I
nte
rna
t
io
na
l J
o
urna
l o
f
Adv
a
nces in Applie
d Science
s
(
I
J
AAS)
Vo
l.
1
5
,
No
.
1
,
Ma
r
ch
20
2
6
,
p
p
.
24
4
~
2
5
2
I
SS
N:
2252
-
8
8
1
4
,
DOI
:
1
0
.
1
1
5
9
1
/ijaas
.
v
1
5
.
i
1
.
pp
24
4
-
2
5
2
244
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
a
s
.
ia
esco
r
e.
co
m
Financia
l distr
ess
predic
tion for
ba
tik
s
ma
ll and
m
ed
ium
e
nterpr
ises
cre
dit
f
ina
ncing
bas
ed
o
n deep
lea
rni
ng
a
lg
o
rithm
T
a
ry
a
di
1
,
B
a
m
ba
ng
Su
diy
a
t
no
2
,
Ro
bert
us
B
a
s
iy
a
2
,
E
ra
Yuni
a
nto
1
1
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
S
y
s
t
e
m
s
,
F
a
c
u
l
t
y
o
f
I
n
f
o
r
ma
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
I
n
st
i
t
u
t
e
o
f
W
i
d
y
a
P
r
a
t
a
ma
,
P
e
k
a
l
o
n
g
a
n
,
I
n
d
o
n
e
s
i
a
2
D
e
p
a
r
t
me
n
t
o
f
M
a
n
a
g
e
me
n
t
,
F
a
c
u
l
t
y
o
f
Ec
o
n
o
mi
c
s a
n
d
B
u
s
i
n
e
ss
,
U
n
i
v
e
r
si
t
y
o
f
S
t
i
k
u
b
a
n
k
,
S
e
mara
n
g
,
I
n
d
o
n
e
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
5
,
2
0
2
4
R
ev
is
ed
J
u
n
1
4
,
2
0
2
5
Acc
ep
ted
J
an
1
3
,
2
0
2
6
On
e
o
f
th
e
b
ig
g
e
st
o
b
sta
c
les
th
a
t
a
n
y
fin
a
n
c
e
p
r
o
v
i
d
e
r
h
a
s
wh
e
n
e
v
a
lu
a
ti
n
g
a
b
o
rr
o
we
r'
s
c
re
d
it
wo
rth
i
n
e
ss
is
th
e
p
re
d
ictio
n
o
f
fin
a
n
c
ial
tro
u
b
le.
Th
e
c
re
d
it
d
e
c
isio
n
-
m
a
k
i
n
g
p
r
o
c
e
ss
is
m
a
d
e
m
o
re
d
iffi
c
u
lt
fo
r
sm
a
ll
a
n
d
m
e
d
iu
m
e
n
terp
rise
s
(S
M
Es)
d
u
e
to
th
e
ir
i
n
h
e
re
n
t
a
m
b
ig
u
it
y
,
wh
ic
h
ra
ise
s
fin
a
n
c
in
g
c
o
sts
a
n
d
lo
we
rs
th
e
c
h
a
n
c
e
o
f
a
p
p
ro
v
a
l.
In
o
rd
e
r
to
e
stim
a
te
a
b
in
o
m
ial
c
las
sifier
fo
r
p
re
d
icti
n
g
fin
a
n
c
ia
l
h
a
rd
sh
ip
u
sin
g
l
o
g
ist
ic
re
g
re
ss
io
n
(
LR)
,
e
x
trem
e
g
ra
d
ien
t
b
o
o
st
in
g
(XG
Bo
o
st)
,
a
n
d
a
rti
ficia
l
n
e
u
ra
l
n
e
tw
o
rk
(AN
N)
tec
h
n
iq
u
e
s,
th
is
st
u
d
y
e
x
a
m
in
e
s
d
a
ta
fro
m
b
a
ti
k
S
M
Es
i
n
P
e
k
a
l
o
n
g
a
n
c
it
y
.
F
in
a
n
c
ial
ra
ti
o
s
p
re
d
ict
t
h
e
first
p
e
rio
d
a
n
d
g
ro
w
i
n
a
m
u
lt
i
-
p
e
rio
d
m
o
d
e
l
b
a
se
d
o
n
tem
p
o
ra
l
fa
c
to
rs,
c
re
d
it
h
isto
r
y
,
a
n
d
a
g
e
.
F
in
a
n
c
ial
d
istres
s
is
d
e
fin
e
d
a
s
a
su
b
sta
n
ti
a
l
o
b
sta
c
le
to
a
b
u
sin
e
ss
'
s
c
a
p
a
c
it
y
t
o
p
a
y
i
ts
d
e
b
ts
a
s o
p
p
o
se
d
t
o
t
h
e
p
o
ten
ti
a
l
fo
r
b
a
n
k
r
u
p
tcy
.
Th
e
l
o
n
g
sh
o
rt
-
term
m
e
m
o
ry
(LS
TM
)
a
lg
o
rit
h
m
with
m
o
re
v
a
riab
les
y
ield
s
t
h
e
b
e
st
p
re
d
icti
o
n
a
c
c
u
ra
c
y
.
T
h
e
stu
d
y
'
s
c
o
n
c
lu
si
o
n
in
d
ica
tes
th
a
t
i
n
o
rd
e
r
to
g
u
a
ra
n
tee
t
h
e
a
c
c
u
ra
c
y
o
f
fin
a
n
c
ial
d
istres
s p
re
d
icti
o
n
,
th
e
t
ime
a
t
risk
m
u
st
b
e
a
d
ju
ste
d
.
K
ey
w
o
r
d
s
:
B
atik
Dee
p
lear
n
in
g
Fin
an
cial
d
is
tr
ess
L
o
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
Sm
all
an
d
m
ed
iu
m
en
ter
p
r
is
es
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
:
T
ar
y
ad
i
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atio
n
Sy
s
tem
s
,
Facu
lty
o
f
I
n
f
o
r
m
atio
n
T
ec
h
n
o
lo
g
y
,
I
n
s
titu
te
o
f
W
id
y
a
Pra
tam
a
Patr
io
t Ro
ad
No
.
2
5
,
Pek
alo
n
g
an
,
C
en
tr
al
J
av
a
,
I
n
d
o
n
es
ia
E
m
ail:
tar
i_
b
all@
s
tm
ik
-
wp
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
C
r
ed
it
r
is
k
m
o
d
ellin
g
b
e
g
in
s
with
len
d
er
s
wh
o
m
u
s
t
ca
lcu
la
te
th
e
ca
p
ital
r
eq
u
ir
em
e
n
ts
to
s
u
p
p
o
r
t
th
e
lo
an
s
p
r
o
v
id
e
d
.
On
e
o
f
th
e
ef
f
o
r
ts
im
p
lem
en
ted
is
b
y
r
eq
u
ir
i
n
g
a
m
in
im
u
m
m
o
d
el
as
o
n
e
o
f
th
e
r
eq
u
ir
em
e
n
ts
in
b
an
k
ass
et
allo
ca
tio
n
.
L
en
d
e
r
s
ca
n
ch
o
o
s
e
o
n
e
o
f
th
e
cr
e
d
it
r
is
k
m
a
n
ag
em
e
n
t
ap
p
r
o
ac
h
e
s
,
n
am
ely
th
e
s
tan
d
ar
d
ap
p
r
o
ac
h
o
r
th
e
in
ter
n
al
r
atin
g
-
b
ased
ap
p
r
o
ac
h
[
1
]
.
T
h
is
is
w
h
at
ca
u
s
es sm
all
an
d
m
ed
iu
m
en
ter
p
r
is
es (
SME
s
)
to
r
ec
eiv
e
d
if
f
e
r
en
t
t
r
ea
tm
en
t
f
r
o
m
o
th
er
b
u
s
in
ess
en
titi
es
r
eg
ar
d
in
g
cr
ed
it
r
is
k
.
SME
s
ar
e
o
n
e
o
f
th
e
b
ac
k
b
o
n
es
o
f
th
e
wo
r
ld
ec
o
n
o
m
y
a
n
d
t
h
e
welf
ar
e
o
f
th
e
co
u
n
tr
y
.
On
e
o
f
th
e
ch
allen
g
es
f
ac
ed
b
y
SME
s
in
r
ec
en
t d
ec
ad
es
is
ac
ce
s
s
to
f
in
an
cin
g
.
I
n
ad
d
itio
n
,
ca
p
ital
av
ailab
ilit
y
r
eq
u
ir
e
m
en
ts
also
p
u
t
p
r
ess
u
r
e
o
n
b
an
k
s
to
p
r
o
v
id
e
lo
a
n
s
to
SME
s
.
T
h
e
in
ab
il
ity
o
f
b
an
k
s
to
f
u
n
d
SME
s
is
h
am
p
er
ed
b
y
th
e
in
cr
ea
s
in
g
b
u
r
d
en
th
at
co
m
es
with
in
cr
ea
s
in
g
m
in
im
u
m
ca
p
ital
r
atio
s
(
w
h
ich
cu
r
r
en
tly
av
er
a
g
e
6
%
t
o
8
%)
[
2]
.
Ma
n
y
s
tu
d
ies
h
av
e
s
h
o
w
n
th
e
im
p
o
r
tan
ce
o
f
SME
s
'
h
ea
lth
[
3
]
–
[
6
]
in
p
r
o
v
id
in
g
cr
e
d
it.
E
d
m
is
ter
[
7
]
ef
f
ec
tiv
el
y
m
o
d
el
led
b
asic
cr
ed
it
ev
alu
atio
n
f
o
r
b
u
s
in
ess
o
r
g
an
izatio
n
s
,
an
d
s
o
p
io
n
ee
r
ed
cr
ed
it
r
is
k
m
o
d
ellin
g
f
o
r
SME
s
.
I
n
th
e
m
ea
n
tim
e,
Altm
an
an
d
Sab
ato
[
8
]
lo
o
k
ed
at
th
e
th
eo
r
etica
l
an
d
p
r
ac
tical
ev
alu
atio
n
o
f
SME
s
'
d
ef
au
lt
l
ik
elih
o
o
d
.
T
h
e
d
ev
el
o
p
ed
m
o
d
el
was
ab
le
to
p
r
e
d
ict
f
in
a
n
cial
d
if
f
icu
lties
f
o
r
SME
s
,
r
esu
ltin
g
in
a
r
ed
u
ctio
n
in
m
o
d
el
r
eq
u
i
r
em
en
ts
b
y
0
.
5
%.
B
ased
o
n
th
is
,
it
ca
n
b
e
s
ai
d
th
at:
i
)
SME
s
ar
e
d
if
f
er
en
t
f
r
o
m
lar
g
e
co
m
p
a
n
ie
s
b
ased
o
n
cr
ed
it
r
is
k
;
an
d
ii
)
B
an
k
s
m
u
s
t
d
if
f
er
en
tiate
th
e
p
r
o
ce
d
u
r
es
f
o
r
r
an
k
in
g
an
d
ass
ess
in
g
SME
s
in
p
r
o
v
id
i
n
g
cr
ed
it.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
F
in
a
n
cia
l d
is
tr
ess
p
r
ed
ictio
n
fo
r
b
a
tik
s
ma
ll a
n
d
med
i
u
m
en
t
erp
r
is
e
s
cred
it fin
a
n
cin
g
b
a
s
e
d
…
(
Ta
r
ya
d
i
)
245
C
r
ed
it
to
SME
s
is
p
o
s
itiv
ely
im
p
ac
ted
b
y
t
h
e
ad
o
p
tio
n
o
f
g
o
v
er
n
m
en
t
g
u
ar
an
tee
p
r
o
g
r
a
m
s
,
cr
ed
it
p
r
o
tectio
n
p
lan
s
,
an
d
ac
co
u
n
tin
g
s
tan
d
ar
d
s
[
5
]
.
Z
h
u
et
a
l
.
[
6
]
s
tated
th
at
SME
lo
an
s
h
av
e
a
g
r
ea
ter
r
is
k
th
an
lar
g
e
co
r
p
o
r
ate
lo
a
n
s
.
T
h
u
s
,
p
r
ed
ictin
g
f
in
a
n
cial
d
is
tr
ess
is
a
k
ey
is
s
u
e
f
o
r
le
n
d
er
s
,
b
o
th
in
d
eter
m
in
in
g
th
e
f
in
an
cial
ca
p
ac
ity
o
f
b
o
r
r
o
wer
s
an
d
w
h
en
d
eter
m
in
in
g
t
h
e
ca
p
ital
r
eq
u
ir
e
m
en
ts
s
et
b
y
f
i
n
an
cial
r
eg
u
lato
r
s
.
T
h
e
m
ain
g
o
al
o
f
b
an
k
r
u
p
tcy
p
r
ed
i
ctio
n
is
to
f
o
r
ec
ast
wh
en
a
c
o
r
p
o
r
at
io
n
will
ce
ase
to
b
e
v
iab
le;
f
in
an
cial
d
if
f
ic
u
lty
is
m
o
r
e
lik
ely
to
b
e
p
r
ed
icted
wh
en
a
co
m
p
an
y
is
h
a
v
in
g
tr
o
u
b
le
f
u
lf
illi
n
g
its
r
esp
o
n
s
ib
ilit
ies
[
2
]
.
So
m
etim
es
f
in
an
cial
h
ar
d
s
h
ip
is
m
er
ely
a
s
etb
ac
k
th
at
p
ass
es
q
u
ick
ly
,
b
u
t
o
th
er
tim
es
it
r
esu
lts
in
b
a
n
k
r
u
p
tcy
.
L
e
n
d
er
s
lo
o
k
at
th
e
tim
e
o
f
cr
e
d
itwo
r
th
in
ess
ass
es
s
m
en
t to
id
en
tify
th
e
b
o
r
r
o
wer
'
s
ab
ilit
y
to
r
ep
ay
th
eir
c
r
ed
it.
R
esear
ch
o
n
cr
ed
it r
is
k
m
o
d
ell
in
g
h
as e
x
p
an
d
e
d
d
r
am
atica
lly
d
u
r
in
g
th
e
p
ast 5
0
y
ea
r
s
,
p
ar
ti
cu
lar
ly
in
th
e
wo
r
k
s
o
f
Altm
an
[
9
]
an
d
Me
r
to
n
[
1
0
]
.
R
esear
ch
h
as
e
m
p
lo
y
ed
m
ac
h
in
e
lear
n
in
g
te
ch
n
iq
u
es
to
esti
m
ate
cr
ed
it
r
is
k
an
d
f
in
a
n
cial
d
is
tr
ess
in
th
e
p
ast
2
0
y
ea
r
s
,
m
ain
ly
ab
an
d
o
n
in
g
class
ical
m
o
d
el
lin
g
[
8
]
,
[
1
1
]
–
[
1
3
]
.
Atiy
a
[
1
4
]
d
ev
elo
p
ed
t
h
e
f
ir
s
t
m
ac
h
in
e
lear
n
in
g
tech
n
i
q
u
e
f
o
r
f
in
an
cial
cr
is
is
p
r
ed
icti
o
n
b
y
s
im
u
latin
g
tr
ad
itio
n
al
p
r
ed
ictio
n
s
m
ad
e
b
y
Me
r
to
n
[
1
0
]
u
s
in
g
ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
(
ANN)
.
T
s
ai
an
d
W
u
[
1
5
]
u
s
ed
m
an
y
ca
teg
o
r
is
atio
n
m
o
d
els
to
ap
p
ly
a
m
o
d
el
th
at
was
co
m
p
ar
ab
le
to
p
ar
a
m
etr
ic
m
o
d
elli
n
g
.
W
h
en
co
m
p
ar
ed
to
a
s
in
g
le
class
if
ica
tio
n
m
o
d
el,
th
is
ap
p
r
o
ac
h
p
er
f
o
r
m
s
p
o
o
r
ly
.
R
esear
ch
er
s
h
av
e
b
ee
n
u
s
in
g
ANN
m
o
d
els
ex
ten
s
iv
ely
,
an
d
th
ey
s
h
o
w
p
r
o
m
is
e
as o
n
e
o
f
t
h
e
m
o
s
t p
o
p
u
lar
m
o
d
ellin
g
m
eth
o
d
s
[
2
]
,
[
8
]
,
[
9
]
.
Sev
er
al
r
esear
ch
er
s
u
s
e
m
ac
h
i
n
e
l
ea
r
n
in
g
tech
n
iq
u
es
to
m
o
d
el
cr
ed
it
r
is
k
[
2
]
,
[
3
]
,
[
1
6
]
–
[
1
9
]
,
to
o
b
tain
th
e
m
o
s
t
ap
p
r
o
p
r
iate
a
p
p
r
o
ac
h
ac
co
r
d
in
g
to
ce
r
tain
co
n
d
itio
n
s
,
s
itu
atio
n
s
,
an
d
t
y
p
es
o
f
in
d
u
s
t
r
ies.
Ma
n
y
s
tu
d
ies
u
s
e
v
ar
io
u
s
tech
n
i
q
u
es
an
d
m
eth
o
d
o
lo
g
ies
to
p
r
e
d
ict
f
in
an
c
ial
d
is
tr
ess
,
p
r
o
d
u
cin
g
v
ar
y
i
n
g
r
esu
lts
.
Alth
o
u
g
h
m
an
y
f
in
a
n
cial
d
is
tr
ess
p
r
ed
ictio
n
s
h
av
e
b
ee
n
c
o
n
d
u
cted
an
d
well
-
s
tu
d
ied
,
th
er
e
h
as
b
ee
n
litt
le
r
esear
ch
o
n
SME
s
,
esp
ec
ially
u
s
in
g
tim
e
f
ac
to
r
s
an
d
th
e
u
s
e
o
f
d
ee
p
lea
r
n
in
g
tech
n
i
q
u
es.
T
h
e
p
u
r
p
o
s
e
o
f
th
is
s
tu
d
y
is
t
o
u
s
e
d
ee
p
lear
n
in
g
an
d
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
to
an
tic
ip
ate
th
e
cr
e
d
it
r
atin
g
p
r
o
s
p
ec
ts
o
f
SME
s
in
o
n
e
y
ea
r
a
n
d
t
o
o
f
f
er
a
f
i
n
an
cial
d
i
s
tr
ess
p
r
ed
ictio
n
m
o
d
el
th
at
ta
k
es in
to
ac
co
u
n
t th
e
tim
e
v
ar
ia
b
le
[
1
1
]
,
[
1
2
]
.
T
h
is
s
tu
d
y
ass
ess
es
th
e
cr
ed
it
r
atin
g
p
r
o
s
p
ec
ts
b
y
m
o
d
ellin
g
t
h
e
f
in
an
cial
d
is
tr
ess
o
f
SME
s
,
wh
er
e
b
a
n
k
r
u
p
tcy
o
r
d
ef
au
lt
d
o
es
n
o
t
alwa
y
s
o
cc
u
r
,
in
co
n
t
r
ast
to
o
th
er
s
tu
d
ies
th
at
f
o
cu
s
o
n
th
e
p
r
o
b
ab
ilit
y
o
f
d
ef
au
lt.
T
h
e
tim
e
elem
en
t is ad
d
ed
to
t
h
e
h
is
to
r
i
ca
l f
ea
tu
r
es,
s
ales,
an
d
ass
et
ch
an
g
es,
in
a
d
d
itio
n
to
th
e
f
in
a
n
cial
r
atio
v
ar
iab
les.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
is
s
tu
d
y
u
s
es
f
in
an
cial
r
ep
o
r
t
d
ata
an
d
th
e
c
r
ed
it
h
is
to
r
y
o
f
b
atik
SME
s
in
Pek
alo
n
g
a
n
city
.
T
h
e
v
ar
iab
les u
s
ed
ar
e
2
3
in
d
ep
en
d
en
t v
ar
iab
les to
class
if
y
f
in
an
cial
d
if
f
icu
lties
o
v
er
a
p
er
io
d
o
f
th
r
ee
co
n
s
ec
u
tiv
e
y
ea
r
s
.
C
o
m
p
ar
is
o
n
o
f
th
e
f
in
an
cial
s
itu
atio
n
o
f
th
e
p
r
ev
io
u
s
f
is
ca
l
y
ea
r
with
th
e
cu
r
r
e
n
t
f
is
ca
l
y
ea
r
,
an
d
co
m
p
ar
is
o
n
o
f
cr
e
d
it
s
co
r
e
d
e
clin
es
ar
e
u
s
ed
as
d
ep
en
d
en
t
v
ar
iab
les.
C
lass
if
icatio
n
p
er
f
o
r
m
an
ce
is
im
p
r
o
v
ed
b
y
tak
in
g
a
d
if
f
er
en
t
v
ar
iab
le
s
elec
tio
n
ap
p
r
o
ac
h
.
I
n
ad
d
itio
n
to
u
s
in
g
f
in
a
n
cial
r
a
tio
v
a
r
iab
les
in
one
-
tim
e
f
ac
to
r
s
an
d
s
ales
ch
ar
ac
ter
is
tics
,
ass
et
ch
an
g
es
an
d
cr
ed
it
m
atu
r
ity
in
d
icato
r
s
ar
e
also
u
s
ed
.
T
h
is
s
tu
d
y
u
s
es
a
liter
atu
r
e
r
ev
iew
an
aly
s
is
m
eth
o
d
an
d
f
in
a
n
cial
d
is
tr
ess
m
o
d
ellin
g
u
s
in
g
d
ee
p
lear
n
i
n
g
a
lg
o
r
ith
m
s
,
n
am
el
y
lo
g
is
tic
r
e
g
r
ess
io
n
(
L
R
)
,
AN
N
,
an
d
lo
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
(
L
STM
)
[
1
3
]
,
[
1
6
]
–
[
1
8
]
.
T
h
e
in
d
e
p
en
d
e
n
t
v
ar
iab
les
u
s
ed
r
ef
er
to
Altm
a
n
an
d
Sab
ato
[
8
]
,
an
d
Ar
o
r
a
an
d
Kau
r
[
2
0
]
,
co
n
s
is
tin
g
o
f
f
in
an
cial
r
atio
s
is
p
r
esen
ted
in
T
a
b
le
1
.
T
h
e
v
ar
i
ab
les an
d
m
etr
ics u
s
ed
as a
n
al
y
s
is
to
o
ls
ca
n
b
e
s
ee
n
in
T
ab
le
1
.
T
ab
le
1
.
I
n
d
ep
e
n
d
en
t
v
ar
iab
le
u
s
ed
in
m
o
d
el
esti
m
atio
n
M
e
a
su
r
e
M
e
t
r
i
c
P
r
o
f
i
t
a
b
i
l
i
t
y
N
e
t
p
r
o
f
i
t
m
a
r
g
i
n
,
g
r
o
ss
p
r
o
f
i
t
mar
g
i
n
Le
v
e
r
a
g
e
D
e
b
t
-
to
-
e
q
u
i
t
y
-
r
a
t
i
o
A
c
t
i
v
i
t
y
R
e
c
e
i
v
a
b
l
e
t
u
r
n
o
v
e
r
r
a
t
i
o
Li
q
u
i
d
i
t
y
C
u
r
r
e
n
t
r
a
t
i
o
,
c
a
s
h
r
a
t
i
o
,
a
n
d
q
u
i
c
k
r
a
t
i
o
C
o
v
e
r
a
g
e
A
sset
c
o
v
e
r
a
g
e
r
a
t
i
o
,
d
e
b
t
-
serv
i
c
e
-
c
o
v
e
r
a
g
e
-
r
a
t
i
o
A
d
d
i
t
i
o
n
a
l
va
r
i
a
b
l
e
C
o
m
p
a
n
y
a
g
e
,
h
i
s
t
o
r
i
c
al
o
v
e
r
d
u
e
,
c
h
a
n
g
e
i
n
sh
o
r
t
-
t
e
r
m
a
sse
t
s,
a
n
d
c
h
a
n
g
e
i
n
sa
l
e
s
Data
m
o
d
elin
g
u
s
in
g
th
e
A
NN
alg
o
r
ith
m
.
ANN
is
a
cl
ass
if
icatio
n
m
o
d
el
u
s
in
g
h
u
m
an
b
r
ain
r
ep
r
esen
tatio
n
.
ANN
co
n
s
is
ts
o
f
in
p
u
t,
o
u
tp
u
t,
an
d
in
te
r
m
ed
iar
y
lay
er
s
.
T
h
e
Y
v
alu
e
(
d
e
p
en
d
en
t
v
ar
iab
le)
is
ca
lcu
lated
b
y
m
u
ltip
ly
in
g
t
h
e
weig
h
t b
y
th
e
in
p
u
t a
n
d
is
u
s
e
d
in
(
1
)
.
=
0
+
∑
=
1
(
1
)
is
th
e
in
p
u
t
weig
h
ted
s
ig
n
al
f
r
o
m
n
o
d
e
,
0
is
th
e
b
ias
v
alu
e;
t
h
e
co
n
n
ec
tio
n
weig
h
t
b
etwe
en
n
o
d
e
an
d
in
p
u
t
is
d
en
o
ted
b
y
;
is
th
e
v
alu
e
o
f
in
p
u
t
,
an
d
th
e
n
u
m
b
er
o
f
n
o
d
es
is
d
en
o
ted
b
y
.
T
h
e
ac
tiv
atio
n
f
u
n
ctio
n
is
u
s
ed
to
p
r
esen
t
th
e
weig
h
ted
s
u
m
o
u
t
p
u
t.
T
h
e
o
u
t
p
u
t
v
alu
e
f
r
o
m
n
o
d
e
k
is
th
e
r
esu
lt
o
f
th
e
ac
tiv
atio
n
f
u
n
ctio
n
as in
p
u
t to
t
h
e
n
ex
t la
y
er
.
T
h
e
ac
tiv
atio
n
f
u
n
ctio
n
is
ca
lcu
lated
b
y
(
2
)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
1
5
,
No
.
1
,
Ma
r
c
h
2
0
2
6
:
244
-
2
5
2
246
(
)
=
1
1
+
−
(
2
)
Stra
tifie
d
s
am
p
lin
g
an
d
c
r
o
s
s
-
v
alid
atio
n
m
eth
o
d
s
,
as
o
u
tl
in
ed
b
y
J
ap
k
o
wicz
an
d
Sh
ah
[
2
1
]
a
n
d
C
h
an
g
et
al
.
[
2
2
]
wer
e
u
s
ed
f
o
r
m
o
d
ellin
g
.
B
u
tar
u
et
a
l
.
[
2
]
p
r
o
v
id
e
d
th
e
b
asis
f
o
r
th
e
c
lass
if
icatio
n
r
esu
lt
th
r
esh
o
ld
s
an
d
th
e
ch
o
ice
o
f
c
u
to
f
f
v
alu
es
f
o
r
v
ar
io
u
s
class
if
ier
s
.
Usi
n
g
th
e
J
ap
k
o
wicz
an
d
S
h
ah
[
2
1
]
tech
n
iq
u
e,
th
e
class
if
ier
p
er
f
o
r
m
a
n
ce
wa
s
ev
alu
ated
with
o
u
t
a
s
tatis
tical
s
ig
n
if
ican
ce
test
,
as
s
tated
b
y
Hu
a
n
g
et
a
l
.
[
1
7
]
an
d
Mo
s
ca
telli
et
a
l
.
[
1
8
]
.
Qu
et
a
l
.
[
2
3
]
d
e
f
in
ed
th
e
c
o
n
f
u
s
io
n
m
atr
ix
tech
n
iq
u
e,
wh
ich
was
u
s
ed
to
s
u
m
m
ar
is
e
th
e
class
if
icatio
n
f
in
d
in
g
s
.
T
h
e
v
is
u
alis
atio
n
s
o
f
th
e
d
etec
tio
n
er
r
o
r
tr
ad
e
o
f
f
(
DE
T
)
an
d
r
ec
eiv
er
o
p
er
atin
g
ch
ar
ac
ter
is
tic
(
R
OC
)
wer
e
b
ased
o
n
r
esear
c
h
co
n
d
u
cted
b
y
Ma
ld
o
n
ad
o
et
a
l
.
[
2
4
]
a
n
d
S
u
n
et
a
l
.
[
2
5
]
.
Ar
ea
u
n
d
er
th
e
c
u
r
v
e
(
AUC),
ac
cu
r
ac
y
m
ea
s
u
r
es
f
o
r
co
n
f
u
s
io
n
m
atr
ices,
an
d
e
q
u
al
e
r
r
o
r
r
ate
(
E
E
R
)
f
o
r
R
OC
an
d
DE
T
g
r
ap
h
s
wer
e
u
s
ed
to
ass
ess
th
e
m
o
d
el'
s
p
er
f
o
r
m
an
ce
[
2
5
]
.
Utilizin
g
a
co
n
f
u
s
io
n
m
atr
i
x
,
th
e
class
if
icatio
n
m
o
d
el'
s
p
er
f
o
r
m
an
ce
was
ass
ess
ed
b
y
co
m
p
u
tin
g
th
e
A
UC
an
d
E
E
R
f
o
r
R
OC
an
d
DE
T
g
r
ap
h
s
[
2
5
]
.
T
h
e
f
in
an
cial
r
atio
s
f
o
r
ass
ess
in
g
SME
s
'
b
u
s
in
es
s
p
o
r
tf
o
lio
s
ar
e
in
f
lu
en
ce
d
b
y
s
ev
er
al
f
ac
to
r
s
s
u
ch
as
m
ar
k
et
s
en
tim
en
t,
ec
o
n
o
m
ic
cy
cles
,
an
d
in
d
u
s
tr
y
d
o
m
in
an
ce
.
T
h
e
d
if
f
er
en
ce
s
in
th
ese
s
tr
u
ctu
r
es
m
ak
e
it
in
ter
esti
n
g
f
o
r
m
ac
h
in
e
lear
n
in
g
to
r
ec
o
g
n
ize
th
e
r
elatio
n
s
h
ip
o
f
ea
ch
ca
s
e
to
a
p
ar
ticu
lar
cl
u
s
ter
s
o
as
to
p
r
o
d
u
c
e
th
e
r
ig
h
t c
lass
if
icatio
n
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
p
o
r
tf
o
lio
o
f
b
at
ik
SME
s
ass
es
s
m
en
ts
th
at
h
av
e
s
ig
n
if
i
ca
n
t
d
if
f
e
r
en
ce
s
f
r
o
m
ea
c
h
S
ME
ca
n
b
e
id
en
tifie
d
.
Su
ch
as
d
if
f
e
r
en
ce
s
in
liq
u
id
ity
r
ati
o
s
,
p
r
o
f
itab
ilit
y
r
atio
s
,
an
d
co
v
e
r
ag
e
o
f
ea
ch
b
atik
SME
a
r
e
r
elativ
ely
th
e
s
am
e
b
ased
o
n
t
h
e
co
n
d
itio
n
s
o
f
th
e
b
ati
k
SM
E
s
.
T
h
e
d
ec
lin
e
in
f
in
an
cial
r
a
tio
s
in
b
at
ik
SME
s
will b
e
s
ee
n
b
y
co
m
p
ar
in
g
th
e
cu
r
r
en
t y
ea
r
with
th
e
p
r
ev
io
u
s
y
ea
r
.
Ov
er
th
e
co
u
r
s
e
o
f
a
y
ea
r
,
T
ab
le
2
d
is
p
lay
s
a
d
r
o
p
in
ev
er
y
liq
u
id
ity
an
d
p
r
o
f
itab
ilit
y
r
atio
.
Ho
wev
er
,
ac
c
o
u
n
ts
r
ec
eiv
ab
le
tu
r
n
o
v
er
r
ates
an
d
o
th
er
b
u
s
in
ess
ac
tiv
ity
in
d
icato
r
s
d
em
o
n
s
tr
ate
th
at
ba
tik
SME
s
ar
e
c
o
llectin
g
ac
co
u
n
ts
r
ec
eiv
a
b
le
f
aster
an
d
h
av
e
a
l
o
wer
d
eb
t
-
to
-
e
q
u
ity
r
atio
.
T
ab
le
2
.
Var
iab
le
a
v
er
ag
es b
a
s
ed
o
n
f
in
a
n
cial
y
ea
r
F
i
n
a
n
c
i
a
l
r
a
t
i
o
c
a
t
e
g
o
r
y
S
p
e
c
i
f
i
c
v
a
r
i
a
b
l
e
F
i
n
a
n
c
i
a
l
y
e
a
r
P
r
o
f
i
t
a
b
i
l
i
t
y
N
e
t
p
r
o
f
i
t
m
a
r
g
i
n
G
r
o
ss p
r
o
f
i
t
m
a
r
g
i
n
0
.
5
0
0
.
0
6
Le
v
e
r
a
g
e
D
e
b
t
-
to
-
e
q
u
i
t
y
-
r
a
t
i
o
1
.
2
7
A
c
t
i
v
i
t
y
R
e
c
e
i
v
a
b
l
e
t
u
r
n
o
v
e
r
r
a
t
i
o
1
7
8
.
1
5
Li
q
u
i
d
i
t
y
C
u
r
r
e
n
t
r
a
t
i
o
C
a
s
h
r
a
t
i
o
Q
u
i
c
k
r
a
t
i
o
2
.
5
5
6
.
3
8
3
.
5
8
C
o
v
e
r
a
g
e
A
sset
c
o
v
e
r
a
g
e
r
a
t
i
o
D
e
b
t
-
s
e
r
v
i
c
e
-
c
o
v
e
r
a
g
e
-
r
a
t
i
o
4
.
5
1
2
.
9
8
A
d
d
i
t
i
o
n
a
l
v
a
r
i
a
b
l
e
C
h
a
n
g
e
i
n
S
a
l
e
s
C
o
m
p
a
n
y
a
g
e
C
h
a
n
g
e
i
n
s
h
o
r
t
-
t
e
r
m
a
ss
e
t
s
0
.
7
3
%
1
0
.
8
0
.
3
9
%
3
.
1
.
Cla
s
s
if
ica
t
io
n
re
s
ults us
ing
cla
s
s
ic
v
a
ria
bles
T
h
e
d
eb
t
s
er
v
ice
co
v
er
a
g
e
r
atio
,
ass
et
co
v
er
ag
e
r
atio
,
ca
s
h
r
atio
,
cu
r
r
en
t
r
atio
,
q
u
ick
r
atio
,
d
eb
t
-
to
-
e
q
u
ity
r
atio
,
g
r
o
s
s
m
ar
g
in
r
atio
,
p
r
o
f
it
m
a
r
g
in
r
ati
o
,
an
d
r
ec
eiv
ab
les
tu
r
n
o
v
er
r
atio
ar
e
am
o
n
g
th
e
co
n
v
en
tio
n
al
p
a
r
am
eter
s
th
at
a
r
e
u
s
ed
in
t
h
e
class
if
icatio
n
p
r
o
ce
s
s
[
8
]
.
T
h
e
lim
it
v
alu
es f
o
r
th
e
L
R
,
ANN,
an
d
L
STM
class
if
icatio
n
m
eth
o
d
s
ar
e
d
eter
m
in
ed
b
y
c
o
n
tr
asti
n
g
ea
ch
m
o
d
el'
s
m
ed
ian
v
al
u
e
with
th
e
g
iv
e
n
p
r
ed
ictio
n
s
,
as
p
r
o
p
o
s
ed
b
y
A
d
d
o
et
a
l
.
[
1
6
]
.
T
h
e
p
r
o
p
e
r
b
in
o
m
ial
v
alu
e
is
ass
ig
n
ed
to
th
e
m
o
d
elin
g
f
in
d
in
g
s
.
T
h
er
e
is
a
n
o
v
er
lap
in
th
e
m
o
d
el
,
wh
ich
in
d
icate
s
th
at
th
er
e
is
a
class
if
icatio
n
d
i
f
f
icu
lty
in
d
is
tin
g
u
is
h
in
g
th
e
two
class
es,
wh
ich
r
esu
lts
in
a
n
eg
ativ
e
im
p
ac
t
o
n
class
if
icatio
n
ac
cu
r
ac
y
.
T
h
is
o
f
ten
h
ap
p
e
n
s
wh
en
th
e
lear
n
i
n
g
ca
s
e
is
u
n
b
alan
ce
d
[
1
7
]
.
T
h
e
li
m
it v
alu
e
is
s
et
at
0
.
0
8
9
f
o
r
LR
an
d
-
0
.
8
0
f
o
r
ANN
an
d
L
STM
class
if
icatio
n
.
B
ased
o
n
th
e
h
ar
m
o
n
ic
m
ea
n
an
d
th
e
th
r
esh
o
ld
v
alu
e
s
et,
th
e
ANN
cla
s
s
if
icatio
n
m
o
d
el
p
r
o
d
u
ce
s
th
e
h
ig
h
est
p
r
ed
ictio
n
ac
c
u
r
ac
y
o
f
5
8
.
7
2
%.
W
h
ile
th
e
p
er
f
o
r
m
an
ce
o
f
LR
an
d
L
STM
is
lo
wer
at
2
.
2
4
an
d
1
.
6
6
(
T
ab
le
s
3
a
n
d
4
)
.
W
h
en
s
p
ec
i
f
ically
o
n
s
en
s
itiv
ity
,
th
e
p
o
s
i
tiv
e
p
r
o
p
o
r
tio
n
id
e
n
tific
atio
n
r
atio
is
a
k
ey
f
ac
to
r
f
o
r
ev
alu
atin
g
class
if
icatio
n
p
er
f
o
r
m
a
n
ce
o
n
an
u
n
b
alan
ce
d
d
ata
s
et,
an
d
ANN
g
ets
th
e
h
ig
h
est
s
co
r
e.
C
la
s
s
ica
l
p
r
ed
icto
r
s
ar
e
d
escr
ib
ed
u
s
in
g
R
OC
an
d
DE
T
,
p
r
e
s
en
ted
in
Fig
u
r
e
1
.
T
h
e
R
OC
g
r
ap
h
(
Fig
u
r
e
1
(
a
)
)
an
d
DE
T
g
r
ap
h
s
in
Fig
u
r
e
1
(
b
)
ex
h
ib
it
th
e
o
u
tco
m
es
o
f
th
e
p
r
ed
icto
r
p
e
r
f
o
r
m
an
ce
ev
alu
a
tio
n
b
ased
o
n
th
e
d
esig
n
ated
th
r
esh
o
l
d
v
alu
e.
All
class
if
icatio
n
m
o
d
els
h
a
v
e
o
v
er
all
p
er
f
o
r
m
an
ce
at
all
lim
its
co
n
s
is
ten
t
with
th
e
r
esu
lts
o
f
th
e
s
in
g
le
v
alu
e
lim
it.
T
h
e
b
est AUC
an
d
EER
v
alu
es a
r
e
g
en
er
ally
s
h
o
wn
b
y
th
e
ANN
m
o
d
el,
wh
ich
ar
e
0
.
6
2
an
d
4
1
%.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
F
in
a
n
cia
l d
is
tr
ess
p
r
ed
ictio
n
fo
r
b
a
tik
s
ma
ll a
n
d
med
i
u
m
en
t
erp
r
is
e
s
cred
it fin
a
n
cin
g
b
a
s
e
d
…
(
Ta
r
ya
d
i
)
247
W
h
ile
at
th
e
ex
tr
em
e
lim
it
,
t
h
e
L
STM
class
if
icatio
n
m
o
d
el
o
u
tp
er
f
o
r
m
s
ANN,
b
u
t
th
e
o
v
er
al
l
ac
cu
r
ac
y
is
lo
wer
,
with
AUC
a
nd
EE
R
v
alu
es
o
f
0
.
6
1
an
d
4
3
%.
T
h
e
lo
west
ac
c
u
r
ac
y
v
alu
e
is
o
b
tain
ed
b
y
th
e
LR
m
o
d
el,
wh
ic
h
is
AUC (
0
.
5
7
)
an
d
E
E
R
=4
5
%.
T
ab
le
3
.
Per
f
o
r
m
an
ce
co
m
p
a
r
is
o
n
o
f
class
ic
p
r
ed
icto
r
s
M
o
d
e
l
A
c
c
u
r
a
c
y
(
%)
H
a
r
mo
n
i
c
me
a
n
(
%)
A
v
e
r
a
g
e
c
l
a
ss
(
%)
LSTM
5
2
.
2
5
5
6
.
1
0
5
6
.
5
9
LR
5
2
.
0
1
5
5
.
5
0
5
5
.
9
1
ANN
5
2
.
8
9
5
7
.
8
2
5
8
.
6
9
T
ab
le
4
.
Deta
iled
c
o
n
f
u
s
io
n
m
atr
ices f
o
r
class
ic
p
r
ed
icto
r
s
M
o
d
e
l
P
r
e
d
i
c
t
e
d
A
c
t
u
a
l
n
e
g
a
t
i
v
e
A
c
t
u
a
l
p
o
si
t
i
v
e
LSTM
N
e
g
a
t
i
v
e
5
6
3
0
5
3
1
3
P
o
si
t
i
v
e
3
0
9
6
5
2
LR
N
e
g
a
t
i
v
e
5
5
9
3
5
3
1
4
P
o
si
t
i
v
e
3
1
7
6
4
1
ANN
N
e
g
a
t
i
v
e
5
6
3
7
5
3
1
7
P
o
si
t
i
v
e
3
1
8
6
8
9
(
a
)
(
b
)
Fig
u
r
e
1
.
C
lass
ic
p
r
ed
icto
r
of
(
a)
R
OC
an
d
(
b
)
DE
T
gr
ap
h
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
1
5
,
No
.
1
,
Ma
r
c
h
2
0
2
6
:
244
-
2
5
2
248
3
.
2
.
Cla
s
s
if
ica
t
io
n
o
utc
o
m
es
inclu
d
ing
t
im
e
f
a
ct
o
r
Nex
t,
th
e
m
o
d
el
is
r
ef
in
ed
b
y
p
r
o
v
id
in
g
ad
d
itio
n
al
i
n
d
ica
to
r
s
o
f
f
in
a
n
cial
d
is
tr
ess
an
d
tim
e.
T
h
is
ad
d
itio
n
m
ak
es
th
e
p
r
ed
icto
r
h
av
e
a
b
r
o
a
d
er
p
er
s
p
ec
tiv
e,
la
g
g
in
g
class
ical
v
ar
iab
les,
h
is
to
r
ical
lag
s
,
co
m
p
an
y
ag
e,
s
ales
ch
an
g
es
,
an
d
s
h
o
r
t
-
ter
m
ass
et
ch
an
g
es.
Fig
u
r
e
2
s
h
o
ws
th
at
th
er
e
i
s
a
lo
wer
o
v
er
lap
o
f
tr
u
e
an
d
p
r
ed
icted
clas
s
es
co
m
p
ar
ed
to
th
e
class
ical
cla
s
s
if
icat
io
n
m
o
d
el,
an
d
th
e
c
h
allen
g
e
with
im
b
alan
ce
d
ca
s
e
p
r
ed
ictio
n
r
em
ain
s
.
T
h
e
k
e
r
n
e
l
d
en
s
ity
f
u
n
ctio
n
g
r
ap
h
s
f
o
r
ea
ch
m
eth
o
d
u
s
ed
,
in
clu
d
i
n
g
lo
g
it,
ar
e
s
h
o
wn
in
Fig
u
r
e
2
(
a)
,
L
STM
in
Fig
u
r
e
2
(
b
)
,
an
d
ANN
in
Fig
u
r
e
2
(
c)
.
T
h
e
th
r
esh
o
ld
v
alu
es
s
et
co
m
p
ar
ed
to
th
e
class
ical
p
r
ed
icto
r
a
r
e
r
elativ
ely
s
im
ilar
,
with
ea
ch
m
o
d
el'
s
v
alu
e
o
f
0
.
0
8
LR
,
-
0
.
8
1
ANN
,
an
d
-
0
.
8
3
f
o
r
L
STM
.
Sh
u
m
way
s
tated
th
at
p
er
io
d
a
d
ju
s
tm
en
t h
as a
p
o
s
itiv
e
r
is
k
o
n
th
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
class
if
icatio
n
alg
o
r
ith
m
.
T
h
e
th
r
esh
o
ld
v
alu
e
a
n
d
th
e
a
d
d
itio
n
o
f
n
ew
in
d
e
p
en
d
e
n
t v
a
r
i
ab
les en
ab
led
th
e
L
STM
m
o
d
e
l to
y
ield
th
e
h
ig
h
est
class
if
icatio
n
ac
cu
r
ac
y
.
T
h
e
h
ar
m
o
n
ic
m
ea
n
v
alu
e
r
o
s
e
t
o
6
0
.
6
1
%,
a
2
.
7
0
r
is
e.
Ad
d
itio
n
ally
,
th
e
s
en
s
itiv
ity
r
atio
wen
t
u
p
b
y
1
0
.
1
6
to
7
2
.
4
%
.
T
h
e
h
ar
m
o
n
ic
av
er
ag
e
o
f
4
.
3
9
f
o
r
th
e
LR
m
o
d
el
in
cr
ea
s
ed
to
6
0
.
8
9
%.
I
n
co
n
tr
ast,
th
e
ANN
m
o
d
el'
s
s
en
s
i
tiv
ity
r
atio
d
r
o
p
p
e
d
b
y
6
.
2
2
to
6
0
.
0
1
%
an
d
its
h
ar
m
o
n
ic
m
ea
n
d
ec
lin
ed
b
y
2
.
9
to
5
5
.
2
4
%.
F
ig
u
r
e
3
s
h
o
ws
th
e
class
if
icati
o
n
with
a
d
d
itio
n
al
f
ac
to
r
s
u
s
in
g
th
e
R
OC
g
r
ap
h
(
F
ig
u
r
e
3
(
a
)
)
a
n
d
DE
T
g
r
a
p
h
(
F
ig
u
r
e
3
(
b
)
).
Similar
to
d
ete
r
m
in
in
g
th
e
th
r
esh
o
ld
v
alu
e,
th
e
L
STM
m
o
d
el,
wh
ich
h
as
an
AUC
v
alu
e
o
f
0
.
5
7
an
d
an
E
E
R
v
alu
e
o
f
4
2
.
8
7
%,
is
th
e
m
o
s
t
ac
cu
r
ate
m
o
d
el
f
o
r
p
r
ed
ictin
g
f
in
an
cial
d
is
tr
ess
.
W
i
th
AUC
an
d
EER
v
alu
es
o
f
0
.
1
9
a
n
d
4
1
.
2
0
%,
r
esp
ec
tiv
ely
,
th
e
LR
m
o
d
el
ac
h
iev
es
th
e
n
e
x
t
p
er
f
o
r
m
an
ce
ac
c
u
r
ac
y
.
T
h
e
n
eg
ativ
e
im
p
ac
t
is
ex
p
e
r
ien
ce
d
b
y
t
h
e
ANN
m
o
d
el
with
t
h
e
ad
d
itio
n
o
f
n
ew
v
ar
iab
les.
T
h
e
AUC
an
d
E
E
R
v
alu
es
ar
e
lo
wer
b
y
-
0
.
0
3
a
n
d
+4
.
T
h
e
r
esu
lts
o
f
th
e
ac
cu
r
ac
y
ass
ess
m
en
t
wi
th
th
e
ad
d
itio
n
o
f
v
ar
ia
b
les
ar
e
p
r
esen
ted
in
T
ab
le
5
.
T
h
e
LR
an
d
L
STM
class
if
icatio
n
m
o
d
els
in
cr
ea
s
ed
th
eir
ac
cu
r
ac
y
with
th
e
a
d
d
itio
n
o
f
n
ew
v
ar
iab
les.
T
h
e
f
i
n
an
cial
d
is
tr
ess
p
r
ed
ictio
n
m
o
d
el
th
at
p
er
f
o
r
m
e
d
b
est
an
d
h
ad
th
e
h
ig
h
est
AUC
an
d
lo
we
s
t
E
E
R
v
alu
es
was
L
STM
.
T
h
e
L
STM
m
eth
o
d
was
also
ab
le
t
o
id
en
tif
y
r
elatio
n
al
v
ar
iab
les b
ased
o
n
r
e
g
u
lar
r
e
g
r
ess
io
n
b
eta
v
alu
es a
n
d
s
h
o
we
d
th
e
n
u
m
b
er
o
f
in
co
r
r
ec
t c
las
s
if
icatio
n
s
b
ased
o
n
v
ar
iab
les
th
at
wer
e
o
m
itted
in
t
h
e
class
if
icatio
n
p
r
o
ce
s
s
.
T
h
e
m
o
s
t
im
p
o
r
ta
n
t
v
a
r
iab
le
th
at
is
co
n
s
id
er
e
d
to
h
a
v
e
a
d
ir
ec
t
im
p
ac
t
o
n
th
e
c
o
r
r
ec
t
ca
s
e
class
if
icat
io
n
is
th
e
ag
e
o
f
th
e
SME
'
s
b
u
s
in
ess
.
Su
n
et.
a
l.
[
2
5
]
ar
g
u
e
th
at
th
e
ag
e
o
f
th
e
b
u
s
in
ess
is
an
im
p
o
r
tan
t v
ar
iab
le
th
at
will a
f
f
ec
t
f
i
n
an
cial
d
if
f
icu
lties
.
(
a)
(
b
)
(
c)
Fig
u
r
e
2
.
Ker
n
el
d
en
s
ity
f
u
n
ct
io
n
g
r
a
p
h
s
s
h
o
win
g
p
r
ed
icted
an
d
ac
tu
al
v
al
u
es
o
f
(
a
)
lo
g
it
,
(
b
)
L
STM
,
an
d
(
c)
ANN
class
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
F
in
a
n
cia
l d
is
tr
ess
p
r
ed
ictio
n
fo
r
b
a
tik
s
ma
ll a
n
d
med
i
u
m
en
t
erp
r
is
e
s
cred
it fin
a
n
cin
g
b
a
s
e
d
…
(
Ta
r
ya
d
i
)
249
(
a
)
(
b
)
Fig
u
r
e
3
.
C
lass
if
ier
s
with
ad
d
itio
n
al
f
ac
to
r
s
of
(
a)
R
OC
an
d
(
b
)
DE
T
gr
a
p
h
s
T
ab
le
5
.
C
lass
if
icatio
n
r
esu
lts
f
o
r
f
in
a
n
cial
d
is
tr
ess
p
r
ed
icto
r
s
M
o
d
e
l
C
l
a
s
si
c
r
a
t
i
o
W
i
t
h
a
d
d
i
t
i
o
n
a
l
f
a
c
t
o
r
AUC
EER
(
%)
AUC
EER
(
%)
LSTM
0
.
6
5
43
0
.
6
8
38
LR
0
.
5
8
44
0
.
6
6
38
ANN
0
.
6
2
41
0
.
5
9
45
3
.
3
.
Dis
cus
s
io
n
Un
d
er
s
tan
d
in
g
cr
e
d
it
r
is
k
m
o
d
ellin
g
is
cr
u
cial
f
o
r
ev
er
y
l
en
d
er
,
wh
eth
er
d
eter
m
in
in
g
th
e
ca
p
ital
r
eq
u
ir
em
e
n
ts
s
et
b
y
r
eg
u
lato
r
y
b
o
d
ies
o
r
ev
alu
atin
g
a
b
o
r
r
o
w
er
'
s
ab
ilit
y
to
r
ep
ay
a
l
o
an
.
T
h
e
p
r
o
ce
s
s
g
ets
m
o
r
e
d
if
f
icu
lt
wh
en
SME
-
s
p
ec
if
ic
i
s
s
u
es
lik
e
lim
ited
b
u
d
g
etar
y
f
l
ex
ib
ilit
y
an
d
r
estricte
d
d
ata
av
ailab
ilit
y
ar
e
tak
en
in
to
ac
co
u
n
t.
So
an
ef
f
o
r
t
is
n
ee
d
ed
to
h
el
p
th
e
p
r
o
ce
s
s
o
f
e
v
alu
atin
g
len
d
i
n
g
f
o
r
SME
s
.
On
e
th
in
g
th
at
n
ee
d
s
to
b
e
co
n
s
id
er
ed
is
th
e
f
in
a
n
ci
al
d
is
tr
ess
th
at
SME
s
ca
n
ex
p
er
ien
ce
.
As
o
p
p
o
s
ed
to
th
e
ty
p
ical
d
e
f
au
lt
p
r
o
b
ab
ilit
y
p
r
ed
icto
r
s
,
t
h
e
d
ep
e
n
d
en
t
v
ar
iab
le
is
d
ete
r
m
in
ed
b
y
class
if
y
in
g
f
in
an
cial
d
is
tr
ess
wh
en
SME
s
ar
e
ex
p
er
ien
cin
g
f
in
an
cial
d
is
tr
ess
an
d
n
o
t
n
ec
ess
ar
ily
r
ea
ch
in
g
th
e
f
in
al
s
tag
e
o
f
b
an
k
r
u
p
tcy
,
r
ef
l
ec
tin
g
th
e
ac
tu
al
len
d
er
s
’
c
r
ed
it
d
ec
is
io
n
-
m
ak
in
g
f
r
am
ewo
r
k
.
T
h
e
in
d
ep
en
d
e
n
t
v
ar
iab
les
ar
e
f
in
an
cial
f
ac
to
r
s
f
r
o
m
th
e
f
in
a
n
cial
s
tr
en
g
th
ev
a
lu
atio
n
ca
teg
o
r
ies,
in
clu
d
in
g
n
atio
n
id
en
titi
es
an
d
liq
u
id
ity
,
lev
er
ag
e
,
p
r
o
f
itab
ilit
y
,
co
v
er
a
g
e,
an
d
ac
tiv
ity
.
T
h
e
s
e
co
n
v
en
tio
n
al
f
in
a
n
cial
r
at
io
s
wer
e
wr
itten
b
y
Oliv
er
et
a
l
.
[
4
]
,
Altm
an
an
d
Sab
ato
[
8
]
,
an
d
E
lh
o
s
en
y
et
a
l
.
[
1
1
]
.
W
ith
th
e
lo
west
E
E
R
o
f
4
1
%
an
d
th
e
h
ig
h
est
AUC
v
alu
e
o
f
0
.
6
2
,
th
e
ANN
is
th
e
b
est
p
r
ed
icto
r
o
f
f
in
a
n
cial
d
is
tr
ess
wh
en
s
in
g
le
-
p
er
io
d
c
lass
ical
r
atio
in
p
u
ts
ar
e
u
s
ed
.
T
h
e
m
o
d
el
c
o
r
r
ec
tly
ca
teg
o
r
izes th
e
f
in
an
cial
is
s
u
es in
6
6
% o
f
s
itu
atio
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
1
5
,
No
.
1
,
Ma
r
c
h
2
0
2
6
:
244
-
2
5
2
250
T
h
e
ac
cu
r
ac
y
o
f
th
e
ca
teg
o
r
i
za
tio
n
was
m
u
c
h
im
p
r
o
v
ed
b
y
th
e
ad
d
itio
n
o
f
a
d
d
itio
n
al
i
n
d
ep
en
d
en
t
v
ar
iab
les.
Ay
u
n
i
et
a
l
.
[
2
6
]
s
tate
th
at
f
ac
to
r
s
th
at
p
r
o
v
i
d
e
a
o
n
e
-
y
ea
r
s
n
a
p
s
h
o
t o
f
f
in
a
n
cial
r
atio
s
wer
e
r
ep
lace
d
with
ad
d
itio
n
al
y
ea
r
-
tim
e
c
o
m
p
o
n
e
n
ts
,
lag
g
ed
h
is
to
r
y
,
ass
et
ch
an
g
es,
a
n
d
s
ales
ch
ar
ac
te
r
is
tics
.
B
y
in
clu
d
in
g
th
e
b
est
class
if
ier
,
L
STM
,
wh
ich
h
ad
th
e
lo
west
E
E
R
o
f
3
8
%
an
d
th
e
h
ig
h
est
AUC
o
f
0
.
6
8
,
th
e
p
r
ed
ictio
n
s
en
s
itiv
ity
in
cr
ea
s
ed
b
y
6
p
er
c
en
tag
e
p
o
in
ts
to
7
2
%.
W
h
en
c
o
m
p
ar
ed
to
L
R
,
ANN,
th
e
m
o
s
t
ef
f
ec
tiv
e
m
eth
o
d
f
o
r
ca
teg
o
r
izin
g
s
tatic
p
er
io
d
s
,
s
aw
a
6
%
-
p
o
in
t
d
ec
r
ea
s
e
in
s
en
s
itiv
ity
p
r
ed
ictio
n
.
T
im
e
co
n
s
id
er
atio
n
s
m
ay
b
e
ac
co
u
n
ted
f
o
r
b
y
th
e
m
ix
e
d
class
if
ier
s
'
r
e
s
p
o
n
s
e
to
th
e
em
p
ir
ical
p
ar
t
o
f
m
o
d
el
co
n
s
tr
u
ctio
n
,
wh
ich
co
u
l
d
in
v
o
lv
e
an
y
th
in
g
f
r
o
m
alter
in
g
tr
ain
in
g
tech
n
i
q
u
es
to
ch
an
g
in
g
v
ar
iab
les
[
1
6
]
,
[
2
0
]
.
B
y
ac
c
o
u
n
tin
g
f
o
r
th
e
r
is
k
y
p
er
io
d
,
th
e
tim
e
co
m
p
o
n
e
n
t
d
o
es,
in
f
ac
t,
lo
wer
t
h
e
u
n
ce
r
tain
ty
f
ac
to
r
,
as
e
v
id
en
ce
d
b
y
th
e
m
u
lti
-
p
e
r
io
d
ca
teg
o
r
izatio
n
'
s
o
v
er
all
s
u
p
er
i
o
r
p
er
f
o
r
m
a
n
ce
o
v
er
th
e
s
tatic
p
er
io
d
p
r
ed
icto
r
.
I
n
th
e
b
est
-
p
e
r
f
o
r
m
in
g
ANN
class
if
ier
with
ad
d
itio
n
al
f
ac
to
r
s
,
th
e
r
elev
an
ce
o
f
ea
ch
in
d
iv
id
u
al
v
ar
iab
le
is
eq
u
iv
alen
t
f
o
r
m
o
s
t
v
ar
iab
les.
T
h
e
co
m
p
an
y
'
s
a
g
e
h
as
th
e
h
ig
h
est
s
ig
n
if
ican
ce
,
wh
ile
th
e
n
atio
n
in
d
icato
r
h
as
th
e
lo
west.
T
h
e
co
m
p
ar
ativ
ely
lo
w
s
ig
n
if
ican
ce
v
alu
es
f
o
r
in
d
iv
id
u
al
v
ar
ia
b
les
im
p
ly
th
at
th
e
in
ter
d
ep
en
d
en
ce
o
f
all
v
ar
iab
l
es,
r
ath
er
th
an
th
e
s
tan
d
-
alo
n
e
co
m
p
o
n
e
n
ts
,
d
eter
m
in
es
th
e
p
r
im
ar
y
class
if
ier
'
s
p
o
wer
.
C
o
m
p
a
r
ed
to
th
e
tr
ad
it
io
n
al
d
ef
a
u
lt
p
r
o
b
ab
ilit
y
class
if
ier
,
th
e
esti
m
ated
f
in
a
n
cial
d
i
s
tr
ess
p
r
ed
icto
r
h
as
a
s
o
m
ewh
at
lo
wer
p
r
e
d
ictiv
e
p
o
wer
o
f
7
2
%.
Oth
er
r
esear
c
h
u
s
in
g
d
e
f
au
lt
p
r
o
b
ab
ilit
y
m
o
d
ellin
g
,
h
o
wev
er
,
s
h
o
ws
ac
cu
r
ac
y
lev
els as h
ig
h
as 8
5
% (
ev
en
af
te
r
ad
ju
s
tin
g
f
o
r
b
ias).
T
h
e
d
if
f
e
r
en
t
way
th
e
d
ep
e
n
d
en
t
v
ar
iab
le
was
f
o
r
m
u
lated
c
o
u
ld
b
e
o
n
e
o
f
th
e
p
o
s
s
ib
le
ca
u
s
es
o
f
th
e
r
ed
u
ce
d
esti
m
ate
ac
cu
r
ac
y
.
W
h
ile
th
e
f
o
cu
s
o
f
tr
ad
itio
n
al
c
r
ed
it
r
is
k
p
r
ed
ictio
n
m
o
d
els
i
s
o
n
b
a
n
k
r
u
p
tcy
o
r
d
ef
au
lt,
f
in
an
cial
d
is
tr
ess
in
th
is
s
tu
d
y
is
d
ef
in
e
d
as
a
SME
s
en
tity
'
s
b
eg
in
n
in
g
ec
o
n
o
m
ic
d
if
f
icu
lties
as
s
h
o
wn
b
y
c
h
an
g
es
in
cr
e
d
it
s
co
r
es.
As
th
e
latter
p
h
ase
o
f
a
co
m
p
an
y
's
life
,
b
an
k
r
u
p
tcy
h
ap
p
e
n
s
s
eld
o
m
an
d
is
tr
ig
g
er
ed
b
y
a
v
a
r
iety
o
f
f
ac
to
r
s
.
H
o
wev
er
,
a
b
u
s
in
ess
ca
n
g
o
t
h
r
o
u
g
h
m
u
ltip
le
in
s
tan
ce
s
o
f
f
in
an
ci
al
d
if
f
icu
lty
with
o
u
t
g
o
in
g
b
an
k
r
u
p
t.
E
v
e
n
ts
lik
e
p
er
s
o
n
n
el
c
h
an
g
es,
w
o
r
k
in
g
ca
p
ital
f
ac
ilit
y
clo
s
u
r
es,
an
d
co
u
r
t
co
n
f
licts
,
f
o
r
in
s
tan
ce
,
ca
n
ca
u
s
e
s
h
o
r
t
-
ter
m
f
in
an
cia
l
s
h
o
ck
s
,
e
v
en
f
o
r
b
u
s
in
ess
e
s
th
at
h
av
e
p
r
ev
i
o
u
s
ly
d
em
o
n
s
tr
ated
a
lo
w
ch
an
ce
o
f
d
ef
a
u
lt.
Fro
m
th
e
s
tan
d
p
o
i
n
t
o
f
a
len
d
er
,
b
o
th
wo
u
ld
b
e
u
n
d
esira
b
le
d
u
e
to
p
er
h
a
p
s
in
cr
ea
s
ed
ca
p
ital
r
eq
u
ir
em
e
n
ts
,
d
ep
en
d
in
g
o
n
th
eir
r
is
k
ap
p
etite.
4.
CO
NCLU
SI
O
N
Un
d
er
s
tan
d
in
g
h
o
w
to
m
o
d
el
c
r
ed
it
r
is
k
is
ess
en
tial
f
o
r
len
d
er
s
.
T
h
e
m
o
d
ellin
g
p
r
o
ce
s
s
b
ec
o
m
es
m
o
r
e
d
if
f
icu
lt
to
h
an
d
le
,
le
a
d
in
g
t
o
SME
s
d
u
e
to
b
u
d
g
et
c
o
n
s
tr
ain
ts
an
d
th
e
av
ailab
ilit
y
o
f
p
r
ed
i
ctab
le
ass
ets.
Un
lik
e
ty
p
ical
d
ef
au
lt
p
r
ed
ictio
n
,
th
e
d
ep
en
d
e
n
t
v
ar
ia
b
le
is
u
s
ed
to
class
if
y
f
in
an
cial
d
is
tr
ess
wh
en
SME
s
ex
p
er
ien
c
e
f
in
an
cial
d
is
tr
ess
an
d
d
o
n
o
t n
ec
ess
ar
ily
en
d
u
p
in
b
an
k
r
u
p
tc
y
.
T
h
e
in
d
ep
e
n
d
en
t v
a
r
iab
les ar
e
f
in
an
cial
f
ac
to
r
s
f
r
o
m
th
e
f
in
an
cial
s
tr
en
g
th
ev
a
lu
atio
n
ca
teg
o
r
y
,
in
cl
u
d
in
g
co
u
n
tr
y
id
e
n
tity
an
d
liq
u
id
ity
,
lev
er
ag
e,
p
r
o
f
itab
ilit
y
,
co
v
er
ag
e,
an
d
ac
tiv
ity
.
W
ith
t
h
e
lo
west
E
E
R
o
f
4
1
%
an
d
th
e
h
ig
h
est
AUC
v
alu
e
o
f
0
.
6
2
,
th
e
ANN
is
th
e
b
est
p
r
ed
icto
r
o
f
f
in
an
cial
d
is
tr
ess
wh
en
th
e
class
ic
s
in
g
le
-
p
er
io
d
r
atio
in
p
u
t
is
u
s
ed
.
T
h
e
m
o
d
el
co
r
r
ec
tly
ca
teg
o
r
izes
f
in
an
cial
is
s
u
es
in
6
6
%
o
f
th
e
s
itu
atio
n
s
.
T
h
e
m
o
d
elin
g
ca
teg
o
r
izatio
n
ac
cu
r
ac
y
is
m
u
ch
b
ette
r
with
th
e
ad
d
itio
n
o
f
ad
d
itio
n
al
in
d
e
p
en
d
e
n
t
v
ar
i
ab
les
th
at
r
ep
r
esen
t
f
ac
t
o
r
s
s
u
c
h
as
y
ea
r
,
ass
et
ch
an
g
es,
an
d
s
ales
ch
ar
ac
ter
is
tics
.
T
h
e
s
en
s
itiv
ity
p
r
e
d
i
ctio
n
o
f
th
e
ANN
m
o
d
el
d
ec
r
ea
s
ed
b
y
6
p
er
ce
n
tag
e
p
o
in
ts
wh
e
n
c
o
m
p
ar
ed
to
th
e
L
STM
m
o
d
el,
wh
ic
h
is
th
e
b
est
class
i
f
ier
m
o
d
el
with
an
AUC
o
f
0
.
5
7
an
d
th
e
lo
west
E
E
R
o
f
4
1
%.
T
h
e
d
e
v
elo
p
m
e
n
t
o
f
an
em
p
ir
ical
m
o
d
el
b
y
c
o
n
s
id
er
in
g
th
e
class
if
icatio
n
r
e
s
p
o
n
s
e
in
cl
u
d
es
v
a
r
iab
les
an
d
m
o
d
if
icatio
n
s
to
tr
ain
in
g
tech
n
iq
u
es.
T
h
e
m
u
lt
i
-
p
er
io
d
class
if
icatio
n
p
er
f
o
r
m
s
b
etter
o
v
er
all
th
an
th
e
s
tatic
p
er
io
d
p
r
ed
icto
r
,
p
r
o
v
in
g
th
at
th
e
tim
e
elem
en
t
r
ea
lly
r
ed
u
ce
s
th
e
u
n
ce
r
tain
t
y
f
ac
to
r
b
y
ac
co
u
n
tin
g
f
o
r
r
is
k
y
tim
es.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
e
au
th
o
r
wo
u
ld
lik
e
to
th
a
n
k
th
e
C
en
ter
f
o
r
R
esear
ch
an
d
C
o
m
m
u
n
ity
Ser
v
ice
(
P3
M)
o
f
I
n
s
titu
te
o
f
W
id
y
a
Pra
tam
a
f
o
r
p
r
o
v
i
d
in
g
t
h
e
n
ec
ess
ar
y
f
ac
ilit
ies
an
d
s
u
p
p
o
r
t f
o
r
th
is
r
esear
ch
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
is
f
u
n
d
e
d
b
y
th
e
Dir
ec
to
r
ate
o
f
R
esear
ch
,
T
ec
h
n
o
lo
g
y
,
an
d
C
o
m
m
u
n
it
y
Ser
v
ice
(
DR
T
PM)
o
f
th
e
Min
is
tr
y
o
f
E
d
u
ca
tio
n
,
C
u
ltu
r
e,
R
esear
ch
,
an
d
T
ec
h
n
o
lo
g
y
.
C
o
n
tr
ac
t
No
.
1
0
8
/E5
/PG.0
2
.
0
0
.
PL/2
0
2
4
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
e
d
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
F
in
a
n
cia
l d
is
tr
ess
p
r
ed
ictio
n
fo
r
b
a
tik
s
ma
ll a
n
d
med
i
u
m
en
t
erp
r
is
e
s
cred
it fin
a
n
cin
g
b
a
s
e
d
…
(
Ta
r
ya
d
i
)
251
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
T
ar
y
ad
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
B
am
b
an
g
Su
d
iy
atn
o
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
R
o
b
er
tu
s
B
asiy
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
E
r
a
Yu
n
ian
to
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
ter
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
s
u
p
p
o
r
tin
g
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
a
v
ailab
le
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
au
t
h
o
r
,
[
T
]
,
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est.
T
o
p
r
o
tect
p
ar
ticip
an
t
p
r
i
v
ac
y
,
in
ac
c
o
r
d
an
ce
with
th
e
eth
ics
ap
p
r
o
v
al
o
f
th
e
I
n
s
titu
te
o
f
W
id
y
a
Pra
tam
a
C
en
ter
f
o
r
R
esear
ch
an
d
C
o
m
m
u
n
ity
Ser
v
ice,
p
u
b
licly
s
h
ar
ea
b
le
m
ate
r
ials
ar
e
lim
ited
to
ag
g
r
eg
ated
r
esu
lts
,
co
d
eb
o
o
k
s
,
an
d
an
aly
s
is
s
cr
ip
ts
.
An
o
n
y
m
ized
s
u
r
v
ey
d
ata
m
a
y
b
e
s
h
a
r
ed
u
n
d
er
a
d
ata
u
s
e
ag
r
ee
m
en
t; f
u
ll in
ter
v
iew
tr
an
s
cr
ip
ts
ar
e
n
o
t p
u
b
licly
av
aila
b
le.
RE
F
E
R
E
NC
E
S
[
1
]
J.
P
i
c
k
e
r
t
,
“
R
i
s
k
a
sse
ssm
e
n
t
o
f
u
n
s
e
c
u
r
e
d
l
o
a
n
s
–
e
x
a
m
p
l
e
o
f
e
n
t
e
r
i
n
g
a
n
e
w
mar
k
e
t
,
”
T
h
e
C
e
n
t
r
a
l
E
u
r
o
p
e
a
n
Re
v
i
e
w
o
f
E
c
o
n
o
m
i
c
s
a
n
d
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
1
,
n
o
.
3
,
N
o
v
.
2
0
1
7
,
d
o
i
:
1
0
.
2
9
0
1
5
/
c
e
r
e
m.
4
4
9
.
[
2
]
F
.
B
u
t
a
r
u
,
Q
.
C
h
e
n
,
B
.
C
l
a
r
k
,
S
.
D
a
s,
A
.
W
.
L
o
,
a
n
d
A
.
S
i
d
d
i
q
u
e
,
“
R
i
s
k
a
n
d
r
i
s
k
m
a
n
a
g
e
me
n
t
i
n
t
h
e
c
r
e
d
i
t
c
a
r
d
i
n
d
u
s
t
r
y
,
”
J
o
u
r
n
a
l
o
f
Ba
n
k
i
n
g
& F
i
n
a
n
c
e
,
v
o
l
.
7
2
,
p
p
.
2
1
8
–
2
3
9
,
N
o
v
.
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
b
a
n
k
f
i
n
.
2
0
1
6
.
0
7
.
0
1
5
.
[
3
]
E.
G
r
e
g
o
v
a
,
K
.
V
a
l
a
s
k
o
v
a
,
P
.
A
d
a
m
k
o
,
M
.
Tu
mp
a
c
h
,
a
n
d
J
.
Jar
o
s,
“
P
r
e
d
i
c
t
i
n
g
f
i
n
a
n
c
i
a
l
d
i
s
t
r
e
ss
o
f
S
l
o
v
a
k
e
n
t
e
r
p
r
i
ses:
c
o
mp
a
r
i
s
o
n
o
f
se
l
e
c
t
e
d
t
r
a
d
i
t
i
o
n
a
l
a
n
d
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms m
e
t
h
o
d
s
,
”
S
u
st
a
i
n
a
b
i
l
i
t
y
,
v
o
l
.
1
2
,
n
o
.
1
0
,
M
a
y
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
su
1
2
1
0
3
9
5
4
.
[
4
]
A
.
J.
B
.
O
l
i
v
e
r
,
A
.
I
.
I
.
D
i
é
g
u
e
z
,
M
.
D
.
O
.
A
l
f
o
n
s
o
,
a
n
d
N
.
W
i
l
s
o
n
,
“
I
mp
r
o
v
i
n
g
b
a
n
k
r
u
p
t
c
y
p
r
e
d
i
c
t
i
o
n
i
n
m
i
c
r
o
-
e
n
t
i
t
i
e
s
b
y
u
si
n
g
n
o
n
l
i
n
e
a
r
e
f
f
e
c
t
s
a
n
d
n
o
n
-
f
i
n
a
n
c
i
a
l
v
a
r
i
a
b
l
e
s
,
”
Fi
n
a
n
c
e
a
ú
v
ě
r:
C
z
e
c
h
J
o
u
rn
a
l
o
f
Ec
o
n
o
m
i
c
s
a
n
d
Fi
n
a
n
c
e
,
v
o
l
.
6
5
,
n
o
.
2
,
p
p
.
1
4
4
–
1
6
6
,
2
0
1
5
.
[
5
]
A
.
N
.
B
e
r
g
e
r
a
n
d
W
.
S
.
F
r
a
m
e
,
“
S
m
a
l
l
b
u
si
n
e
ss
c
r
e
d
i
t
sc
o
r
i
n
g
a
n
d
c
r
e
d
i
t
a
v
a
i
l
a
b
i
l
i
t
y
,
”
J
o
u
rn
a
l
o
f
S
m
a
l
l
B
u
si
n
e
ss
M
a
n
a
g
e
m
e
n
t
,
v
o
l
.
4
5
,
n
o
.
1
,
p
p
.
5
–
2
2
,
J
a
n
.
2
0
0
7
,
d
o
i
:
1
0
.
1
1
1
1
/
j
.
1
5
4
0
-
6
2
7
X
.
2
0
0
7
.
0
0
1
9
5
.
x
.
[
6
]
Y
.
Z
h
u
,
C
.
X
i
e
,
B
.
S
u
n
,
G
.
-
J.
W
a
n
g
,
a
n
d
X
.
-
G
.
Y
a
n
,
“
P
r
e
d
i
c
t
i
n
g
C
h
i
n
a
’
s
S
M
E
c
r
e
d
i
t
r
i
sk
i
n
su
p
p
l
y
c
h
a
i
n
f
i
n
a
n
c
i
n
g
b
y
l
o
g
i
st
i
c
r
e
g
r
e
ss
i
o
n
,
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
a
n
d
h
y
b
r
i
d
m
o
d
e
l
s
,
”
S
u
st
a
i
n
a
b
i
l
i
t
y
,
v
o
l
.
8
,
n
o
.
5
,
M
a
y
2
0
1
6
,
d
o
i
:
1
0
.
3
3
9
0
/
s
u
8
0
5
0
4
3
3
.
[
7
]
R
.
O
.
Ed
mi
s
t
e
r
,
“
F
i
n
a
n
c
i
a
l
r
a
t
i
o
s
a
s
d
i
s
c
r
i
mi
n
a
n
t
p
r
e
d
i
c
t
o
r
s
o
f
sma
l
l
b
u
s
i
n
e
ss
f
a
i
l
u
r
e
,
”
T
h
e
J
o
u
r
n
a
l
o
f
Fi
n
a
n
c
e
,
v
o
l
.
2
7
,
n
o
.
1
,
p
p
.
1
3
9
–
1
4
0
,
M
a
r
.
1
9
7
2
,
d
o
i
:
1
0
.
1
1
1
1
/
j
.
1
5
4
0
-
6
2
6
1
.
1
9
7
2
.
t
b
0
0
6
3
3
.
x
.
[
8
]
E.
I
.
A
l
t
ma
n
a
n
d
G
.
S
a
b
a
t
o
,
“
M
o
d
e
l
l
i
n
g
c
r
e
d
i
t
r
i
s
k
f
o
r
S
M
Es
:
e
v
i
d
e
n
c
e
f
r
o
m
t
h
e
U
.
S
.
mar
k
e
t
,
”
Ab
a
c
u
s
,
v
o
l
.
4
3
,
n
o
.
3
,
p
p
.
3
3
2
–
3
5
7
,
S
e
p
.
2
0
0
7
,
d
o
i
:
1
0
.
1
1
1
1
/
j
.
1
4
6
7
-
6
2
8
1
.
2
0
0
7
.
0
0
2
3
4
.
x
.
[
9
]
E.
I
.
A
l
t
m
a
n
,
“
F
i
n
a
n
c
i
a
l
r
a
t
i
o
s,
d
i
s
c
r
i
mi
n
a
n
t
a
n
a
l
y
si
s
a
n
d
t
h
e
p
r
e
d
i
c
t
i
o
n
o
f
c
o
r
p
o
r
a
t
e
b
a
n
k
r
u
p
t
c
y
,
”
T
h
e
J
o
u
rn
a
l
o
f
F
i
n
a
n
c
e
,
v
o
l
.
2
3
,
n
o
.
4
,
p
p
.
5
8
9
–
6
0
9
,
S
e
p
.
1
9
6
8
,
d
o
i
:
1
0
.
1
1
1
1
/
j
.
1
5
4
0
-
6
2
6
1
.
1
9
6
8
.
t
b
0
0
8
4
3
.
x
.
[
1
0
]
R
.
C
.
M
e
r
t
o
n
,
“
O
n
t
h
e
p
r
i
c
i
n
g
o
f
c
o
r
p
o
r
a
t
e
d
e
b
t
:
t
h
e
r
i
s
k
st
r
u
c
t
u
r
e
o
f
i
n
t
e
r
e
st
r
a
t
e
s,
”
T
h
e
J
o
u
r
n
a
l
o
f
F
i
n
a
n
c
e
,
v
o
l
.
2
9
,
n
o
.
2
,
p
p
.
4
4
9
–
4
7
0
,
M
a
y
1
9
7
4
,
d
o
i
:
1
0
.
1
1
1
1
/
j
.
1
5
4
0
-
6
2
6
1
.
1
9
7
4
.
t
b
0
3
0
5
8
.
x
.
[
1
1
]
M
.
El
h
o
se
n
y
,
N
.
M
e
t
a
w
a
,
G
.
S
z
t
a
n
o
,
a
n
d
I
.
M
.
E
l
-
h
a
sn
o
n
y
,
“
D
e
e
p
l
e
a
r
n
i
n
g
-
b
a
se
d
mo
d
e
l
f
o
r
f
i
n
a
n
c
i
a
l
d
i
s
t
r
e
ss
p
r
e
d
i
c
t
i
o
n
,
”
A
n
n
a
l
s
o
f
O
p
e
r
a
t
i
o
n
s
Re
se
a
rc
h
,
v
o
l
.
3
4
5
,
n
o
.
2
–
3
,
p
p
.
8
8
5
–
9
0
7
,
F
e
b
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
4
7
9
-
0
2
2
-
0
4
7
6
6
-
5.
[
1
2
]
F
.
M
.
I
r
v
a
n
,
“
C
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
s
i
s
o
f
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
s
i
n
t
e
g
r
a
t
e
d
w
i
t
h
A
l
t
ma
n
z
-
sc
o
r
e
f
o
r
f
i
n
a
n
c
i
a
l
d
i
s
t
r
e
ss
p
r
e
d
i
c
t
i
o
n
i
n
c
o
m
p
a
n
i
e
s
l
i
st
e
d
o
n
t
h
e
I
n
d
o
n
e
si
a
st
o
c
k
e
x
c
h
a
n
g
e
(
I
D
X
)
,
”
E
K
O
MB
I
S
RE
VI
EW
:
J
u
rn
a
l
I
l
m
i
a
h
Ek
o
n
o
m
i
d
a
n
Bi
sn
i
s
,
v
o
l
.
1
2
,
n
o
.
2
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
3
7
6
7
6
/
e
k
o
m
b
i
s.
v
1
2
i
2
.
5
4
7
8
.
[
1
3
]
H
.
A
.
B
e
k
h
e
t
a
n
d
S
.
F
.
K
.
El
e
t
t
e
r
,
“
C
r
e
d
i
t
r
i
sk
a
ss
e
ssm
e
n
t
m
o
d
e
l
f
o
r
J
o
r
d
a
n
i
a
n
c
o
mm
e
r
c
i
a
l
b
a
n
k
s:
n
e
u
r
a
l
sc
o
r
i
n
g
a
p
p
r
o
a
c
h
,
”
R
e
v
i
e
w
o
f
D
e
v
e
l
o
p
m
e
n
t
F
i
n
a
n
c
e
,
v
o
l
.
4
,
n
o
.
1
,
p
p
.
2
0
–
2
8
,
Ja
n
.
2
0
1
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
d
f
.
2
0
1
4
.
0
3
.
0
0
2
.
[
1
4
]
A
.
F
.
A
t
i
y
a
,
“
B
a
n
k
r
u
p
t
c
y
p
r
e
d
i
c
t
i
o
n
f
o
r
c
r
e
d
i
t
r
i
sk
u
si
n
g
n
e
u
r
a
l
n
e
t
w
o
r
k
s
:
a
s
u
r
v
e
y
a
n
d
n
e
w
r
e
s
u
l
t
s,
”
I
EEE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
N
e
u
r
a
l
N
e
t
w
o
rks
,
v
o
l
.
1
2
,
n
o
.
4
,
p
p
.
9
2
9
–
9
3
5
,
Ju
l
.
2
0
0
1
,
d
o
i
:
1
0
.
1
1
0
9
/
7
2
.
9
3
5
1
0
1
.
[
1
5
]
C.
-
F
.
Tsa
i
a
n
d
J.
-
W
.
W
u
,
“
U
si
n
g
n
e
u
r
a
l
n
e
t
w
o
r
k
e
n
sem
b
l
e
s
f
o
r
b
a
n
k
r
u
p
t
c
y
p
r
e
d
i
c
t
i
o
n
a
n
d
c
r
e
d
i
t
sc
o
r
i
n
g
,
”
Ex
p
e
r
t
S
y
s
t
e
m
s
w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
4
,
n
o
.
4
,
p
p
.
2
6
3
9
–
2
6
4
9
,
M
a
y
2
0
0
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
0
7
.
0
5
.
0
1
9
.
[
1
6
]
P
.
A
d
d
o
,
D
.
G
u
e
g
a
n
,
a
n
d
B
.
H
a
ssa
n
i
,
“
C
r
e
d
i
t
r
i
sk
a
n
a
l
y
s
i
s
u
s
i
n
g
ma
c
h
i
n
e
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
s
,
”
Ri
s
k
s
,
v
o
l
.
6
,
n
o
.
2
,
A
p
r
.
2
0
1
8
,
d
o
i
:
1
0
.
3
3
9
0
/
r
i
sk
s
6
0
2
0
0
3
8
.
[
1
7
]
X
.
H
u
a
n
g
,
X
.
Li
u
,
a
n
d
Y
.
R
e
n
,
“
En
t
e
r
p
r
i
se
c
r
e
d
i
t
r
i
sk
e
v
a
l
u
a
t
i
o
n
b
a
se
d
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
a
l
g
o
r
i
t
h
m,
”
C
o
g
n
i
t
i
v
e
S
y
st
e
m
s
R
e
se
a
rc
h
,
v
o
l
.
5
2
,
p
p
.
3
1
7
–
3
2
4
,
D
e
c
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
g
s
y
s.
2
0
1
8
.
0
7
.
0
2
3
.
[
1
8
]
M
.
M
o
s
c
a
t
e
l
l
i
,
F
.
P
a
r
l
a
p
i
a
n
o
,
S
.
N
a
r
i
z
z
a
n
o
,
a
n
d
G
.
V
i
g
g
i
a
n
o
,
“
C
o
r
p
o
r
a
t
e
d
e
f
a
u
l
t
f
o
r
e
c
a
s
t
i
n
g
w
i
t
h
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
Ex
p
e
r
t
S
y
st
e
m
s
w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
6
1
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
0
.
1
1
3
5
6
7
.
[
1
9
]
D
.
B
o
u
g
h
a
c
i
,
A
.
A
.
K
.
A
l
k
h
a
w
a
l
d
e
h
,
J.
J
.
J
a
b
e
r
,
a
n
d
N
.
H
a
m
a
d
n
e
h
,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
w
i
t
h
se
g
me
n
t
a
t
i
o
n
f
o
r
c
r
e
d
i
t
s
c
o
r
i
n
g
a
n
d
b
a
n
k
r
u
p
t
c
y
p
r
e
d
i
c
t
i
o
n
,
”
Em
p
i
r
i
c
a
l
E
c
o
n
o
m
i
c
s
,
v
o
l
.
6
1
,
n
o
.
3
,
p
p
.
1
2
8
1
–
1
3
0
9
,
S
e
p
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s0
0
1
8
1
-
0
2
0
-
0
1
9
0
1
-
8.
[
2
0
]
N
.
A
r
o
r
a
a
n
d
P
.
D
.
K
a
u
r
,
“
A
B
o
l
a
sso
b
a
se
d
c
o
n
s
i
st
e
n
t
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
e
n
a
b
l
e
d
r
a
n
d
o
m
f
o
r
e
s
t
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
l
g
o
r
i
t
h
m:
a
n
a
p
p
l
i
c
a
t
i
o
n
t
o
c
r
e
d
i
t
r
i
s
k
a
sses
sme
n
t
,
”
Ap
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
8
6
,
Ja
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
s
o
c
.
2
0
1
9
.
1
0
5
9
3
6
.
[
2
1
]
N
.
Jap
k
o
w
i
c
z
a
n
d
M
.
S
h
a
h
,
E
v
a
l
u
a
t
i
n
g
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
s
.
C
a
m
b
r
i
d
g
e
U
n
i
v
e
r
si
t
y
P
r
e
ss,
2
0
1
1
.
d
o
i
:
1
0
.
1
0
1
7
/
C
B
O
9
7
8
0
5
1
1
9
2
1
8
0
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
1
5
,
No
.
1
,
Ma
r
c
h
2
0
2
6
:
244
-
2
5
2
252
[
2
2
]
Y.
-
C
.
C
h
a
n
g
,
K
.
-
H
.
C
h
a
n
g
,
H
.
-
H
.
C
h
u
,
a
n
d
L
.
-
I
.
To
n
g
,
“
Es
t
a
b
l
i
sh
i
n
g
d
e
c
i
s
i
o
n
t
r
e
e
-
b
a
se
d
s
h
o
r
t
-
t
e
r
m
d
e
f
a
u
l
t
c
r
e
d
i
t
r
i
s
k
a
ssessm
e
n
t
mo
d
e
l
s
,
”
C
o
m
m
u
n
i
c
a
t
i
o
n
s
i
n
S
t
a
t
i
st
i
c
s
-
T
h
e
o
ry
a
n
d
Me
t
h
o
d
s
,
v
o
l
.
4
5
,
n
o
.
2
3
,
p
p
.
6
8
0
3
–
6
8
1
5
,
D
e
c
.
2
0
1
6
,
d
o
i
:
1
0
.
1
0
8
0
/
0
3
6
1
0
9
2
6
.
2
0
1
4
.
9
6
8
7
3
0
.
[
2
3
]
Y
.
Q
u
,
P
.
Q
u
a
n
,
M
.
Le
i
,
a
n
d
Y
.
S
h
i
,
“
R
e
v
i
e
w
o
f
b
a
n
k
r
u
p
t
c
y
p
r
e
d
i
c
t
i
o
n
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
,
”
Pro
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
6
2
,
p
p
.
8
9
5
–
8
9
9
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
1
9
.
1
2
.
0
6
5
.
[
2
4
]
S
.
M
a
l
d
o
n
a
d
o
,
J.
P
é
r
e
z
,
a
n
d
C
.
B
r
a
v
o
,
“
C
o
s
t
-
b
a
s
e
d
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
f
o
r
s
u
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
s
:
a
n
a
p
p
l
i
c
a
t
i
o
n
i
n
c
r
e
d
i
t
sc
o
r
i
n
g
,
”
Eu
r
o
p
e
a
n
J
o
u
r
n
a
l
o
f
O
p
e
r
a
t
i
o
n
a
l
R
e
s
e
a
r
c
h
,
v
o
l
.
2
6
1
,
n
o
.
2
,
p
p
.
6
5
6
–
6
6
5
,
S
e
p
.
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
j
o
r
.
2
0
1
7
.
0
2
.
0
3
7
.
[
2
5
]
J.
S
u
n
,
J.
L
a
n
g
,
H
.
F
u
j
i
t
a
,
a
n
d
H
.
L
i
,
“
I
mb
a
l
a
n
c
e
d
e
n
t
e
r
p
r
i
s
e
c
r
e
d
i
t
e
v
a
l
u
a
t
i
o
n
w
i
t
h
D
TE
-
S
B
D
:
d
e
c
i
s
i
o
n
t
r
e
e
e
n
semb
l
e
b
a
se
d
o
n
S
M
O
TE
a
n
d
b
a
g
g
i
n
g
w
i
t
h
d
i
f
f
e
r
e
n
t
i
a
t
e
d
sam
p
l
i
n
g
r
a
t
e
s,
”
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
4
2
5
,
p
p
.
7
6
–
9
1
,
J
a
n
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
s
.
2
0
1
7
.
1
0
.
0
1
7
.
[
2
6
]
N
.
W
.
D
.
A
y
u
n
i
,
W
.
H
.
U
t
t
h
a
v
i
,
a
n
d
N
.
N
.
L
a
smi
n
i
,
“
A
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s:
a
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
i
n
f
i
n
a
n
c
i
a
l
d
i
st
r
e
ss
p
r
e
d
i
c
t
i
o
n
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
u
s
t
a
i
n
a
b
l
e
G
ree
n
T
o
u
ri
sm
A
p
p
l
i
e
d
S
c
i
e
n
c
e
-
En
g
i
n
e
e
ri
n
g
A
p
p
l
i
e
d
S
c
i
e
n
c
e
2
0
2
4
(
I
C
o
S
T
A
S
-
EA
S
2
0
2
4
)
,
2
0
2
4
,
p
p
.
9
9
–
1
0
8
.
d
o
i
:
1
0
.
2
9
9
1
/
9
7
8
-
94
-
6
4
6
3
-
5
8
7
-
4
_
1
2
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ta
r
y
a
d
i
is
a
n
e
x
p
e
rien
c
e
d
lec
t
u
re
r
with
a
p
r
o
v
e
n
trac
k
re
c
o
rd
in
th
e
F
a
c
u
l
ty
o
f
In
fo
rm
a
ti
o
n
S
y
ste
m
s.
Co
m
p
e
ten
t
in
th
e
field
o
f
a
rti
ficia
l
in
telli
g
e
n
c
e
a
n
d
m
a
c
h
in
e
lea
rn
in
g
.
Th
e
re
se
a
rc
h
c
o
n
d
u
c
ted
d
isc
u
ss
e
s
a
lo
t
o
f
a
rti
ficia
l
i
n
telli
g
e
n
c
e
a
n
d
tea
c
h
e
s
a
t
th
e
F
a
c
u
l
t
y
o
f
In
fo
rm
a
ti
o
n
S
y
ste
m
s,
In
stit
u
te
o
f
Wi
d
y
a
P
ra
tam
a
,
P
e
k
a
lo
n
g
a
n
,
In
d
o
n
e
sia
.
He
c
a
n
b
e
c
o
n
tac
ted
at
e
m
a
il
:
tari_
b
a
ll
@s
tmik
-
wp
.
a
c
.
i
d
.
Ba
m
b
a
n
g
S
u
d
iy
a
tn
o
is
a
ss
o
c
iate
p
ro
fe
ss
o
r
,
De
p
a
rtme
n
t
o
f
M
a
n
a
g
e
m
e
n
t,
Un
iv
e
rsity
o
f
S
ti
k
u
b
a
n
k
,
S
e
m
a
ra
n
g
,
In
d
o
n
e
sia
.
Re
se
a
rc
h
in
th
e
field
o
f
m
a
n
a
g
e
m
e
n
t,
e
c
o
n
o
m
ics
,
a
n
d
i
n
tere
st
in
th
e
d
e
v
e
lo
p
m
e
n
t
o
f
sm
a
ll
a
n
d
m
e
d
iu
m
e
n
terp
rise
s.
He
c
a
n
b
e
c
o
n
tac
ted
at
e
m
a
il
:
b
o
fy
sa
tri
a
sm
a
ra
@y
a
h
o
o
.
c
o
m
.
Ro
b
e
r
tu
s
Ba
siy
a
is
a
ss
o
c
iate
p
ro
fe
ss
o
r
,
De
p
a
rtme
n
t
o
f
M
a
n
a
g
e
m
e
n
t,
Un
i
v
e
rsity
o
f
S
ti
k
u
b
a
n
k
S
e
m
a
ra
n
g
,
I
n
d
o
n
e
s
ia.
Re
se
a
rc
h
in
th
e
field
o
f
m
a
n
a
g
e
m
e
n
t,
e
c
o
n
o
m
ics
,
a
n
d
in
tere
st
in
th
e
d
e
v
e
l
o
p
m
e
n
t
o
f
sm
a
ll
a
n
d
m
e
d
iu
m
e
n
terp
rise
s.
He
c
a
n
b
e
c
o
n
tac
ted
at
e
m
a
il
:
rb
a
siy
a
@e
d
u
.
u
n
is
b
a
n
k
.
a
c
.
id
.
Er
a
Yun
in
a
t
o
is
a
lec
tu
re
r
a
n
d
re
se
a
rc
h
e
r
a
t
th
e
F
a
c
u
lt
y
o
f
In
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
a
t
th
e
In
sti
tu
te o
f
Wi
d
y
a
P
ra
tam
a
,
P
e
k
a
lo
n
g
a
n
,
I
n
d
o
n
e
sia
.
His
re
se
a
r
c
h
in
tere
sts
in
c
lu
d
e
c
o
m
p
u
ter
n
e
two
r
k
s,
m
a
c
h
in
e
lea
rn
in
g
,
a
n
d
i
n
fo
rm
a
ti
o
n
s
y
st
e
m
s.
H
e
c
a
n
b
e
c
o
n
tac
ted
at
e
m
a
il
:
e
ra
.
y
u
n
i
n
a
to
@
g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.