
[1
7
]
Y.
L
iu
,
Z.
Ou
y
a
n
g
&
P
.
Ch
e
n
g
,
“
P
re
d
ictin
g
c
o
n
s
u
m
e
rs’ ad
o
p
ti
o
n
o
f
e
le
c
tri
c
v
e
h
icle
s d
u
rin
g
th
e
c
i
ty
s
m
o
g
c
risis:
A
n
a
p
p
li
c
a
ti
o
n
o
f
th
e
p
ro
tec
ti
v
e
a
c
ti
o
n
d
e
c
isio
n
m
o
d
e
l”,
J
o
u
r
n
a
l
o
f
En
v
iro
n
me
n
ta
l
Psy
c
h
o
l
o
g
y
,
6
4
,
3
0
-
3
8
,
2
0
1
9
.
[1
8
]
D.
M
.
T
a
o
f
e
e
q
,
A
.
Q.
A
d
e
lek
e
&
A
.
K.
Ha
ss
a
n
,
“
F
a
c
to
rs
Affe
c
ti
n
g
Co
n
trac
to
rs
risk
a
tt
it
u
d
e
f
ro
m
M
a
la
y
sia
c
o
n
stru
c
ti
o
n
in
d
u
stry
p
e
r
sp
e
c
ti
v
e
”
,
S
o
c
i
a
l
S
c
ie
n
c
e
a
n
d
Hu
m
a
n
it
ies
J
o
u
rn
a
l
,
1
2
8
1
-
1
2
9
8
,
2
0
1
9
.
[1
9
]
F
.
Ne
g
ri,
“
Eco
n
o
m
ic
o
r
c
u
lt
u
ra
l
b
a
c
k
las
h
?
Re
th
in
k
in
g
o
u
tsid
e
rs’
v
o
ti
n
g
b
e
h
a
v
io
r.
”
El
e
c
to
ra
l
S
tu
d
i
e
s
,
5
9
,
1
5
8
-
1
6
3
,
2
0
1
9
.
[2
0
]
M
.
He
rb
e
rg
,
G
.
E.
T
o
rg
e
r
se
n
&
T
.
Ru
n
d
m
o
,
“
Co
m
p
e
ten
c
e
f
o
r
th
e
Un
f
o
re
se
e
n
:
S
o
c
ial
S
u
p
p
o
rt
a
n
d
Co
n
c
u
rre
n
t
L
e
a
rn
in
g
a
s Ba
sic
Co
m
p
o
n
e
n
ts o
f
In
tera
c
ti
o
n
u
n
d
e
r
Risk
”
,
Fro
n
ti
e
r
s in
Co
mm
u
n
ica
ti
o
n
,
4
,
1
9
,
2
0
1
9
.
[2
1
]
T
.
M
.
Co
o
n
e
y
&
M
.
L
icc
iar
d
i,
“
T
h
e
S
a
m
e
b
u
t
Diff
e
r
e
n
t:
Un
d
e
rsta
n
d
i
n
g
En
trep
re
n
e
u
rial
Be
h
a
v
io
u
r
in
Disa
d
v
a
n
tag
e
d
Co
m
m
u
n
it
ies
”
,
En
tre
p
re
n
e
u
ria
l
Be
h
a
v
i
o
u
r
,
p
p
.
3
1
7
-
3
4
5
,
2
0
1
9
.
[2
2
]
A
.
A
n
n
a
re
ll
i,
C.
Ba
tt
istella
&
F
.
No
n
in
o
,
“
Ho
w
to
T
rig
g
e
r
th
e
S
trate
g
ic
A
d
v
a
n
tag
e
o
f
P
ro
d
u
c
t
S
e
r
v
ice
S
y
ste
m
s
”
,
In
T
h
e
Ro
a
d
to
S
e
rv
it
iza
ti
o
n
,
S
p
r
i
n
g
e
r,
Ch
a
m
,
2
0
1
9
,
p
p
.
9
5
-
1
4
1
.
[2
3
]
S
.
Kin
g
sn
o
rt
h
,
Dig
it
a
l
ma
rk
e
ti
n
g
stra
teg
y
:
a
n
in
te
g
ra
ted
a
p
p
r
o
a
c
h
to
o
n
li
n
e
ma
rk
e
ti
n
g
,
Ko
g
a
n
P
a
g
e
P
u
b
l
ish
e
rs,
2
0
1
9
.
[2
4
]
P
.
P
.
R
o
k
a
d
e
,
“
Bu
sin
e
ss
re
c
o
m
m
e
n
d
a
ti
o
n
b
a
se
d
o
n
c
o
l
lab
o
ra
ti
v
e
f
il
terin
g
a
n
d
f
e
a
tu
re
e
n
g
in
e
e
rin
g
–
a
p
ro
p
o
s
e
d
a
p
p
ro
a
c
h
”
,
I
n
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
&
Co
mp
u
ter
En
g
in
e
e
ri
ng
,
9
,
p
p
.
2
0
8
8
-
8
7
0
8
,
2
0
1
9
.
[2
5
]
A
.
S
.
Ra
wa
t,
A
.
Ra
n
a
,
A
.
Ku
m
a
r
&
A
.
Ba
g
w
a
ri,
“
A
p
p
li
c
a
ti
o
n
o
f
M
u
lt
i
L
a
y
e
r
Artif
icia
l
Ne
u
ra
l
Ne
tw
o
rk
in
th
e
Dia
g
n
o
sis
S
y
ste
m
:
A
S
y
ste
m
a
ti
c
Re
v
ie
w
”
,
IAE
S
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
of
Arti
fi
c
ia
l
In
telli
g
e
n
c
e
(
IJ
-
A
I)
,
v
o
l,
7
,
No
.
3
138
-
1
4
2
,
2
0
1
8
.
[2
6
]
H.
Ka
ri
m
,
S
.
R.
Nia
k
a
n
&
R.
S
a
f
d
a
ri,
“
Co
m
p
a
riso
n
o
f
Ne
u
ra
l
Ne
tw
o
rk
T
ra
in
in
g
A
lg
o
rit
h
m
s
f
o
r
C
las
sif
ic
a
ti
o
n
o
f
He
a
rt
Dise
a
s
e
s”
,
IAE
S
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
of
Art
if
icia
l
In
tell
ig
e
n
c
e
(
I
J
-
AI)
,
v
o
l,
7
,
No
.
4
,
2
0
1
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.