I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
38
,
No
.
1
,
A
p
r
il
20
25
,
p
p
.
508
~
516
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
38.
i
1
.
p
p
508
-
5
1
6
508
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Co
mpa
ring
ma
chine learning
mo
de
ls for
Indo
nesia
st
o
ck
ma
rket
pr
edictio
n
Selly
Ana
s
t
a
s
s
ia
Am
ellia
K
ha
ris
1
,
Arm
a
n H
a
qq
i A
nn
a
Z
i
li
2
,
M
a
ula
na
M
a
lik
2
,
Wa
hy
u Nury
a
nin
g
rum
2
,
Ag
us
t
ia
ni P
utr
i
3
1
D
e
p
a
r
t
me
n
t
o
f
M
a
t
h
e
m
a
t
i
c
s
,
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
U
n
i
v
e
r
si
t
a
s T
e
r
b
u
k
a
,
Ta
n
g
e
r
a
n
g
,
I
n
d
o
n
e
si
a
2
D
e
p
a
r
t
me
n
t
o
f
M
a
t
h
e
m
a
t
i
c
s
,
F
a
c
u
l
t
y
o
f
M
a
t
h
e
mat
i
c
s
a
n
d
N
a
t
u
r
a
l
S
c
i
e
n
c
e
s,
U
n
i
v
e
r
s
i
t
a
s I
n
d
o
n
e
si
a
,
D
e
p
o
k
,
I
n
d
o
n
e
si
a
3
D
e
p
a
r
t
me
n
t
o
f
M
a
t
h
e
m
a
t
i
c
s
,
F
a
c
u
l
t
y
o
f
M
a
t
h
e
mat
i
c
s
a
n
d
N
a
t
u
r
a
l
S
c
i
e
n
c
e
s,
U
n
i
v
e
r
s
i
t
a
s Ne
g
e
r
i
M
a
l
a
n
g
,
M
a
l
a
n
g
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
19
,
2
0
2
4
R
ev
is
ed
Oct
17
,
2
0
2
4
Acc
ep
ted
Oct
30
,
2
0
2
4
Th
e
fin
a
n
c
ial
m
a
rk
e
t
h
o
l
d
a
si
g
n
if
ica
n
t
ro
le i
n
th
e
e
c
o
n
o
m
y
a
n
d
th
e
a
b
il
it
y
t
o
a
c
c
u
ra
tely
p
re
d
ict
sto
c
k
p
rice
s
p
o
se
s
a
m
a
jo
r
c
h
a
ll
e
n
g
e
,
p
a
rt
icu
larly
i
n
v
o
latil
e
m
a
rk
e
ts
l
ik
e
I
n
d
o
n
e
sia
.
Th
is
stu
d
y
in
v
e
stig
a
tes
t
h
e
a
p
p
l
i
c
a
ti
o
n
o
f
th
re
e
su
p
e
r
v
ise
d
m
a
c
h
i
n
e
lea
rn
i
n
g
a
lg
o
rit
h
m
s:
ra
n
d
o
m
f
o
re
st
(R
F
),
su
p
p
o
rt
v
e
c
to
r
re
g
re
ss
io
n
(
S
VR),
K
-
n
e
a
re
st
n
e
ig
h
b
o
r
(KN
N)
to
p
re
d
ict
t
h
e
c
lo
sin
g
p
rice
s
o
f
sto
c
k
s.
Th
e
d
a
ta
u
s
e
d
i
n
th
is
re
se
a
rc
h
c
o
n
sists
o
f
BBC
A,
P
WON,
a
n
d
TOW
R
sto
c
k
s.
T
h
is
stu
d
y
a
d
o
p
te
d
d
a
i
ly
h
ist
o
rica
l
sto
c
k
p
r
ice
s
fro
m
M
a
rc
h
2
0
1
7
t
o
F
e
b
r
u
a
ry
2
0
2
0
,
wh
ich
we
re
n
o
rm
a
li
z
e
d
a
n
d
se
g
m
e
n
ted
in
to
train
in
g
a
n
d
tes
ti
n
g
d
a
tas
e
ts.
Th
e
m
o
d
e
ls
we
re
train
e
d
u
sin
g
m
a
c
h
in
e
lea
rn
in
g
tec
h
n
i
q
u
e
s,
a
n
d
t
h
e
ir
p
r
e
d
ictiv
e
a
c
c
u
ra
c
y
wa
s
e
v
a
lu
a
ted
u
sin
g
ro
o
t
m
e
a
n
sq
u
a
re
e
rro
r
(RM
S
E)
a
n
d
m
e
a
n
a
b
so
lu
te
e
rro
r
(M
AE).
T
h
e
h
isto
rica
l
sto
c
k
d
a
ta
in
c
l
u
d
e
s
Op
e
n
,
Hi
g
h
,
Lo
w,
a
n
d
C
lo
se
p
rice
s.
Th
e
re
su
l
t
in
d
ica
ted
th
a
t
S
VR
c
o
n
siste
n
tl
y
o
u
t
p
e
rfo
r
m
s
RF
a
n
d
KN
N
i
n
term
s
o
f
RM
S
E
a
n
d
M
AE
a
c
ro
ss
d
iffere
n
t
sto
c
k
s.
T
h
e
S
VR
m
e
th
o
d
p
r
o
d
u
c
e
d
R
M
S
E
v
a
l
u
e
s
o
f
4
.
7
9
%
fo
r
BBCA
st
o
c
k
,
1
0
.
6
1
%
fo
r
P
WON
sto
c
k
,
a
n
d
1
5
.
1
4
%
f
o
r
TOW
R
sto
c
k
,
a
n
d
p
r
o
d
u
c
e
s
M
AE
v
a
lu
e
s
o
f
3
.
5
2
%
f
o
r
BBCA
sto
c
k
,
8
.
4
9
%
f
o
r
P
WON sto
c
k
,
a
n
d
1
3
.
7
8
%
fo
r
TOW
R
sto
c
k
.
K
ey
w
o
r
d
s
:
I
n
v
estme
n
t
K
-
n
ea
r
est n
eig
h
b
o
r
R
an
d
o
m
f
o
r
est
Sto
ck
p
r
ice
p
r
ed
ictio
n
Su
p
p
o
r
t
v
ec
to
r
r
e
g
r
ess
io
n
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
:
Selly
An
astas
s
ia
Am
ellia
Kh
a
r
is
Dep
ar
tm
en
t o
f
Ma
th
em
atics,
Facu
lty
o
f
Scien
ce
a
n
d
T
ec
h
n
o
l
o
g
y
,
Un
i
v
er
s
itas
T
er
b
u
k
a
1
5
4
1
8
So
u
th
T
an
g
er
a
n
g
,
B
an
t
en
,
I
n
d
o
n
esia
E
m
ail: selly
@
ec
am
p
u
s
.
u
t.a
c.
id
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
welf
ar
e
o
f
an
y
g
r
o
win
g
n
atio
n
,
ec
o
n
o
m
y
,
o
r
c
o
m
m
u
n
ity
in
t
h
e
2
1
st
ce
n
t
u
r
y
p
r
im
ar
ily
r
ests
o
v
er
th
eir
s
to
ck
p
r
ice
an
d
m
ar
k
et
ec
o
n
o
m
y
,
b
y
th
e
f
in
an
cial
m
ar
k
et
s
er
v
in
g
as
th
e
k
e
y
p
illa
r
[
1
]
,
[
2
]
.
Fin
an
cial
m
ar
k
ets
r
em
ain
u
n
q
u
esti
o
n
ab
ly
f
o
r
em
o
s
t
am
o
n
g
th
e
m
o
s
t
ex
h
ilar
atin
g
in
v
en
tio
n
s
o
f
r
ec
en
t
y
ea
r
s
.
Gettin
g
p
r
ec
is
e
f
o
r
ec
as
ts
f
o
r
f
i
n
an
cial
f
u
tu
r
e
tim
e
s
er
ies
r
ec
e
n
tly
r
em
ain
s
a
ch
allen
g
in
g
u
n
d
er
ta
k
in
g
f
o
r
n
u
m
er
o
u
s
s
ch
o
lar
s
[
3
]
-
[
5
]
,
esp
ec
ially
o
win
g
to
th
e
p
r
esen
ce
o
f
n
o
n
li
n
e
ar
,
ir
r
eg
u
lar
,
an
d
u
n
p
r
ed
ictab
l
e
n
atu
r
e
[
6
]
.
B
y
th
e
ad
v
en
t
o
f
q
u
an
titativ
e
f
in
an
cial
m
an
ag
em
en
t,
ac
cu
r
a
te
f
o
r
ec
asts
o
f
s
to
ck
p
r
ice
s
h
if
ts
ar
e
ess
en
tial
f
o
r
in
v
estme
n
t
ap
p
r
o
ac
h
es,
w
h
ich
h
as
ca
p
t
u
r
ed
th
e
c
o
n
s
id
er
ab
le
en
th
u
s
iasm
f
r
o
m
c
o
m
p
an
ies
an
d
s
ch
o
lar
s
.
Desp
ite
m
ac
h
in
e
lear
n
in
g
m
o
d
els
ar
e
f
r
eq
u
en
tly
u
s
ed
in
em
er
g
in
g
m
ar
k
ets,
a
s
ig
n
if
i
ca
n
t
g
ap
ex
is
ts
in
und
er
s
tan
d
i
n
g
th
eir
e
f
f
ec
tiv
e
n
ess
,
p
ar
ticu
lar
ly
in
v
o
latile
r
eg
io
n
s
lik
e
I
n
d
o
n
esia.
T
h
is
s
tu
d
y
ad
d
r
ess
es
to
b
r
id
g
e
th
at
g
ap
b
y
co
m
p
ar
in
g
th
e
p
er
f
o
r
m
an
ce
o
f
th
r
ee
m
ac
h
in
e
lear
n
in
g
m
o
d
els:
r
an
d
o
m
f
o
r
est (
R
F),
s
u
p
p
o
r
t
v
ec
to
r
r
e
g
r
ess
io
n
(
SVR
)
,
an
d
K
-
n
ea
r
est n
eig
h
b
o
r
(
KNN)
wi
th
in
th
e
I
n
d
o
n
esian
s
to
ck
m
ar
k
et
co
n
tex
t.
Fo
r
ec
asti
n
g
s
to
ck
p
r
ices
in
e
m
er
g
in
g
m
ar
k
ets
s
u
ch
as
I
n
d
o
n
esia
b
e
a
d
if
f
icu
lt
is
s
u
e
d
u
e
to
in
h
er
en
t
v
o
latilit
y
,
n
o
n
lin
ea
r
b
eh
av
i
o
r
,
an
d
th
e
in
f
lu
e
n
ce
o
f
v
a
r
io
u
s
ec
o
n
o
m
ic,
p
o
liti
ca
l,
an
d
p
s
y
ch
o
lo
g
ical
f
ac
to
r
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
C
o
mp
a
r
in
g
ma
ch
in
e
lea
r
n
i
n
g
mo
d
els fo
r
i
n
d
o
n
esia
s
to
ck
ma
r
ke
t
… (
S
elly
A
n
a
s
ta
s
s
ia
A
mellia
K
h
a
r
is
)
509
T
r
ad
itio
n
al
s
tatis
tical
m
o
d
el
s
o
f
ten
s
tr
u
g
g
le
to
ac
c
o
u
n
t
f
o
r
th
ese
c
o
m
p
lex
ities
,
lea
d
in
g
t
o
in
ac
c
u
r
ate
p
r
ed
ictio
n
s
an
d
p
o
te
n
tial
f
in
a
n
cial
lo
s
s
es
[
7
]
,
[
8
]
.
I
n
th
e
c
o
n
tex
t
o
f
th
e
I
n
d
o
n
esian
s
to
ck
m
ar
k
et,
p
r
e
v
alen
t
liter
atu
r
e
in
d
icate
s
th
at
s
to
ck
p
r
i
ce
s
ar
e
i
n
f
lu
en
ce
d
b
y
v
a
r
io
u
s
f
ac
to
r
s
in
clu
d
in
g
p
o
liti
c
al
is
s
u
es,
ec
o
n
o
m
ic
co
n
d
itio
n
s
,
co
m
m
o
d
ity
p
r
ice
in
d
ex
es,
in
v
esto
r
ex
p
ec
tatio
n
s
,
s
h
if
ts
in
d
if
f
er
en
t
s
to
ck
m
ar
k
ets,
an
d
in
v
esto
r
p
s
y
ch
o
lo
g
y
[
9
]
.
T
h
ese
m
u
ltif
ac
eted
in
f
lu
e
n
ce
s
co
n
tr
ib
u
te
t
o
th
e
co
m
p
lex
it
y
o
f
ac
cu
r
atel
y
f
o
r
ec
asti
n
g
s
to
ck
p
r
ice
m
o
v
em
en
ts
.
C
o
n
s
eq
u
e
n
tly
,
th
er
e
is
a
n
ee
d
f
o
r
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
s
th
at
ar
e
ca
p
ab
le
o
f
m
o
d
ellin
g
an
d
an
aly
zin
g
th
ese
in
tr
icate
p
atter
n
s
.
T
h
e
s
ig
n
if
ican
ce
o
f
s
to
ck
class
if
icatio
n
is
o
f
ten
r
ef
le
cted
in
h
ig
h
m
a
r
k
e
t
c
a
p
i
t
a
li
z
a
ti
o
n
,
a
n
d
v
a
r
i
o
u
s
t
e
c
h
n
i
c
a
l
m
e
t
r
ic
s
a
r
e
a
v
a
i
l
a
b
l
e
t
o
d
e
r
i
v
e
i
n
s
i
g
h
ts
f
r
o
m
s
t
o
c
k
p
r
i
c
e
d
a
t
a
[
1
0
]
.
C
o
m
m
o
n
ly
,
s
to
ck
in
d
ex
d
ea
l
s
ar
e
d
er
iv
ed
f
r
o
m
s
to
ck
s
p
r
ices
with
h
ea
v
y
m
ar
k
et
in
v
estme
n
ts
an
d
th
ese
in
d
ices
f
r
eq
u
en
tly
will
p
r
o
v
id
e
a
f
o
r
ec
ast
o
f
th
e
s
tatu
s
o
f
th
e
ec
o
n
o
m
y
o
f
ea
c
h
n
atio
n
.
Fo
r
in
s
tan
ce
,
s
ev
er
al
liter
atu
r
e
ev
id
en
ce
t
h
a
t
th
e
ec
o
n
o
m
ic
d
ev
elo
p
m
en
t
i
n
m
an
y
n
atio
n
s
h
as
b
ee
n
s
ig
n
if
ican
tly
af
f
ec
ted
b
y
th
e
ca
p
italizatio
n
o
f
th
eir
s
to
ck
m
ar
k
ets
[
1
1
]
.
Ho
wev
er
,
s
h
if
ts
in
s
to
ck
p
r
ices
ex
h
ib
it
v
a
g
u
e
p
r
o
p
er
ties
,
wh
ich
p
u
ts
in
v
estme
n
ts
at
r
is
k
f
o
r
i
n
v
esto
r
s
.
Ad
d
itio
n
ally
,
it
is
c
h
allen
g
in
g
to
i
d
en
tify
th
e
m
a
r
k
et’
s
s
tatu
s
with
r
esp
ec
t
to
g
o
v
er
n
m
en
ts
.
I
n
f
ac
t,
s
to
ck
p
r
ices
ar
e
in
h
er
en
tly
v
o
latile,
n
o
n
lin
ea
r
,
an
d
u
n
p
r
ed
i
ctab
le.
Hen
ce
,
th
is
f
r
eq
u
e
n
tly
lead
s
t
o
u
n
d
er
p
e
r
f
o
r
m
an
ce
in
s
tatis
tical
f
o
r
ec
asti
n
g
m
o
d
els
an
d
f
ailu
r
e
to
f
o
r
ec
a
s
t
v
alu
es
an
d
s
h
if
ts
ac
cu
r
ately
[
1
2
]
,
[
1
3
]
.
T
h
is
ch
allen
g
e
u
n
d
er
s
co
r
es
th
e
n
ee
d
t
o
ex
p
l
o
r
e
s
tr
o
n
g
er
an
d
m
o
r
e
a
d
ap
tiv
e
f
o
r
ec
asti
n
g
m
eth
o
d
s
.
T
h
e
I
n
d
o
n
esian
s
to
ck
m
ar
k
et
is
r
en
o
wn
ed
f
o
r
its
v
o
latilit
y
,
with
p
r
ices
ch
a
n
g
es
f
r
eq
u
e
n
tly
b
y
th
e
p
r
ev
io
u
s
d
ay
’
s
clo
s
in
g
p
r
ice.
T
h
ese
cir
cu
m
s
tan
ce
s
m
ak
e
i
t
d
if
f
icu
lt
f
o
r
tr
ad
itio
n
al
tim
e
s
er
ies
f
o
r
ec
asti
n
g
ap
p
r
o
ac
h
es,
wh
ich
d
ep
e
n
d
o
n
s
tab
le
tr
en
d
s
to
p
e
r
f
o
r
m
.
Ov
er
th
e
s
h
o
r
t
tim
ef
r
am
e,
t
h
e
m
ar
k
et
p
e
r
f
o
r
m
s
lik
ewise
to
th
e
v
o
tin
g
to
o
l,
b
u
t
o
v
er
th
e
m
o
r
e
p
r
o
lo
n
g
ed
tim
ef
r
am
e,
it
is
b
eh
a
v
io
r
ally
s
im
ilar
to
t
h
e
weig
h
i
n
g
to
o
l
an
d
t
h
er
ef
o
r
e
a
s
co
p
e
e
x
is
ts
f
o
r
f
o
r
ec
asti
n
g
t
h
e
m
ar
k
et
s
h
if
ts
f
o
r
an
ex
ten
d
e
d
p
e
r
io
d
[
1
4
]
.
Ma
c
h
in
e
lear
n
in
g
h
as
b
ec
o
m
e
th
e
f
o
r
em
o
s
t
in
f
lu
en
tial
in
s
tr
u
m
en
t
en
co
m
p
ass
in
g
d
is
tin
ct
alg
o
r
it
h
m
s
f
o
r
ef
f
icien
tly
ev
o
lv
in
g
t
h
eir
v
er
s
io
n
o
n
a
s
p
ec
if
ic
is
s
u
e.
Ma
ch
in
e
lear
n
in
g
is
wid
ely
r
ec
o
g
n
ized
as
h
av
in
g
n
o
tewo
r
th
y
p
o
wer
s
in
r
ec
o
g
n
izin
g
ac
cu
r
a
te
in
f
o
r
m
atio
n
a
n
d
ca
p
t
u
r
in
g
tr
en
d
s
f
r
o
m
d
ata
s
ets
[
1
5
]
.
I
n
th
is
s
tu
d
y
,
th
r
ee
s
u
p
er
v
is
ed
m
ac
h
in
e
lea
r
n
in
g
a
lg
o
r
ith
m
s
:
RF
,
SVR
,
an
d
K
-
NN
ar
e
em
p
lo
y
e
d
to
f
o
r
ec
ast
th
e
clo
s
in
g
p
r
ices
o
f
s
to
ck
s
in
th
e
I
n
d
o
n
esian
m
ar
k
et.
T
h
ese
m
o
d
els
u
tili
ze
a
n
ewly
cr
ea
ted
s
et
o
f
v
ar
iab
les
d
e
r
i
v
ed
f
r
o
m
f
in
a
n
cial
d
atasets
,
in
clu
d
in
g
o
p
e
n
,
clo
s
e,
lo
w,
an
d
h
ig
h
p
r
ices
f
o
r
s
p
ec
if
ic
en
ter
p
r
is
es.
T
h
ese
in
d
ic
ato
r
s
ar
e
s
elec
ted
to
en
h
an
ce
th
e
m
o
d
els’
p
r
ec
is
io
n
in
f
o
r
ec
asti
n
g
t
h
e
f
o
llo
win
g
d
ay
’
s
clo
s
in
g
p
r
ices.
Am
o
n
g
all
n
o
n
-
p
ar
am
etr
ic
m
o
d
els,
KNN
is
a
p
o
p
u
lar
ap
p
r
o
ac
h
an
d
b
r
o
ad
ly
im
p
le
m
e
n
ted
in
n
u
m
er
o
u
s
p
r
ed
ictio
n
[
1
6
]
-
[
1
8
]
.
I
n
th
is
s
tr
ateg
y
,
th
e
n
u
m
b
er
o
f
n
ea
r
est
n
eig
h
b
o
r
s
(
K)
d
eter
m
in
es
th
e
m
o
d
el’
s
ab
ilit
y
to
ca
p
tu
r
e
r
elatio
n
s
h
ip
s
with
in
th
e
d
ata,
with
th
e
r
o
o
t
m
ea
n
s
q
u
a
r
e
er
r
o
r
(
R
MSE
)
s
er
v
in
g
as
a
k
ey
m
etr
ic
f
o
r
p
er
f
o
r
m
an
ce
ev
alu
atio
n
.
T
h
u
s
,
th
e
n
ea
r
est
n
eig
h
b
o
r
s
m
o
d
el
p
r
esen
ts
th
e
p
o
i
n
ts
o
f
d
ata
with
lo
w
R
MSE
an
d
lar
g
e
r
esem
b
lan
ce
.
T
h
is
ap
p
r
o
ac
h
p
r
o
v
id
es
ex
ce
llen
t
p
r
ed
ictiv
e
p
o
we
r
f
o
r
b
o
t
h
m
u
ltid
im
en
s
io
n
al
an
d
im
p
er
f
ec
t
d
ata.
K
-
N
N
s
ap
p
r
o
ac
h
is
id
ea
l
f
o
r
f
o
r
ec
asti
n
g
ag
ain
s
t
th
e
s
to
ck
m
a
r
k
et
[
1
9
]
,
[
2
0
]
.
Fu
r
th
er
m
o
r
e
,
SVR
is
al
s
o
o
n
e
o
f
t
h
e
m
ac
h
i
n
e
lear
n
in
g
alg
o
r
ith
m
s
th
at
co
n
s
id
er
ab
ly
ap
p
lied
f
o
r
f
o
r
ec
asti
n
g
b
o
th
th
e
v
al
u
es
o
f
s
to
ck
m
ar
k
et
in
d
ices
an
d
s
to
ck
p
r
ice
[
2
1
]
.
A
n
u
m
b
e
r
o
f
s
tu
d
ies
h
av
e
o
f
f
e
r
ed
to
u
tili
ze
RF
f
o
r
th
e
p
u
r
p
o
s
e
o
f
p
r
ed
i
ctio
n
.
RF
is
a
co
m
m
o
n
ly
u
s
ed
e
n
s
em
b
le
tech
n
i
q
u
e
th
at
p
er
f
o
r
m
s
th
e
task
o
f
class
if
icatio
n
an
d
r
eg
r
ess
io
n
.
T
h
is
in
s
tr
u
m
en
t
wo
r
k
s
b
y
b
u
ild
in
g
s
ev
er
al
ju
d
g
m
en
t
tr
ee
s
in
tr
ain
in
g
tim
e
th
at
p
r
o
d
u
ce
s
th
e
av
er
ag
e
r
e
g
r
ess
io
n
f
r
o
m
th
e
s
i
n
g
le
ju
d
g
em
en
t tr
ee
s
[
2
2
]
.
P
r
ev
io
u
s
s
tu
d
ies
u
s
in
g
v
ar
io
u
s
m
ac
h
in
e
lear
n
in
g
m
o
d
els
to
in
v
esti
g
ate
s
to
c
k
p
r
ice
p
r
ed
ictio
n
.
Hen
r
iq
u
e
et
al
.
p
r
ed
ict
s
to
ck
p
r
ices
f
o
r
lar
g
e
an
d
s
m
all
ca
p
italizatio
n
s
in
th
r
ee
d
if
f
er
en
t
m
ar
k
ets
u
s
in
g
SVR
[
2
3
]
.
Z
h
en
g
et
a
l.
[
2
4
]
em
p
lo
y
ed
RF
f
o
r
an
aly
ze
an
d
f
o
r
ec
as
t
th
e
US
Sto
ck
Ma
r
k
et
u
s
in
g
o
p
tim
al
p
ar
am
eter
s
.
Fu
r
th
er
m
o
r
e
,
Sar
ala
an
d
B
h
u
s
h
an
p
r
ed
ict
th
e
s
to
ck
p
r
ice
u
s
in
g
KNN
ap
p
r
o
ac
h
with
a
p
r
o
b
ab
ilis
tic
m
eth
o
d
[
2
5
]
.
Un
lik
e
p
r
ev
io
u
s
r
esear
ch
th
at
h
a
v
e
p
r
e
d
o
m
in
a
n
tly
f
o
cu
s
ed
o
n
d
e
v
elo
p
ed
m
ar
k
e
ts
o
r
s
in
g
le
-
m
o
d
e
l
ap
p
r
o
ac
h
es,
th
is
s
tu
d
y
u
s
es v
a
r
io
u
s
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
s
o
n
d
aily
h
is
to
r
ical
d
ata
to
c
o
m
p
ar
e
th
r
ee
s
to
ck
s
d
ata
in
I
n
d
o
n
esia,
wh
ich
is
an
em
er
g
in
g
co
u
n
tr
y
a
n
d
h
as
h
ig
h
v
o
latilit
y
.
T
h
is
s
tu
d
y
p
r
o
v
i
d
es
n
ew
in
s
ig
h
ts
f
o
r
in
v
esto
r
s
,
p
ar
tic
u
lar
ly
in
em
er
g
in
g
ec
o
n
o
m
ies lik
e
I
n
d
o
n
esia
,
r
eg
ar
d
in
g
th
e
u
s
e
o
f
m
ac
h
in
e
lear
n
in
g
to
p
r
ed
ict
s
to
ck
p
r
ices a
n
d
e
f
f
ec
tiv
ely
ad
ap
t to
s
u
ch
co
n
d
itio
n
s
.
T
h
e
ef
f
ec
tiv
en
ess
o
f
t
h
ese
m
o
d
els
is
ev
alu
ated
u
s
in
g
two
k
ey
m
etr
ics:
R
MSE
an
d
m
ea
n
ab
s
o
lu
te
er
r
o
r
(
MA
E
)
.
R
MSE
is
d
ef
in
ed
as
th
e
av
er
ag
e
v
alu
e
o
f
th
e
s
u
m
o
f
s
q
u
ar
ed
e
r
r
o
r
s
th
at
ca
n
b
e
u
tili
ze
d
to
m
ea
s
u
r
e
th
e
m
a
g
n
itu
d
e
o
f
t
h
e
er
r
o
r
v
alu
e
i
n
a
m
o
d
el.
MA
E
is
th
e
av
er
ag
e
v
alu
e
o
f
th
e
ab
s
o
lu
te
d
if
f
er
e
n
ce
b
etwe
en
p
r
ed
icted
a
n
d
ac
tu
a
l
d
ata
to
m
ea
s
u
r
e
th
e
m
ag
n
itu
d
e
o
f
a
m
o
d
el
er
r
o
r
with
o
u
t
co
n
s
id
er
i
n
g
its
d
ir
ec
tio
n
.
A
m
o
d
el
is
ac
cu
r
ate
if
it
h
as
lo
wer
R
MSE
an
d
M
AE
v
alu
es.
T
h
is
r
esear
c
h
u
tili
ze
s
d
aily
h
is
to
r
ical
d
ata
f
r
o
m
I
DX3
0
s
to
ck
s
f
o
r
an
aly
s
is
.
T
h
is
s
tu
d
y
co
n
tr
ib
u
t
es
to
ad
v
an
ce
m
en
t
o
f
f
in
a
n
cial
f
o
r
ec
asti
n
g
u
s
in
g
m
ac
h
in
e
lear
n
in
g
.
T
h
e
f
o
llo
wi
n
g
s
ec
tio
n
s
o
f
th
is
p
ap
er
ar
e
o
r
g
an
ized
as f
o
llo
ws:
th
e
m
eth
o
d
s
ec
tio
n
d
escr
ib
es
d
ata
h
is
to
r
ical
s
to
ck
p
r
ice
d
ata
co
llectio
n
,
d
ata
p
r
ep
r
o
ce
s
s
in
g
,
m
o
d
el
c
o
n
s
t
r
u
c
t
i
o
n
a
n
d
j
u
s
t
i
f
i
c
a
t
i
o
n
,
a
n
d
p
e
r
f
o
r
m
a
n
c
e
e
v
a
l
u
a
t
i
o
n
.
T
h
e
r
e
s
u
l
t
s
a
n
d
d
i
s
c
u
s
s
i
o
n
s
e
c
t
i
o
n
d
e
s
c
r
i
b
e
t
h
e
f
i
n
d
i
n
g
s
,
c
o
m
p
a
r
i
n
g
S
V
R
,
R
F
,
a
n
d
K
N
N
p
e
r
f
o
r
m
a
n
c
e
o
f
e
a
c
h
m
o
d
e
l
i
n
t
h
e
I
n
d
o
n
e
s
i
a
n
m
a
r
k
e
t
.
F
i
n
a
l
l
y
,
t
h
e
c
o
n
c
l
u
s
i
o
n
h
i
g
h
l
i
g
h
t
s
t
h
e
f
i
n
d
i
n
g
s
a
n
d
s
t
u
d
y
’
s
c
o
n
t
r
i
b
u
t
i
o
n
s
t
o
t
h
e
f
i
e
l
d
a
n
d
s
u
g
g
e
s
t
s
d
i
r
e
c
t
i
o
n
s
f
o
r
f
u
t
u
r
e
r
e
s
e
a
r
c
h
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
38
,
No
.
1
,
Ap
r
il
20
25
:
5
0
8
-
5
1
6
510
2.
M
E
T
H
O
D
Fig
u
r
e
1
s
h
o
ws
th
e
r
esear
c
h
s
tep
.
T
h
is
s
tu
d
y
u
tili
ze
d
d
aily
h
is
to
r
ical
s
to
ck
p
r
ices
f
r
o
m
Ma
r
ch
2
0
1
7
to
Feb
r
u
ar
y
2
0
2
0
.
T
h
e
r
esear
ch
co
llectin
g
h
is
to
r
ical
s
to
ck
p
r
ice
d
ata,
wh
ich
is
s
u
b
s
eq
u
e
n
tly
n
o
r
m
alize
d
a
n
d
d
iv
id
ed
in
to
tr
ai
n
in
g
an
d
test
in
g
d
atasets
.
Ma
c
h
in
e
lear
n
in
g
is
em
p
lo
y
ed
o
n
th
e
tr
ain
in
g
d
ata
to
tr
ain
th
e
m
o
d
el.
Su
b
s
eq
u
e
n
tly
,
a
p
r
ed
i
ctiv
e
m
o
d
el
is
co
n
s
tr
u
cted
u
s
in
g
RF
,
SVR
,
an
d
KNN.
T
h
e
test
in
g
d
ata
is
th
en
ev
alu
ated
u
s
in
g
ea
c
h
m
eth
o
d
to
o
b
tain
p
r
ed
ictio
n
r
esu
lts
.
T
h
e
p
r
ed
ictiv
e
o
u
tco
m
es
ar
e
co
m
p
ar
ed
with
t
h
e
ac
tu
al
r
esu
lts
,
an
d
ac
cu
r
ac
y
i
s
ca
lcu
lated
u
s
in
g
R
MSE
an
d
MA
E
.
Af
ter
o
b
tain
in
g
th
e
ac
cu
r
ac
y
r
esu
lts
f
o
r
ea
ch
m
eth
o
d
,
a
co
m
p
ar
is
o
n
is
m
ad
e
to
d
eter
m
in
e
th
e
b
est p
r
ed
ictiv
e
m
o
d
el.
Fig
u
r
e
1
.
R
esear
ch
s
tep
2
.
1
.
H
is
t
o
ric
a
l st
o
ck
price
da
t
a
co
llect
i
o
n
T
h
is
s
tu
d
y
u
tili
ze
d
a
d
ataset
co
m
p
r
is
in
g
d
aily
h
is
to
r
ical
s
to
ck
d
ata
to
talin
g
7
2
5
s
am
p
les
,
in
clu
d
in
g
th
r
ee
I
DX3
0
s
to
ck
s
:
PT.
B
an
k
C
en
tr
al
Asi
a
T
b
k
(
B
B
C
A)
,
PT.
Pak
u
wo
n
J
ati
T
b
k
(
PW
O
N)
,
an
d
PT.
Sar
an
a
Me
n
ar
a
Nu
s
an
tar
a
T
b
k
(
T
O
W
R
)
.
T
h
e
d
ataset
in
clu
d
es
k
e
y
v
ar
iab
les
s
u
c
h
as
Op
en
,
Hi
g
h
,
L
o
w,
an
d
C
lo
s
e
p
r
ices
with
ea
ch
v
ar
iab
le
r
ep
r
esen
tin
g
s
p
ec
if
ic
asp
ec
ts
o
f
d
aily
s
to
ck
tr
an
s
ac
tio
n
s
.
‘
Op
en
’
r
ef
er
s
to
th
e
p
r
ice
at
th
e
b
eg
in
n
in
g
o
f
t
h
e
tr
an
s
a
ctio
n
ac
tiv
ity
,
‘
Hig
h
’
an
d
‘
L
o
w’
in
d
icate
th
e
h
i
g
h
est
an
d
lo
west
p
r
ices
d
u
r
in
g
th
e
tr
an
s
ac
tio
n
ac
tiv
ity
o
n
a
g
iv
en
d
a
y
,
an
d
‘
C
lo
s
e’
is
d
ef
in
ed
as
th
e
last
ap
p
ea
r
i
n
g
s
to
ck
p
r
ice
b
ef
o
r
e
th
e
m
ar
k
et
clo
s
es
as
s
h
o
wn
in
Fi
g
u
r
e
2
.
T
h
e
d
ata
was
s
o
u
r
ce
d
f
r
o
m
in
v
esti
n
g
.
co
m
web
s
ite,
en
s
u
r
in
g
a
r
eliab
le
an
d
co
m
p
r
eh
e
n
s
iv
e
d
ataset
f
o
r
an
aly
s
is
.
T
h
is
s
tu
d
y
in
co
r
p
o
r
ated
a
d
ataset
o
f
h
is
to
r
ical
d
aily
s
to
ck
s
,
in
wh
ich
th
e
Op
en
,
Hig
h
,
an
d
L
o
w
p
r
ice
wer
e
lab
elled
as
in
d
ep
en
d
en
t
v
ar
iab
les,
wh
er
ea
s
th
e
C
lo
s
e
p
r
ice
was
th
e
d
ep
en
d
e
n
t v
ar
iab
le.
T
h
e
d
ata
a
n
aly
s
is
,
illu
s
tr
ated
in
Fig
u
r
e
2
(
a)
,
d
em
o
n
s
tr
ates th
at
B
B
C
A
e
x
h
ib
its
a
r
elativ
ely
s
tab
le
s
to
ck
f
lu
ctu
atio
n
,
d
em
o
n
s
tr
atin
g
a
b
u
llis
h
tr
en
d
o
v
e
r
tim
e,
as
o
p
p
o
s
ed
to
PW
ON
in
Fig
u
r
e
2
(
b
)
,
an
d
T
OW
R
in
Fig
u
r
e
2
(
c)
.
(
a)
(
b
)
(
c)
Fig
u
r
e
2
.
Sto
ck
p
r
ice
tr
e
n
d
s
:
(
a)
B
B
C
A,
(
b
)
PW
ON,
an
d
(
c)
T
OW
R
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
C
o
mp
a
r
in
g
ma
ch
in
e
lea
r
n
i
n
g
mo
d
els fo
r
i
n
d
o
n
esia
s
to
ck
ma
r
ke
t
… (
S
elly
A
n
a
s
ta
s
s
ia
A
mellia
K
h
a
r
is
)
511
2
.
2
.
Da
t
a
prepro
ce
s
s
ing
His
to
r
ical
s
to
ck
d
ata
f
r
eq
u
en
tl
y
m
an
if
ests
n
o
n
-
lin
ea
r
ch
ar
ac
t
er
is
tics
.
I
n
th
is
co
n
tex
t,
to
m
in
im
ize
th
e
er
r
o
r
r
ate
o
f
th
e
f
o
r
ec
ast
o
u
t
p
u
t,
d
ata
n
o
r
m
aliza
tio
n
is
n
e
ce
s
s
ar
y
.
No
r
m
aliza
tio
n
is
a
c
r
u
cial
p
r
e
p
r
o
ce
s
s
in
g
s
tep
to
e
n
s
u
r
e
t
h
e
c
o
m
p
ar
a
b
ilit
y
o
f
v
a
r
iab
les.
T
h
is
s
tu
d
y
e
m
p
lo
y
ed
z
-
s
co
r
e
n
o
r
m
aliza
tio
n
to
s
tan
d
ar
d
ize
th
e
d
ata,
en
s
u
r
in
g
all
v
a
r
iab
les
ar
e
o
n
a
co
m
p
a
r
ab
le
s
ca
le.
Z
-
s
c
o
r
e
n
o
r
m
aliza
tio
n
was
s
elec
ted
b
ec
au
s
e
it
is
less
s
en
s
itiv
e
to
o
u
tlier
s
a
n
d
b
ett
er
s
u
ited
f
o
r
alg
o
r
ith
m
s
lik
e
SVR
,
wh
ich
ass
u
m
e
th
at
th
e
d
ata
is
n
o
r
m
ally
d
is
tr
ib
u
ted
.
T
h
e
z
-
s
co
r
e
n
o
r
m
a
lizatio
n
as
s
h
o
wn
in
(
1
)
:
∗
=
−
(
1
)
wh
er
e
r
ep
r
esen
ts
th
e
o
b
s
er
v
ed
v
alu
e,
d
en
o
tes
th
e
m
ea
n
o
f
v
a
r
iab
le,
an
d
r
ep
r
esen
ts
t
h
e
s
tan
d
ar
d
d
ev
iatio
n
.
T
h
is
p
r
o
ce
s
s
is
ap
p
lied
u
n
if
o
r
m
ly
to
t
h
e
o
p
e
n
,
h
i
g
h
,
lo
w,
an
d
clo
s
e
p
r
ices a
cr
o
s
s
all
s
elec
ted
s
to
ck
s
.
T
h
e
n
o
r
m
alize
d
d
ata
was
th
en
s
p
lit
in
to
tr
ain
in
g
an
d
test
i
n
g
s
ets
b
ased
o
n
th
e
ch
r
o
n
o
l
o
g
ical
o
r
d
er
o
f
th
e
tr
an
s
ac
tio
n
p
er
io
d
.
T
h
e
tr
ain
i
n
g
d
ata
in
clu
d
ed
7
0
5
s
am
p
le
s
f
r
o
m
Ma
r
ch
1
,
2
0
1
7
to
J
an
u
ar
y
3
1
,
2
0
2
0
.
T
h
e
test
in
g
d
ata
co
m
p
r
is
ed
2
0
s
am
p
les
f
r
o
m
Feb
r
u
a
r
y
2
0
2
0
,
in
ten
d
ed
to
ev
alu
ate
t
h
e
p
r
ed
ictiv
e
m
o
d
el
b
y
co
m
p
ar
in
g
th
e
p
r
ed
icted
o
u
tp
u
ts
with
th
e
ac
tu
al
v
alu
es to
ca
l
cu
late
th
e
er
r
o
r
r
ate.
2
.
3
.
M
o
del
co
ns
t
ruct
io
n a
nd
j
us
t
if
ica
t
io
n
T
h
is
r
esear
ch
em
p
l
o
y
ed
th
r
e
e
m
ac
h
in
e
lea
r
n
in
g
alg
o
r
ith
m
s
to
g
en
e
r
ate
f
o
r
ec
asti
n
g
m
o
d
els:
RF
,
SVR
,
KNN
r
eg
r
ess
io
n
.
T
h
ese
m
o
d
els
wer
e
s
elec
ted
b
ec
au
s
e
th
ey
o
f
f
er
a
b
alan
ce
b
etwe
en
co
m
p
le
x
ity
an
d
in
ter
p
r
etab
ilit
y
,
m
ak
i
n
g
th
em
id
ea
l
f
o
r
an
aly
zin
g
th
e
v
o
latile
an
d
m
u
ltifa
ce
ted
n
at
u
r
e
o
f
t
h
e
I
n
d
o
n
esian
s
to
ck
m
ar
k
et.
2
.
3
.
1
.
Ra
nd
o
m
f
o
re
s
t
RF
d
is
p
lay
s
n
u
m
er
o
u
s
g
r
o
win
g
tr
ee
s
f
o
r
m
in
g
a
f
o
r
est,
wh
er
e
ea
ch
tr
ee
is
b
u
ilt u
s
in
g
a
r
an
d
o
m
s
u
b
s
et
o
f
th
e
d
ata
an
d
f
ea
tu
r
es
,
p
r
o
v
id
in
g
r
o
b
u
s
t
p
r
e
d
ictio
n
s
th
r
o
u
g
h
th
e
a
g
g
r
e
g
atio
n
o
f
m
u
ltip
le
m
o
d
els.
B
y
av
er
ag
in
g
ea
ch
tr
ee
’
s
o
u
tp
u
t,
th
is
en
s
em
b
le
tech
n
iq
u
e
im
p
r
o
v
es
p
r
ed
ictio
n
ac
cu
r
ac
y
wh
ile
lo
wer
in
g
t
h
e
v
ar
ian
ce
o
f
ten
s
ee
n
in
s
in
g
le
d
ec
is
io
n
tr
ee
s
[
1
8
]
.
Fu
r
th
er
m
o
r
e,
t
h
e
p
r
e
d
ictio
n
o
u
tco
m
es
f
r
o
m
ea
ch
r
e
g
r
ess
io
n
tr
ee
ar
e
av
er
ag
e
d
,
p
r
o
d
u
cin
g
th
e
R
F
p
r
ed
ictio
n
o
u
tp
u
t.
T
h
e
R
F
alg
o
r
ith
m
u
s
es
b
o
o
ts
tr
ap
p
in
g
o
r
r
an
d
o
m
r
esam
p
lin
g
o
f
d
ata
to
g
e
n
er
at
e
b
o
o
ts
tr
ap
s
am
p
les,
ea
ch
u
s
ed
to
co
n
s
tr
u
ct
a
r
eg
r
ess
io
n
tr
ee
.
T
h
e
p
r
e
d
icted
va
lu
es
g
en
er
ated
b
y
th
e
R
F
ap
p
r
o
ac
h
ca
n
b
e
ex
p
r
ess
ed
th
r
o
u
g
h
(
2
)
wh
er
e
is
th
e
o
u
tp
u
t
o
f
th
e
p
r
ed
ictio
n
f
r
o
m
th
e
ℎ
r
eg
r
ess
io
n
tr
ee
an
d
is
th
e
n
u
m
b
e
r
o
f
r
eg
r
ess
io
n
tr
e
es.
=
1
∑
=
1
(
2
)
2
.
3
.
2
.
Su
pp
o
rt
v
ec
t
o
r
re
g
re
s
s
io
n
SVR
is
an
ap
p
r
o
ac
h
s
tem
m
in
g
f
r
o
m
s
u
p
p
o
r
t
v
ec
t
o
r
m
ac
h
in
es
(
SVM)
u
s
ed
t
o
r
e
g
r
ess
io
n
p
r
o
b
lem
s
.
T
h
is
ap
p
r
o
ac
h
g
en
e
r
ates
r
ea
l
o
r
c
o
n
tin
u
o
u
s
-
v
alu
e
d
o
u
tp
u
ts
with
th
e
aim
o
f
f
i
n
d
in
g
a
f
u
n
c
tio
n
as
a
s
ep
ar
atin
g
lin
e
(
h
y
p
er
p
la
n
e)
in
th
e
f
o
r
m
o
f
a
r
eg
r
ess
io
n
f
u
n
ctio
n
,
im
p
l
em
en
tin
g
t
h
e
co
n
ce
p
t
o
f
-
in
s
en
s
itiv
e
ar
ea
.
T
h
e
er
r
o
r
to
ler
a
n
ce
b
etwe
en
p
r
e
d
icted
v
alu
es
an
d
ac
tu
al
d
ata
ca
n
b
e
s
p
ec
if
ied
b
y
a
v
alu
e
o
f
.
SVR
h
as
p
r
o
v
en
to
d
eliv
er
ex
ce
llen
t
p
er
f
o
r
m
a
n
ce
as
it
ad
d
r
ess
es
th
e
is
s
u
e
o
f
o
v
er
f
itti
n
g
i
n
d
ata
[2
6
]
.
T
h
is
m
eth
o
d
m
ec
h
an
is
m
in
v
o
lv
es
s
ee
k
in
g
th
e
m
ax
im
u
m
d
is
tan
ce
b
etwe
en
two
class
es
to
o
b
tain
th
e
o
p
tim
al
h
y
p
er
p
lan
e
th
at
s
ep
ar
ates
th
e
two
class
e
s
[2
7
]
.
I
n
th
is
co
n
tex
t,
th
e
lin
ea
r
m
o
d
el
to
b
e
u
s
ed
as
th
e
r
eg
r
ess
io
n
f
u
n
ctio
n
in
SVM
to
d
eter
m
in
e
t
h
e
h
y
p
er
p
lan
e
h
a
s
a
g
en
e
r
al
f
o
r
m
,
as
o
u
tlin
e
d
in
(
3
)
wh
e
r
e
∗
as
th
e
v
ec
to
r
o
f
in
d
ep
en
d
en
t
v
ar
iab
les
in
th
e
tr
ain
in
g
d
ata,
as
th
e
we
ig
h
t
p
ar
am
eter
s
in
th
e
m
o
d
el,
∅
(
∗
)
as
th
e
f
ea
tu
r
e
tr
an
s
f
o
r
m
atio
n
f
u
n
ctio
n
o
n
th
e
tr
ain
in
g
d
ata,
a
n
d
as a
b
ias ter
m
(
in
th
e
f
o
r
m
o
f
a
co
n
s
tan
t)
.
(
∗
)
=
∅
(
∗
)
+
(
3
)
2
.
3
.
3
.
K
-
nea
re
s
t
neig
hb
o
r
re
g
re
s
s
io
n
KNN
is
o
n
e
o
f
th
e
ap
p
r
o
ac
h
es
u
s
ed
f
o
r
p
r
ed
ictiv
e
a
n
aly
s
is
o
n
a
d
ataset
b
ased
o
n
tr
ai
n
in
g
d
ata
ex
tr
ac
ted
f
r
o
m
its
n
ea
r
est
n
e
ig
h
b
o
r
s
with
in
th
e
d
ataset.
T
h
ese
n
ea
r
est
n
ei
g
h
b
o
r
s
ar
e
u
s
ed
to
p
r
ed
ict
th
e
r
esp
o
n
s
e
v
ar
ia
b
le
v
alu
es
f
o
r
test
ex
am
p
les.
T
h
e
h
y
p
er
p
a
r
a
m
eter
d
eter
m
in
es
h
o
w
m
an
y
n
ei
g
h
b
o
r
s
ar
e
in
clu
d
ed
w
h
en
p
r
ed
ictin
g
v
al
u
es
f
o
r
t
h
e
test
in
g
d
ata.
T
h
e
b
est
v
alu
e
f
o
r
ca
n
b
e
d
eter
m
in
ed
b
y
p
ar
a
m
eter
o
p
tim
izatio
n
.
On
e
c
o
m
m
o
n
m
eth
o
d
f
o
r
m
ea
s
u
r
in
g
th
e
p
r
o
x
im
ity
o
r
d
is
tan
ce
b
etwe
e
n
n
eig
h
b
o
r
s
is
th
e
E
u
clid
ea
n
d
is
tan
ce
,
ca
lcu
lated
as
s
h
o
wn
in
(
4
)
wh
e
r
e
(
,
∗
)
as
E
u
clid
ea
n
d
is
tan
ce
,
wh
er
e
an
d
∗
as
th
e
in
d
ep
en
d
en
t v
ar
ia
b
le
o
f
t
h
e
test
in
g
an
d
tr
ai
n
in
g
d
ata
p
o
in
ts
,
r
esp
ec
tiv
ely
.
(
,
∗
)
=
√
(
∑
(
−
∗
)
2
)
=
1
(
4
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
38
,
No
.
1
,
Ap
r
il
20
25
:
5
0
8
-
5
1
6
512
2
.
4
.
P
er
f
o
r
m
a
nce
ev
a
lua
t
io
n
2
.
4
.
1
.
Ro
o
t
m
ea
n sq
ua
re
d e
rr
o
r
(
RM
SE
)
T
h
e
R
MSE
is
em
p
lo
y
ed
to
ass
ess
th
e
er
r
o
r
esti
m
atio
n
o
f
th
e
p
er
f
o
r
m
an
ce
g
e
n
er
ated
b
y
th
e
R
F,
SV
R
,
an
d
KNN
alg
o
r
ith
m
s
.
I
n
ad
d
itio
n
,
th
ese
esti
m
atio
n
s
ar
e
c
o
m
p
ar
ed
,
th
e
m
ag
n
itu
d
e
o
f
e
r
r
o
r
s
p
r
o
d
u
ce
d
i
n
co
m
p
ar
is
o
n
to
th
e
ac
t
u
al
d
at
a
is
ca
lcu
lated
.
A
lo
wer
R
M
SE
v
alu
e
s
h
o
ws
h
ig
h
er
ac
cu
r
ac
y
in
th
e
m
o
d
el
’
s
esti
m
atio
n
s
.
R
MSE
m
ea
s
u
r
es
th
e
ex
ten
t
to
wh
ich
th
e
p
r
ed
ic
ted
v
alu
es
f
r
o
m
a
m
o
d
el
a
p
p
r
o
x
im
ate
th
e
ac
tu
a
l
v
alu
es,
an
d
a
lo
wer
v
al
u
e
in
d
i
ca
tes th
at
th
e
m
o
d
el
p
r
ed
ictio
n
s
ar
e
m
o
r
e
ac
cu
r
ate.
T
h
e
R
MSE
ca
n
b
e
ex
p
r
ess
es
u
s
in
g
(
5
)
wh
er
e
∗
r
ep
r
esen
ts
th
e
ac
tu
al
v
alu
e
in
th
e
ℎ
d
ata
p
o
in
t,
r
ep
r
esen
ts
th
e
p
r
ed
icted
v
al
u
e
in
th
e
ℎ
d
ata
p
o
in
t,
is
th
e
v
ar
iab
le
o
f
t
h
e
ℎ
d
ata
p
o
in
t,
an
d
is
th
e
to
tal
n
u
m
b
er
o
f
d
ata
s
a
m
p
les.
=
√
1
∑
(
∗
−
)
2
=
1
(
5
)
2
.
4
.
2
.
M
ea
n
a
bs
o
lute
er
ro
r
MA
E
is
an
ap
p
r
o
ac
h
u
s
ed
to
m
ea
s
u
r
e
th
e
ac
cu
r
ac
y
lev
el
o
f
a
p
r
ed
ictiv
e
m
o
d
el.
I
t
r
e
p
r
esen
ts
th
e
av
er
ag
e
a
b
s
o
lu
te
er
r
o
r
b
etwe
en
th
e
p
r
ed
icted
v
alu
es
g
en
er
ated
b
y
t
h
e
R
F,
SVR
,
an
d
KNN
an
d
th
e
ac
tu
a
l
v
alu
es.
A
lo
wer
MA
E
in
d
icate
s
h
ig
h
er
ac
cu
r
ac
y
in
th
e
p
r
ed
ictiv
e
m
o
d
el.
MA
E
ca
n
b
e
co
m
p
u
ted
u
tili
zin
g
(
6
)
∗
r
ep
r
esen
ts
th
e
ac
tu
al
v
alu
e
in
th
e
ℎ
d
ata
p
o
in
t,
r
ep
r
esen
ts
th
e
p
r
ed
icted
v
alu
e
in
th
e
ℎ
d
ata
p
o
in
t,
i
s
th
e
v
ar
iab
le
o
f
th
e
ℎ
d
ata
p
o
i
n
t,
an
d
is
th
e
to
tal
n
u
m
b
er
o
f
d
ata
s
am
p
les.
=
1
∑
|
∗
−
|
=
1
(
6
)
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
R
F,
SV
R
,
an
d
KNN
wer
e
em
p
lo
y
ed
to
f
o
r
ec
ast
th
e
s
to
ck
p
r
i
ce
tr
en
d
s
o
f
th
r
ee
I
DX3
0
s
to
c
k
s
:
B
B
C
A
,
PW
ON,
an
d
T
O
W
R
.
Su
b
s
eq
u
en
tly
,
th
e
f
o
r
ec
asted
p
r
ices
o
b
tain
ed
f
r
o
m
th
e
th
r
ee
m
eth
o
d
s
wer
e
co
m
p
ar
ed
with
th
e
ac
tu
al
d
ata.
B
a
s
ed
o
n
th
e
r
esu
lts
o
b
tain
ed
f
r
o
m
th
e
s
im
u
latio
n
u
s
in
g
th
e
R
Stu
d
io
ap
p
licatio
n
,
th
e
f
ir
s
t
o
u
tp
u
t
co
m
p
r
is
es
th
e
clo
s
in
g
s
to
ck
p
r
ice
p
r
ed
ictio
n
s
g
en
e
r
ated
o
n
th
e
test
in
g
d
ata
in
T
ab
les
1
-
3
.
T
ab
le
1
s
h
o
ws th
e
p
r
ed
icted
o
u
tco
m
es
f
o
r
B
B
C
A
s
to
ck
,
T
ab
le
2
f
o
r
PW
ON
s
to
ck
,
an
d
T
ab
le
3
f
o
r
T
OW
R
s
to
ck
.
T
ab
le
1
.
Pre
d
icted
o
u
tco
m
es
o
f
R
F,
SVR
,
an
d
KNN
o
n
B
B
C
A
s
to
ck
No
D
a
t
e
A
c
t
u
a
l
p
r
i
c
e
F
o
r
e
c
a
st
i
n
g
p
r
i
c
e
RF
S
V
R
K
N
N
1
0
3
/
0
2
/
2
0
2
0
3
2
.
2
0
0
,
0
0
3
2
.
6
7
9
,
6
5
3
2
.
3
2
5
,
4
3
3
1
.
9
4
0
,
0
0
2
0
4
/
0
2
/
2
0
2
0
3
3
.
0
0
0
,
0
0
3
3
.
0
6
2
,
9
0
3
2
.
7
7
4
,
7
1
3
3
.
2
9
5
,
0
0
3
0
5
/
0
2
/
2
0
2
0
3
3
.
6
5
0
,
0
0
3
3
.
3
5
8
,
5
9
3
3
.
4
4
3
,
9
8
3
3
.
6
9
0
,
0
0
⋮
⋮
⋮
⋮
⋮
⋮
20
2
8
/
0
2
/
2
0
2
0
3
1
.
4
5
0
,
0
0
3
0
.
6
5
4
,
5
8
3
0
.
7
4
4
,
4
5
3
0
.
7
2
5
,
0
0
T
ab
le
2
.
Pre
d
icted
o
u
tco
m
es
o
f
R
F,
SVR
,
an
d
KNN
o
n
PW
ON
s
to
ck
No
D
a
t
e
A
c
t
u
a
l
p
r
i
c
e
F
o
r
e
c
a
st
i
n
g
p
r
i
c
e
RF
S
V
R
K
N
N
1
0
3
/
0
2
/
2
0
2
0
5
1
0
,
0
0
0
0
5
1
4
,
1
7
4
2
5
2
1
,
1
9
0
1
5
1
5
,
0
0
0
0
2
0
4
/
0
2
/
2
0
2
0
5
2
5
,
0
0
0
0
5
1
4
,
1
7
4
2
5
2
1
,
1
9
0
1
5
1
5
,
0
0
0
0
3
0
5
/
0
2
/
2
0
2
0
5
2
5
,
0
0
0
0
5
1
8
,
0
6
0
2
5
1
9
,
0
7
6
1
5
2
2
,
5
0
0
0
⋮
⋮
⋮
⋮
⋮
⋮
20
2
8
/
0
2
/
2
0
2
0
5
3
0
,
0
0
0
0
5
2
6
,
5
1
2
0
5
2
4
,
1
1
1
3
5
2
5
,
7
1
4
3
T
ab
le
3
.
Pre
d
icted
o
u
tco
m
es
o
f
R
F,
SVR
,
an
d
KNN
o
n
T
OW
R
s
to
ck
No
D
a
t
e
A
c
t
u
a
l
p
r
i
c
e
F
o
r
e
c
a
st
i
n
g
p
r
i
c
e
RF
S
V
R
K
N
N
1
0
3
/
0
2
/
2
0
2
0
8
3
0
,
0
0
0
0
8
3
7
,
6
7
6
6
8
3
4
,
9
4
7
3
8
3
7
,
6
0
0
0
2
0
4
/
0
2
/
2
0
2
0
8
5
0
,
0
0
0
0
8
3
4
,
4
1
8
9
8
3
3
,
9
1
6
6
8
3
0
,
1
4
2
9
3
0
5
/
0
2
/
2
0
2
0
8
5
5
,
0
0
0
0
8
4
6
,
8
6
3
3
8
4
6
,
5
2
1
4
8
4
7
,
4
0
0
0
⋮
⋮
⋮
⋮
⋮
⋮
20
2
8
/
0
2
/
2
0
2
0
8
0
5
,
0
0
0
0
8
0
5
,
4
7
9
1
7
9
5
,
6
2
4
7
8
0
4
,
6
6
6
7
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
C
o
mp
a
r
in
g
ma
ch
in
e
lea
r
n
i
n
g
mo
d
els fo
r
i
n
d
o
n
esia
s
to
ck
ma
r
ke
t
… (
S
elly
A
n
a
s
ta
s
s
ia
A
mellia
K
h
a
r
is
)
513
T
h
e
s
ec
o
n
d
r
esu
lt
was
a
g
r
a
p
h
ical
r
e
p
r
esen
tatio
n
o
f
th
e
s
to
ck
p
r
ice
ac
co
r
d
in
g
to
th
e
test
in
g
d
ata
g
en
er
ated
f
r
o
m
th
e
p
r
ed
ictio
n
r
esu
lts
o
f
th
e
cl
o
s
in
g
s
to
ck
p
r
ice.
I
n
Fig
u
r
e
3
th
e
b
lack
lin
e
r
ep
r
esen
ted
th
e
tr
en
d
f
o
r
m
e
d
b
ased
o
n
ac
tu
al
d
ata,
th
e
g
r
ee
n
lin
e
illu
s
tr
ated
th
e
tr
en
d
b
ased
o
n
th
e
R
F
ap
p
r
o
ac
h
,
th
e
b
lu
e
lin
e
in
d
icate
d
th
e
t
r
en
d
ac
co
r
d
i
n
g
to
SVR
,
an
d
th
e
r
ed
lin
e
d
en
o
ted
th
e
tr
en
d
b
ased
o
n
th
e
KN
N.
T
h
e
s
to
ck
p
r
ice
co
m
p
ar
is
o
n
o
f
B
B
C
A,
PW
ON
,
an
d
T
OW
R
wer
e
s
eq
u
e
n
tially
d
e
p
icted
i
n
Fig
u
r
es
3
(
a
)
-
3
(
c
)
.
I
n
e
v
alu
atin
g
th
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
p
r
ed
ictio
n
m
o
d
els,
R
MSE
an
d
MA
E
w
er
e
ca
lcu
lated
.
A
m
o
d
el
was
m
o
r
e
ac
c
u
r
ate
if
it
h
ad
lo
wer
R
MSE
an
d
MA
E
v
alu
es
co
m
p
ar
e
d
to
o
th
er
m
o
d
els.
T
ab
le
4
r
e
p
r
esen
ted
th
at
th
e
lo
west
R
MSE
v
alu
es
f
o
r
B
B
C
A,
P
W
ON,
an
d
T
W
OR
wer
e
o
b
tain
ed
wh
en
u
tili
zin
g
t
h
e
SVR
m
eth
o
d
.
Similar
ly
,
th
e
ca
lcu
latio
n
o
f
MA
E
v
alu
es in
T
ab
le
5
,
th
e
l
o
west r
esu
lts
wer
e
o
b
tain
ed
w
h
en
u
s
in
g
th
e
SVR
ap
p
r
o
ac
h
.
(
a)
(
b
)
(
c)
Fig
u
r
e
3
.
C
o
m
p
a
r
is
o
n
o
f
tr
en
d
p
r
ed
ictio
n
s
:
(
a)
B
B
C
A,
(
b
)
PW
ON,
an
d
(
c)
T
W
OR
s
to
ck
s
T
ab
le
4
.
C
o
m
p
a
r
is
o
n
o
f
R
MSE
v
alu
es
A
l
g
o
r
i
t
h
m
F
o
r
e
c
a
st
i
n
g
p
r
i
c
e
B
B
C
A
P
W
O
N
TO
W
R
S
V
R
0
.
0
4
7
9
3
5
0
.
1
0
6
0
9
1
0
.
1
5
1
4
0
6
RF
0
.
0
6
8
0
1
2
0
.
1
2
0
7
5
7
0
.
2
0
9
9
7
7
K
N
N
0
.
0
6
9
8
1
1
0
.
1
2
5
4
5
8
0
.
2
3
8
4
9
8
T
ab
le
5
.
C
o
m
p
a
r
is
o
n
o
f
MA
E
v
alu
es
A
l
g
o
r
i
t
h
m
F
o
r
e
c
a
st
i
n
g
p
r
i
c
e
B
B
C
A
P
W
O
N
TO
W
R
S
V
R
0
.
0
3
5
1
5
5
0
.
0
8
4
8
9
5
0
.
1
3
7
8
0
8
RF
0
.
0
5
3
4
6
5
0
.
1
0
1
7
3
7
0
.
1
7
6
3
5
3
K
N
N
0
.
0
5
2
1
2
8
0
.
1
0
3
8
1
1
0
.
1
7
5
1
5
7
T
h
e
co
m
p
ar
is
o
n
o
f
R
MSE
v
al
u
es
b
etwe
en
th
e
R
F,
SVR
,
an
d
KNN
m
eth
o
d
s
was
g
i
v
en
in
Fig
u
r
e
4
.
T
h
e
SVR
m
eth
o
d
g
en
er
ate
d
R
MSE
v
alu
es
o
f
4
.
7
9
%
f
o
r
B
B
C
A
s
to
ck
s
,
1
0
.
6
1
%
f
o
r
P
W
ON
s
to
ck
s
,
an
d
1
5
.
1
4
%
f
o
r
T
OW
R
s
to
ck
s
.
Me
an
wh
ile,
th
e
R
F
ap
p
r
o
ac
h
p
r
o
d
u
ce
d
an
R
MSE
v
alu
e
o
f
6
.
8
0
%
f
o
r
B
B
C
A
s
h
ar
es,
1
2
.
0
8
%
f
o
r
PW
ON
s
h
ar
es,
an
d
2
1
%
f
o
r
T
OW
R
s
h
ar
es.
Fu
r
th
er
m
o
r
e,
th
e
KNN
ap
p
r
o
ac
h
g
en
er
ated
R
MSE
v
alu
es
o
f
6
.
9
8
%
f
o
r
B
B
C
A
s
to
ck
s
,
1
2
.
5
5
%
f
o
r
PW
ON
s
to
ck
s
,
an
d
2
3
.
8
5
%
f
o
r
T
OW
R
s
to
ck
s
.
T
h
ese
R
MSE
v
alu
es
p
r
o
v
id
ed
a
q
u
an
titativ
e
m
ea
s
u
r
em
en
t
o
f
f
o
r
ec
ast
ac
cu
r
ac
y
f
o
r
ea
ch
m
et
h
o
d
o
n
ea
ch
s
to
ck
.
R
MSE
r
ep
r
esen
ted
th
e
e
x
ten
t
to
wh
ich
th
e
p
r
ed
icted
v
alu
e
s
d
ev
iated
f
r
o
m
t
h
e
ac
tu
al
v
al
u
es.
L
o
wer
R
MSE
v
a
l
u
e
s
t
y
p
i
c
a
ll
y
r
e
p
r
e
s
e
n
t
e
d
a
c
l
o
s
e
r
m
a
t
c
h
b
e
t
we
e
n
p
r
e
d
i
c
t
ed
a
n
d
a
c
t
u
a
l
v
a
l
u
e
s
.
I
n
F
i
g
u
r
e
4
,
i
t
c
a
n
b
e
n
o
t
i
c
e
d
t
h
a
t
t
h
e
SVR
a
l
g
o
r
i
t
h
m
p
r
o
v
i
d
e
d
t
h
e
b
e
s
t
f
o
r
e
c
as
t
o
u
t
c
o
m
es
co
m
p
a
r
e
d
t
o
R
F
a
n
d
KN
N
f
r
o
m
t
h
e
R
MS
E
v
a
l
u
e
.
T
h
e
co
m
p
ar
is
o
n
o
f
MA
E
v
alu
es
am
o
n
g
th
e
R
F,
SV
R
,
an
d
KNN
m
eth
o
d
was
illu
s
tr
ated
in
Fig
u
r
e
5
.
T
h
e
SVR
m
eth
o
d
r
esu
lted
M
AE
v
alu
es
o
f
3
.
5
2
%
f
o
r
B
B
C
A
s
to
ck
,
8
.
4
9
%
f
o
r
PW
ON
s
t
o
ck
,
an
d
1
3
.
7
8
%
f
o
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
38
,
No
.
1
,
Ap
r
il
20
25
:
5
0
8
-
5
1
6
514
T
OW
R
s
to
ck
.
I
n
c
o
n
tr
ast,
th
e
R
F
ap
p
r
o
ac
h
g
en
e
r
ated
MA
E
v
alu
es
o
f
5
.
3
5
%
f
o
r
B
B
C
A
s
to
ck
,
1
0
.
1
7
%
f
o
r
PW
ON
s
to
ck
,
an
d
1
7
.
6
4
%
f
o
r
T
OW
R
s
to
ck
.
Ad
d
itio
n
ally
,
th
e
KNN
m
eth
o
d
r
esu
lted
in
MA
E
v
alu
es
o
f
5
.
2
1
%
f
o
r
B
B
C
A
s
to
ck
,
1
0
.
3
8
%
f
o
r
PW
ON
s
to
ck
,
an
d
1
7
.
5
2
%
f
o
r
T
OW
R
s
to
ck
.
MA
E
was
a
m
etr
ic
th
at
m
ea
s
u
r
es
th
e
av
er
ag
e
m
a
g
n
it
u
d
e
o
f
e
r
r
o
r
s
b
etwe
en
p
r
ed
ic
ted
an
d
ac
tu
al
v
al
u
es.
T
h
e
l
o
wer
MA
E
v
alu
es
d
em
o
n
s
tr
ated
a
b
etter
f
it
an
d
h
ig
h
er
ac
c
u
r
ac
y
in
t
h
e
p
r
e
d
ictio
n
s
m
ad
e
b
y
th
e
r
esp
ec
tiv
e
m
eth
o
d
s
.
I
n
Fig
u
r
e
5
,
it
ca
n
b
e
o
b
s
er
v
ed
th
at
th
e
SVR
alg
o
r
ith
m
y
ield
ed
th
e
b
est
p
r
ed
ictio
n
o
u
tp
u
ts
co
m
p
a
r
ed
to
R
F
an
d
KNN
f
r
o
m
MA
E
v
alu
es.
Fig
u
r
e
4
.
C
o
m
p
a
r
is
o
n
g
r
ap
h
o
f
R
MSE
v
alu
es
Fig
u
r
e
5
.
C
o
m
p
a
r
is
o
n
g
r
ap
h
o
f
MA
E
v
alu
es
T
h
e
r
esu
lts
in
d
icate
t
h
at
th
e
SVR
m
o
d
el
p
er
f
o
r
m
ed
b
etter
in
p
r
ed
ictin
g
s
to
ck
p
r
ices
th
an
R
F
an
d
KNN
f
o
r
all
th
r
ee
o
f
th
e
ev
alu
ated
eq
u
ities
,
as
s
ee
n
b
y
th
e
s
m
aller
R
MSE
an
d
MA
E
v
alu
es.
T
h
e
b
ette
r
p
er
f
o
r
m
an
ce
o
f
th
e
SVR
m
o
d
el
is
co
n
s
is
ten
t
with
p
r
ev
io
u
s
r
esear
ch
th
at
in
d
icate
s
SVR
ca
n
ef
f
ec
tiv
ely
ca
p
tu
r
e
in
tr
icate
,
n
o
n
-
lin
ea
r
r
elatio
n
s
h
ip
s
in
f
in
an
cial
d
ata,
esp
ec
ially
in
h
i
g
h
ly
v
o
latile
m
ar
k
ets
[2
8
]
.
T
h
e
lo
wer
er
r
o
r
r
ates
ass
o
ciate
d
with
SV
R
ca
n
b
e
attr
ib
u
ted
t
o
it
s
ab
ilit
y
to
m
o
d
el
th
e
d
ata
with
an
ap
p
r
o
p
r
iate
k
er
n
el
f
u
n
ctio
n
,
o
p
tim
izin
g
th
e
h
y
p
er
p
ar
am
eter
s
to
s
u
it
th
e
s
p
ec
if
ic
ch
ar
ac
ter
is
tics
o
f
th
e
s
to
ck
m
ar
k
et
b
ein
g
an
aly
ze
d
.
T
h
is
is
p
ar
tic
u
lar
ly
r
elev
an
t
in
t
h
e
co
n
tex
t
o
f
t
h
e
I
n
d
o
n
esian
s
to
ck
m
ar
k
et,
w
h
er
e
v
o
latilit
y
an
d
r
ap
id
ch
an
g
es
in
s
to
ck
p
r
ices
ar
e
co
m
m
o
n
.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
R
F,
wh
ile
s
tr
o
n
g
,
was
s
lig
h
tly
lo
wer
th
an
SVR
,
lik
ely
d
u
e
to
its
s
en
s
itiv
ity
to
th
e
d
ep
th
an
d
n
u
m
b
er
o
f
tr
ee
s
u
s
ed
in
th
e
en
s
em
b
le,
wh
ich
m
ay
n
o
t
h
a
v
e
b
ee
n
o
p
tim
ized
f
o
r
th
e
p
ar
ticu
lar
d
ata
p
atter
n
s
in
th
is
s
tu
d
y
.
Ho
wev
er
,
KNN’
s
lo
wer
p
er
f
o
r
m
an
ce
m
a
y
b
e
d
u
e
t
o
its
r
elian
ce
o
n
lo
ca
l
d
ata
p
o
in
ts
,
wh
ich
m
ig
h
t
n
o
t
ca
p
tu
r
e
b
r
o
ad
e
r
m
a
r
k
et
t
r
en
d
s
as
ef
f
ec
tiv
ely
as
th
e
o
th
e
r
m
o
d
els.
T
h
is
s
tu
d
y
’
s
f
in
d
in
g
was
co
n
s
is
ten
t
with
p
r
e
v
io
u
s
r
esear
ch
th
at
h
ig
h
lig
h
t
th
e
ef
f
icac
y
o
f
SVR
in
s
to
ck
p
r
ice
f
o
r
ec
asti
n
g
[
29
]
.
Ho
wev
er
,
i
t’
s
cr
u
cial
to
r
ec
o
g
n
ize
t
h
at
I
n
d
o
n
esia
h
a
s
u
n
iq
u
e
m
ar
k
et
cir
cu
m
s
tan
ce
s
,
s
u
ch
g
r
ea
ter
v
o
latilit
y
an
d
less
m
ar
k
et
m
atu
r
ity
,
wh
ic
h
m
ak
e
th
ese
r
esu
lts
p
ar
ticu
lar
ly
v
alu
ab
le.
Stu
d
ies
co
n
d
u
cted
in
m
o
r
e
s
tab
le
m
ar
k
ets
m
ay
f
in
d
th
at
m
o
d
el
s
u
ch
as
R
F
o
u
tp
er
f
o
r
m
SV
R
.
Nev
er
th
eless
,
in
th
e
I
n
d
o
n
esian
co
n
tex
t
am
p
lifie
s
th
e
b
en
ef
its
o
f
n
o
n
-
lin
ea
r
,
k
e
r
n
el
-
b
as
ed
ap
p
r
o
ac
h
es
lik
e
SVR
ar
e
m
o
r
e
ad
v
an
tag
eo
u
s
.
T
h
is
im
p
lies
th
at
e
v
en
wh
ile
S
VR
’
s
s
u
p
er
io
r
ity
h
as
b
ee
n
wel
l
s
tu
d
ied
,
its
u
s
e
in
em
er
g
in
g
m
ar
k
ets
p
r
o
v
id
es
a
d
d
itio
n
al
i
n
s
ig
h
ts
in
to
its
r
o
b
u
s
tn
ess
u
n
d
er
d
if
f
er
en
t
ec
o
n
o
m
ic
co
n
d
itio
n
s
.
T
h
is
s
tu
d
y
lim
ited
th
e
f
in
d
in
g
s
’
g
e
n
er
aliza
b
ilit
y
b
y
c
o
n
ce
n
tr
atin
g
ju
s
t
o
n
th
e
I
n
d
o
n
esian
s
to
ck
m
ar
k
et,
e
v
en
if
i
t
o
f
f
er
ed
i
n
s
ig
h
tf
u
l
in
f
o
r
m
atio
n
.
Fu
tu
r
e
r
esear
ch
s
h
o
u
ld
i
n
v
esti
g
ate
th
e
u
s
e
o
f
th
ese
m
o
d
els
in
o
th
er
d
e
v
elo
p
in
g
ec
o
n
o
m
ies an
d
th
r
o
u
g
h
o
u
t v
a
r
io
u
s
tim
e
p
er
io
d
s
to
v
alid
ate
t
h
e
g
en
er
aliza
b
ilit
y
o
f
th
ese
f
in
d
in
g
s
.
4.
CO
NCLU
SI
O
N
T
h
is
r
esear
ch
in
v
esti
g
ated
th
e
co
m
p
ar
is
o
n
o
f
th
r
ee
a
p
p
r
o
ac
h
es
f
o
r
f
o
r
ec
asti
n
g
s
to
ck
p
r
ice
tr
en
d
s
in
clu
d
in
g
RF
,
SVR
,
an
d
KNN
with
in
th
e
v
o
latile
I
n
d
o
n
esian
m
ar
k
et.
T
h
e
an
aly
s
is
u
tili
ze
d
d
aily
h
is
to
r
ical
s
to
ck
d
ata
f
r
o
m
th
r
ee
I
DX3
0
-
lis
ted
co
m
p
an
ies:
PT.
B
an
k
C
en
tr
al
Asi
a
T
b
k
(
B
B
C
A)
,
PT.
Pak
u
wo
n
J
ati
T
b
k
(
PW
ON)
,
an
d
PT.
Sar
an
a
Me
n
ar
a
Nu
s
an
tar
a
T
b
k
(
T
OW
R
)
.
T
h
e
ev
al
u
at
io
n
m
etr
ics
em
p
lo
y
ed
wer
e
R
MSE
an
d
MA
E
.
T
h
e
f
in
d
in
g
s
r
ev
ea
led
th
at
th
e
SVR
m
eth
o
d
ac
h
iev
es
th
e
b
est
p
er
f
o
r
m
a
n
ce
,
s
h
o
wed
lo
wer
R
MSE
an
d
MA
E
v
alu
es
th
a
n
th
o
s
e
o
f
R
F
an
d
KNN.
T
h
ese
r
esu
lts
s
u
g
g
est
th
at
SVR
ef
f
ec
tiv
e
to
ca
p
tu
r
e
co
m
p
le
x
R
M
S
E
v
a
l
u
e
s
M
A
E
v
a
l
u
es
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
C
o
mp
a
r
in
g
ma
ch
in
e
lea
r
n
i
n
g
mo
d
els fo
r
i
n
d
o
n
esia
s
to
ck
ma
r
ke
t
… (
S
elly
A
n
a
s
ta
s
s
ia
A
mellia
K
h
a
r
is
)
515
an
d
n
o
n
-
lin
ea
r
r
elatio
n
s
h
ip
s
.
T
h
e
s
tu
d
y
ad
d
r
ess
es
a
g
ap
in
th
e
liter
atu
r
e
b
y
f
o
cu
s
in
g
o
n
a
n
em
er
g
in
g
m
ar
k
et,
o
f
f
er
in
g
n
ew
in
s
ig
h
ts
in
to
th
e
ap
p
licab
ilit
y
o
f
m
ac
h
in
e
le
ar
n
in
g
m
o
d
els
b
ey
o
n
d
d
ev
el
o
p
ed
m
a
r
k
ets.
T
h
e
im
p
licatio
n
s
ex
ten
d
to
in
v
esto
r
s
an
d
f
i
n
an
cial
an
al
y
s
ts
,
wh
o
m
ay
b
en
e
f
it
f
r
o
m
in
teg
r
atin
g
n
o
n
-
lin
ea
r
,
k
e
r
n
el
-
b
ased
ap
p
r
o
ac
h
es
lik
e
SVR
i
n
to
th
eir
p
r
ed
ictiv
e
s
tr
ateg
ies.
Fu
tu
r
e
s
tu
d
ies
s
h
o
u
ld
in
v
esti
g
ate
s
im
ilar
m
o
d
els
in
m
o
r
e
em
e
r
g
in
g
m
ar
k
ets,
im
p
r
o
v
e
m
o
d
el
p
a
r
am
eter
s
,
an
d
c
o
n
s
id
er
a
d
d
itio
n
al
f
in
a
n
cial
in
d
icato
r
s
to
en
h
an
ce
p
r
e
d
ictiv
e
ac
cu
r
ac
y
.
T
h
is
s
tu
d
y
co
n
tr
ib
u
tes
to
th
e
s
ch
o
lar
ly
d
is
co
u
r
s
e
o
n
m
ac
h
in
e
lear
n
in
g
in
f
in
an
cial
f
o
r
ec
asti
n
g
an
d
o
f
f
er
s
p
r
ag
m
atic
in
s
tr
u
m
en
ts
to
e
n
h
an
ce
in
v
estme
n
t stra
teg
ies in
e
m
er
g
in
g
m
ar
k
ets.
RE
F
E
R
E
NC
E
S
[
1
]
M
.
G
ö
ç
k
e
n
,
M
.
Ö
z
ç
a
l
i
c
i
,
A
.
B
o
r
u
,
a
n
d
A
.
T.
D
o
s
d
o
ʇ
r
u
,
“
I
n
t
e
g
r
a
t
i
n
g
me
t
a
h
e
u
r
i
s
t
i
c
s
a
n
d
A
r
t
i
f
i
c
i
a
l
N
e
u
r
a
l
N
e
t
w
o
r
k
s
f
o
r
i
m
p
r
o
v
e
d
st
o
c
k
p
r
i
c
e
p
r
e
d
i
c
t
i
o
n
,
”
Ex
p
e
r
t
S
y
s
t
e
m
s w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
4
4
,
p
p
.
3
2
0
–
3
3
1
,
F
e
b
.
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
1
5
.
0
9
.
0
2
9
.
[
2
]
A
.
K
.
N
a
ssi
r
t
o
u
ssi
,
S
.
A
g
h
a
b
o
z
o
r
g
i
,
T.
Y
i
n
g
W
a
h
,
a
n
d
D
.
C
.
L.
N
g
o
,
“
T
e
x
t
m
i
n
i
n
g
f
o
r
mar
k
e
t
p
r
e
d
i
c
t
i
o
n
:
A
sy
st
e
ma
t
i
c
r
e
v
i
e
w
,
”
Ex
p
e
rt
S
y
st
e
m
s w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
4
1
,
n
o
.
1
6
,
p
p
.
7
6
5
3
–
7
6
7
0
,
N
o
v
.
2
0
1
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
1
4
.
0
6
.
0
0
9
.
[
3
]
A
.
A
.
R
o
d
r
i
g
u
e
s
a
n
d
S
.
Ll
e
o
,
“
C
o
mb
i
n
i
n
g
st
a
n
d
a
r
d
a
n
d
b
e
h
a
v
i
o
r
a
l
p
o
r
t
f
o
l
i
o
t
h
e
o
r
i
e
s:
a
p
r
a
c
t
i
c
a
l
a
n
d
i
n
t
u
i
t
i
v
e
a
p
p
r
o
a
c
h
,
”
Q
u
a
n
t
i
t
a
t
i
v
e
F
i
n
a
n
c
e
,
v
o
l
.
1
8
,
n
o
.
5
,
p
p
.
7
0
7
–
7
1
7
,
D
e
c
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
8
0
/
1
4
6
9
7
6
8
8
.
2
0
1
7
.
1
4
0
1
2
2
5
.
[
4
]
Z.
Q
.
Ji
a
n
g
e
t
a
l
.
,
“
S
h
o
r
t
t
e
r
m
p
r
e
d
i
c
t
i
o
n
o
f
e
x
t
r
e
m
e
r
e
t
u
r
n
s
b
a
se
d
o
n
t
h
e
r
e
c
u
r
r
e
n
c
e
i
n
t
e
r
v
a
l
a
n
a
l
y
si
s
,
”
Q
u
a
n
t
i
t
a
t
i
v
e
F
i
n
a
n
c
e
,
v
o
l
.
1
8
,
n
o
.
3
,
p
p
.
3
5
3
–
3
7
0
,
O
c
t
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
8
0
/
1
4
6
9
7
6
8
8
.
2
0
1
7
.
1
3
7
3
8
4
3
.
[
5
]
T.
F
i
sc
h
e
r
a
n
d
C
.
K
r
a
u
ss,
“
D
e
e
p
l
e
a
r
n
i
n
g
w
i
t
h
l
o
n
g
s
h
o
r
t
-
t
e
r
m
mem
o
r
y
n
e
t
w
o
r
k
s
f
o
r
f
i
n
a
n
c
i
a
l
mar
k
e
t
p
r
e
d
i
c
t
i
o
n
s
,
”
E
u
r
o
p
e
a
n
J
o
u
rn
a
l
o
f
O
p
e
r
a
t
i
o
n
a
l
Re
se
a
rc
h
,
v
o
l
.
2
7
0
,
n
o
.
2
,
p
p
.
6
5
4
–
6
6
9
,
O
c
t
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
j
o
r
.
2
0
1
7
.
1
1
.
0
5
4
.
[
6
]
Y
.
S
.
A
b
u
-
M
o
st
a
f
a
a
n
d
A
.
F
.
A
t
i
y
a
,
“
I
n
t
r
o
d
u
c
t
i
o
n
t
o
f
i
n
a
n
c
i
a
l
f
o
r
e
c
a
s
t
i
n
g
,
”
A
p
p
l
i
e
d
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
6
,
n
o
.
3
,
p
p
.
2
0
5
–
2
1
3
,
J
u
l
.
1
9
9
6
,
d
o
i
:
1
0
.
1
0
0
7
/
B
F
0
0
1
2
6
6
2
6
.
[
7
]
S
.
A
sa
d
i
,
E.
H
a
d
a
v
a
n
d
i
,
F
.
M
e
h
ma
n
p
a
z
i
r
,
a
n
d
M
.
M
.
N
a
k
h
o
st
i
n
,
“
H
y
b
r
i
d
i
z
a
t
i
o
n
o
f
e
v
o
l
u
t
i
o
n
a
r
y
Le
v
e
n
b
e
r
g
-
M
a
r
q
u
a
r
d
t
n
e
u
r
a
l
n
e
t
w
o
r
k
s
a
n
d
d
a
t
a
p
r
e
-
p
r
o
c
e
ss
i
n
g
f
o
r
st
o
c
k
m
a
r
k
e
t
p
r
e
d
i
c
t
i
o
n
,
”
K
n
o
w
l
e
d
g
e
-
Ba
se
d
S
y
s
t
e
m
s
,
v
o
l
.
3
5
,
p
p
.
2
4
5
–
2
5
8
,
N
o
v
.
2
0
1
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
k
n
o
sy
s
.
2
0
1
2
.
0
5
.
0
0
3
.
[
8
]
S
.
A
k
h
t
e
r
a
n
d
M
.
A
.
M
i
s
i
r
,
“
C
a
p
i
t
a
l
mark
e
t
s
e
f
f
i
c
i
e
n
c
y
:
Ev
i
d
e
n
c
e
f
r
o
m
t
h
e
e
mer
g
i
n
g
c
a
p
i
t
a
l
m
a
r
k
e
t
w
i
t
h
p
a
r
t
i
c
u
l
a
r
r
e
f
e
r
e
n
c
e
t
o
D
h
a
k
a
s
t
o
c
k
e
x
c
h
a
n
g
e
,
”
S
o
u
t
h
As
i
a
n
J
o
u
rn
a
l
o
f
M
a
n
a
g
e
m
e
n
t
,
v
o
l
.
1
2
,
n
o
.
3
,
p
p
.
3
5
–
5
1
,
2
0
0
5
.
[
9
]
K
.
M
i
a
o
,
F
.
C
h
e
n
,
a
n
d
Z.
Z
h
a
o
,
“
S
t
o
c
k
p
r
i
c
e
f
o
r
e
c
a
st
b
a
se
d
o
n
b
a
c
t
e
r
i
a
l
c
o
l
o
n
y
R
B
F
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
J
o
u
rn
a
l
o
f
Q
i
n
g
d
a
o
U
n
i
v
e
rsi
t
y
,
v
o
l
.
2
,
p
p
.
2
1
0
–
2
3
0
,
2
0
0
7
.
[
1
0
]
J.
Le
h
o
c
z
k
y
a
n
d
M
.
S
c
h
e
r
v
i
sh
,
“
O
v
e
r
v
i
e
w
a
n
d
h
i
st
o
r
y
o
f
st
a
t
i
st
i
c
s
f
o
r
e
q
u
i
t
y
m
a
r
k
e
t
s
,
”
A
n
n
u
a
l
Re
v
i
e
w
o
f
S
t
a
t
i
st
i
c
s
a
n
d
I
t
s
Ap
p
l
i
c
a
t
i
o
n
,
v
o
l
.
5
,
n
o
.
1
,
p
p
.
2
6
5
–
2
8
8
,
M
a
r
.
2
0
1
8
,
d
o
i
:
1
0
.
1
1
4
6
/
a
n
n
u
r
e
v
-
st
a
t
i
s
t
i
c
s
-
0
3
1
0
1
7
-
1
0
0
5
1
8
.
[
1
1
]
A
.
A
a
l
i
-
B
u
j
a
r
i
,
F
.
V
e
n
e
g
a
s
-
M
a
r
t
í
n
e
z
,
a
n
d
G
.
P
é
r
e
z
-
L
e
c
h
u
g
a
,
“
I
mp
a
c
t
o
d
e
l
a
c
a
p
i
t
a
l
i
z
a
c
i
ó
n
b
u
r
sá
t
i
l
y
d
e
l
sp
r
e
a
d
b
a
n
c
a
r
i
o
so
b
r
e
e
l
c
r
e
c
i
mi
e
n
t
o
y
e
l
d
e
s
a
r
r
o
l
l
o
e
n
A
méric
a
La
t
i
n
a
:
u
n
a
e
s
t
i
m
a
c
i
ó
n
d
e
d
a
t
o
s
d
e
p
a
n
e
l
c
o
n
M
G
M
-
si
s
t
e
m
a
,
”
C
o
n
t
a
d
u
r
i
a
y
Ad
m
i
n
i
s
t
r
a
c
i
o
n
,
v
o
l
.
6
2
,
n
o
.
5
,
p
p
.
1
4
2
7
–
1
4
4
1
,
D
e
c
.
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
y
a
.
2
0
1
7
.
0
9
.
0
0
5
.
[
1
2
]
M
.
P
.
N
a
e
i
n
i
,
H
.
T
a
r
e
m
i
a
n
,
a
n
d
H
.
B
.
H
a
s
h
e
mi
,
“
S
t
o
c
k
mark
e
t
v
a
l
u
e
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
i
n
2
0
1
0
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
I
n
f
o
rm
a
t
i
o
n
S
y
st
e
m
s
a
n
d
I
n
d
u
st
r
i
a
l
M
a
n
a
g
e
m
e
n
t
A
p
p
l
i
c
a
t
i
o
n
s,
C
I
S
I
M
2
0
1
0
,
O
c
t
.
2
0
1
0
,
p
p
.
1
3
2
–
1
3
6
,
d
o
i
:
1
0
.
1
1
0
9
/
C
I
S
I
M
.
2
0
1
0
.
5
6
4
3
6
7
5
.
[
1
3
]
B
.
Q
i
a
n
a
n
d
K
.
R
a
sh
e
e
d
,
“
S
t
o
c
k
mar
k
e
t
p
r
e
d
i
c
t
i
o
n
w
i
t
h
m
u
l
t
i
p
l
e
c
l
a
ssi
f
i
e
r
s,
”
Ap
p
l
i
e
d
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
2
6
,
n
o
.
1
,
p
p
.
2
5
–
3
3
,
N
o
v
.
2
0
0
7
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
0
4
8
9
-
0
0
6
-
0
0
0
1
-
7.
[
1
4
]
D
.
S
h
a
h
,
H
.
I
sah
,
a
n
d
F
.
Z
u
l
k
e
r
n
i
n
e
,
“
S
t
o
c
k
mar
k
e
t
a
n
a
l
y
si
s
:
A
r
e
v
i
e
w
a
n
d
t
a
x
o
n
o
my
o
f
p
r
e
d
i
c
t
i
o
n
t
e
c
h
n
i
q
u
e
s,”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Fi
n
a
n
c
i
a
l
S
t
u
d
i
e
s
,
v
o
l
.
7
,
n
o
.
2
,
p
.
2
6
,
M
a
y
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
i
j
f
s7
0
2
0
0
2
6
.
[
1
5
]
E.
S
.
O
l
i
v
a
s,
“
H
a
n
d
b
o
o
k
o
f
r
e
s
e
a
r
c
h
o
n
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
l
i
c
a
t
i
o
n
s
a
n
d
t
r
e
n
d
s:
A
l
g
o
r
i
t
h
ms
,
me
t
h
o
d
s,
a
n
d
t
e
c
h
n
i
q
u
e
s,”
H
e
r
sh
e
y
,
P
A
,
U
S
A
:
I
G
I
G
l
o
b
a
l
,
2
0
0
9
.
[
1
6
]
R
.
E.
M
c
R
o
b
e
r
t
s,
“
Es
t
i
m
a
t
i
n
g
f
o
r
e
st
a
t
t
r
i
b
u
t
e
p
a
r
a
me
t
e
r
s
f
o
r
sm
a
l
l
a
r
e
a
s
u
s
i
n
g
n
e
a
r
e
st
n
e
i
g
h
b
o
r
s
t
e
c
h
n
i
q
u
e
s
,
”
F
o
r
e
st
E
c
o
l
o
g
y
a
n
d
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
2
7
2
,
p
p
.
3
–
1
2
,
M
a
y
2
0
1
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
f
o
r
e
c
o
.
2
0
1
1
.
0
6
.
0
3
9
.
[
1
7
]
S
.
A
.
A
.
K
h
a
r
i
s,
G
.
F
.
H
e
r
t
o
n
o
,
S
.
R
.
I
r
a
w
a
n
,
E
.
W
a
h
y
u
n
i
n
g
r
u
m,
a
n
d
Y
u
mi
a
t
i
,
“
S
t
u
d
e
n
t
s’
su
c
c
e
ss
p
r
e
d
i
c
t
i
o
n
b
a
se
d
o
n
t
h
e
f
u
z
z
y
K
-
n
e
a
r
e
s
t
n
e
i
g
h
b
o
r
me
t
h
o
d
i
n
U
n
i
v
e
r
si
t
a
s
Te
r
b
u
k
a
,
”
i
n
E
d
u
c
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
i
n
t
h
e
N
e
w
N
o
rm
a
l
:
N
o
w
a
n
d
Be
y
o
n
d
,
R
o
u
t
l
e
d
g
e
,
2
0
2
3
,
p
p
.
2
1
2
–
2
1
8
.
[
1
8
]
S
.
A
.
A
.
K
h
a
r
i
s
a
n
d
A
.
H
.
A
.
Zi
l
i
,
“
P
r
e
d
i
c
t
i
n
g
l
i
f
e
e
x
p
e
c
t
a
n
c
y
o
f
l
u
n
g
c
a
n
c
e
r
p
a
t
i
e
n
t
s
a
f
t
e
r
t
h
o
r
a
c
i
c
s
u
r
g
e
r
y
u
si
n
g
S
M
O
T
E
a
n
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s,”
J
u
rn
a
l
N
a
t
u
ra
l
,
v
o
l
.
2
3
,
n
o
.
3
,
p
p
.
1
5
2
–
1
6
1
,
O
c
t
.
2
0
2
3
,
d
o
i
:
1
0
.
2
4
8
1
5
/
j
n
.
v
2
3
i
3
.
2
9
1
4
4
.
[
1
9
]
R
.
E.
M
c
R
o
b
e
r
t
s,
“
D
i
a
g
n
o
st
i
c
t
o
o
l
s
f
o
r
n
e
a
r
e
st
n
e
i
g
h
b
o
r
s
t
e
c
h
n
i
q
u
e
s
w
h
e
n
u
se
d
w
i
t
h
s
a
t
e
l
l
i
t
e
i
ma
g
e
r
y
,
”
R
e
m
o
t
e
S
e
n
si
n
g
o
f
En
v
i
r
o
n
m
e
n
t
,
v
o
l
.
1
1
3
,
n
o
.
3
,
p
p
.
4
8
9
–
4
9
9
,
M
a
r
.
2
0
0
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
s
e
.
2
0
0
8
.
0
6
.
0
1
5
.
[
2
0
]
S
.
M
a
g
n
u
ss
e
n
,
E.
T
o
mp
p
o
,
a
n
d
R
.
E.
M
c
R
o
b
e
r
t
s,
“
A
m
o
d
e
l
-
a
ss
i
st
e
d
k
-
n
e
a
r
e
st
n
e
i
g
h
b
o
u
r
a
p
p
r
o
a
c
h
t
o
r
e
mo
v
e
e
x
t
r
a
p
o
l
a
t
i
o
n
b
i
a
s,
”
S
c
a
n
d
i
n
a
v
i
a
n
J
o
u
r
n
a
l
o
f
F
o
res
t
R
e
se
a
rch
,
v
o
l
.
2
5
,
n
o
.
2
,
p
p
.
1
7
4
–
1
8
4
,
M
a
r
.
2
0
1
0
,
d
o
i
:
1
0
.
1
0
8
0
/
0
2
8
2
7
5
8
1
0
0
3
6
6
7
3
4
8
.
[
2
1
]
J.
P
a
t
e
l
,
S
.
S
h
a
h
,
P
.
T
h
a
k
k
a
r
,
a
n
d
K
.
K
o
t
e
c
h
a
,
“
P
r
e
d
i
c
t
i
n
g
st
o
c
k
mark
e
t
i
n
d
e
x
u
s
i
n
g
f
u
s
i
o
n
o
f
mac
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
,
”
Ex
p
e
rt
S
y
st
e
m
s w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
4
2
,
n
o
.
4
,
p
p
.
2
1
6
2
–
2
1
7
2
,
M
a
r
.
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
1
4
.
1
0
.
0
3
1
.
[
2
2
]
M
.
K
u
mar a
n
d
M
.
T
h
e
n
m
o
z
h
i
,
“
F
o
r
e
c
a
st
i
n
g
st
o
c
k
i
n
d
e
x
m
o
v
e
me
n
t
:
a
c
o
mp
a
r
i
so
n
o
f
su
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
s
a
n
d
r
a
n
d
o
m f
o
r
e
s
t
,
”
S
S
RN
El
e
c
t
ro
n
i
c
J
o
u
r
n
a
l
,
2
0
1
1
,
d
o
i
:
1
0
.
2
1
3
9
/
ssr
n
.
8
7
6
5
4
4
.
[
2
3
]
B
.
M
.
H
e
n
r
i
q
u
e
,
V
.
A
.
S
o
b
r
e
i
r
o
,
a
n
d
H
.
K
i
m
u
r
a
,
“
S
t
o
c
k
p
r
i
c
e
p
r
e
d
i
c
t
i
o
n
u
si
n
g
su
p
p
o
r
t
v
e
c
t
o
r
r
e
g
r
e
s
si
o
n
o
n
d
a
i
l
y
a
n
d
u
p
t
o
t
h
e
mi
n
u
t
e
p
r
i
c
e
s,
”
J
o
u
rn
a
l
o
f
Fi
n
a
n
c
e
a
n
d
D
a
t
a
S
c
i
e
n
c
e
,
v
o
l
.
4
,
n
o
.
3
,
p
p
.
1
8
3
–
2
0
1
,
S
e
p
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
f
d
s.
2
0
1
8
.
0
4
.
0
0
3
.
[
2
4
]
J.
Z
h
e
n
g
,
D
.
X
i
n
,
Q
.
C
h
e
n
g
,
M
.
Ti
a
n
,
a
n
d
L.
Y
a
n
g
,
“
T
h
e
r
a
n
d
o
m
f
o
r
e
st
m
o
d
e
l
f
o
r
a
n
a
l
y
z
i
n
g
a
n
d
f
o
r
e
c
a
s
t
i
n
g
t
h
e
U
S
st
o
c
k
mar
k
e
t
u
n
d
e
r
t
h
e
b
a
c
k
g
r
o
u
n
d
o
f
s
mart
f
i
n
a
n
c
e
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
3
rd
I
n
t
e
r
n
a
t
i
o
n
a
l
A
c
a
d
e
m
i
c
C
o
n
f
e
re
n
c
e
o
n
B
l
o
c
k
c
h
a
i
n
,
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
S
m
a
rt
Fi
n
a
n
c
e
(
I
C
BI
S
2
0
2
4
)
,
A
t
l
a
n
t
i
s
P
r
e
ss I
n
t
e
r
n
a
t
i
o
n
a
l
B
V
,
2
0
2
4
,
p
p
.
8
2
–
9
0
.
[
2
5
]
V
.
S
a
r
a
l
a
a
n
d
G
.
N
.
V
.
P
.
B
h
u
s
h
a
n
,
“
S
t
o
c
k
m
a
r
k
e
t
t
r
e
n
d
p
r
e
d
i
c
t
i
o
n
u
si
n
g
K
-
n
e
a
r
e
st
n
e
i
g
h
b
o
r
(
K
N
N
)
a
l
g
o
r
i
t
h
m,
”
J
o
u
r
n
a
l
o
f
En
g
i
n
e
e
ri
n
g
S
c
i
e
n
c
e
s
,
v
o
l
.
1
3
,
n
o
.
8
,
2
0
2
2
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
w
w
w
.
j
e
sp
u
b
l
i
c
a
t
i
o
n
.
c
o
m
.
[2
6
]
A
.
J.
S
mo
l
a
a
n
d
B
.
S
c
h
ö
l
k
o
p
f
,
“
A
t
u
t
o
r
i
a
l
o
n
su
p
p
o
r
t
v
e
c
t
o
r
r
e
g
r
e
ss
i
o
n
,
”
S
t
a
t
i
st
i
c
s
a
n
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
4
,
n
o
.
3
,
p
p
.
1
9
9
–
2
2
2
,
A
u
g
.
2
0
0
4
,
d
o
i
:
1
0
.
1
0
2
3
/
B
:
S
TC
O
.
0
0
0
0
0
3
5
3
0
1
.
4
9
5
4
9
.
8
8
.
[2
7
]
Z.
R
u
s
t
a
m
a
n
d
S
.
A
.
A
.
K
h
a
r
i
s
,
“
M
u
l
t
i
c
l
a
ss
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
n
b
r
a
i
n
c
a
n
c
e
r
w
i
t
h
m
u
l
t
i
p
l
e
su
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
a
n
d
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
b
a
s
e
d
o
n
k
e
r
n
e
l
f
u
n
c
t
i
o
n
,
”
i
n
AI
P
C
o
n
f
e
r
e
n
c
e
Pr
o
c
e
e
d
i
n
g
s
,
2
0
1
8
,
v
o
l
.
2
0
2
3
,
p
.
2
0
2
3
3
,
d
o
i
:
1
0
.
1
0
6
3
/
1
.
5
0
6
4
2
3
0
.
[2
8
]
X
.
Y
a
n
,
“
R
e
s
e
a
r
c
h
o
n
f
i
n
a
n
c
i
a
l
f
i
e
l
d
i
n
t
e
g
r
a
t
i
n
g
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
:
a
p
p
l
i
c
a
t
i
o
n
b
a
si
s
,
c
a
s
e
a
n
a
l
y
s
i
s,
a
n
d
S
V
R
m
o
d
e
l
-
b
a
s
e
d
o
v
e
r
n
i
g
h
t
,
”
Ap
p
l
i
e
d
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
3
7
,
n
o
.
1
,
J
u
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
8
0
/
0
8
8
3
9
5
1
4
.
2
0
2
3
.
2
2
2
2
2
5
8
.
[
29
]
A
.
A
mp
o
u
n
t
o
l
a
s
,
“
En
h
a
n
c
i
n
g
f
o
r
e
c
a
st
i
n
g
a
c
c
u
r
a
c
y
i
n
c
o
mm
o
d
i
t
y
a
n
d
f
i
n
a
n
c
i
a
l
m
a
r
k
e
t
s
:
i
n
s
i
g
h
t
s
f
r
o
m
G
A
R
C
H
a
n
d
S
V
R
mo
d
e
l
s
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Fi
n
a
n
c
i
a
l
S
t
u
d
i
e
s
,
v
o
l
.
1
2
,
n
o
.
3
,
p
.
5
9
,
J
u
n
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
i
j
f
s
1
2
0
3
0
0
5
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
38
,
No
.
1
,
Ap
r
il
20
25
:
5
0
8
-
5
1
6
516
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
S
e
ll
y
An
a
sta
ss
ia
A
m
e
ll
ia
K
h
a
r
i
s
is
As
sista
n
t
P
ro
fe
ss
o
r
a
t
Un
i
v
e
rsitas
Terb
u
k
a
,
In
d
o
n
e
sia
.
S
e
ll
y
'
s
a
c
a
d
e
m
ic
c
a
re
e
r
is
n
o
t
o
n
l
y
re
flec
ted
i
n
h
e
r
a
c
a
d
e
m
ic
a
c
h
iev
e
m
e
n
ts,
b
u
t
a
lso
in
h
e
r
c
o
n
tri
b
u
ti
o
n
t
o
re
se
a
rc
h
a
n
d
d
e
v
e
lo
p
m
e
n
t
i
n
th
e
f
ield
s
o
f
M
a
th
e
m
a
ti
c
s
a
n
d
M
a
t
h
e
m
a
ti
c
s
Ed
u
c
a
ti
o
n
.
As
a
d
e
d
ica
ted
a
c
a
d
e
m
ic,
sh
e
h
a
s
p
u
b
li
sh
e
d
n
u
m
e
ro
u
s
sc
ien
ti
fic
a
rti
c
les
a
n
d
is
a
re
sp
e
c
ted
c
o
n
tr
ib
u
to
r
i
n
t
h
e
sc
ien
t
ifi
c
c
o
m
m
u
n
i
ty
.
Be
h
i
n
d
h
e
r
a
c
a
d
e
m
ic
a
c
h
iev
e
m
e
n
ts,
S
e
ll
y
i
s
a
lso
k
n
o
wn
a
s
a
g
o
o
d
m
e
n
t
o
r
f
o
r
stu
d
e
n
ts
a
n
d
c
o
ll
e
a
g
u
e
s.
S
h
e
o
ft
e
n
p
ro
v
i
d
e
s
e
n
c
o
u
ra
g
e
m
e
n
t
a
n
d
g
u
i
d
a
n
c
e
t
o
t
h
o
se
wh
o
a
re
tr
y
in
g
t
o
a
c
h
ie
v
e
su
c
c
e
ss
in
a
c
a
d
e
m
ics
.
Wi
th
h
e
r
p
a
ss
io
n
f
o
r
k
n
o
wle
d
g
e
a
n
d
d
e
d
ica
ti
o
n
to
sc
ie
n
c
e
,
S
e
ll
y
c
o
n
ti
n
u
e
s
to
m
o
v
e
fo
r
wa
rd
in
h
e
r
a
c
a
d
e
m
ic
c
a
r
e
e
r.
He
r
li
fe
is p
ro
o
f
th
a
t
w
it
h
p
e
rsiste
n
c
e
a
n
d
h
a
rd
wo
r
k
,
a
n
y
a
c
a
d
e
m
ic d
re
a
m
a
n
d
p
u
r
p
o
se
s c
a
n
b
e
re
a
li
z
e
d
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
se
ll
y
@e
c
a
m
p
u
s.u
t.
a
c
.
id
.
Ar
m
a
n
H
a
q
q
i
Ann
a
Zil
i
re
c
e
iv
e
d
h
is
b
a
c
h
e
l
o
r'
s
a
n
d
m
a
ste
r'
s
d
e
g
re
e
s
in
M
a
th
e
m
a
ti
c
s fro
m
th
e
Un
iv
e
rsit
y
o
f
In
d
o
n
e
sia
.
Cu
rre
n
tl
y
h
e
se
rv
e
s
a
s a
n
As
sista
n
t
P
ro
fe
ss
o
r
a
t
th
e
De
p
a
rtme
n
t
o
f
M
a
t
h
e
m
a
ti
c
s,
Un
iv
e
rsity
o
f
I
n
d
o
n
e
sia
(UI).
He
h
a
s
e
x
p
e
rien
c
e
tes
ti
n
g
a
n
d
g
u
i
d
in
g
th
e
fin
a
l
a
ss
ig
n
m
e
n
t
writi
n
g
o
f
m
o
re
th
a
n
3
0
stu
d
e
n
ts.
His
a
c
a
d
e
m
ic
c
a
re
e
r
is
n
o
t
o
n
l
y
re
flec
ted
in
h
is
a
c
a
d
e
m
ic
a
c
h
iev
e
m
e
n
ts,
b
u
t
a
lso
i
n
h
is
c
o
n
tri
b
u
t
io
n
to
re
se
a
rc
h
a
n
d
d
e
v
e
lo
p
m
e
n
t
i
n
th
e
fiel
d
s
o
f
A
p
p
li
e
d
M
a
t
h
e
m
a
ti
c
s
a
n
d
Ac
t
u
a
ri
a
l
S
c
ien
c
e
.
As
a
d
e
d
ica
ted
a
c
a
d
e
m
ic,
h
e
h
a
s
p
u
b
li
sh
e
d
n
u
m
e
ro
u
s
sc
ien
ti
f
ic
a
rti
c
les
a
n
d
is
a
re
sp
e
c
ted
c
o
n
tr
ib
u
to
r
in
t
h
e
sc
ien
ti
fic
c
o
m
m
u
n
it
y
.
He
h
a
s
a
u
t
h
o
re
d
o
r
c
o
-
a
u
th
o
re
d
m
o
re
th
a
n
1
5
p
u
b
l
ica
ti
o
n
s.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
a
p
p
li
e
d
m
a
th
e
m
a
ti
c
s,
a
c
tu
a
rial
sc
ien
c
e
,
m
a
c
h
in
e
lea
rn
in
g
,
a
n
d
a
rti
f
icia
l
in
telli
g
e
n
c
e
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
rm
a
n
h
a
z
@s
c
i.
u
i.
a
c
.
id
.
Ma
u
l
a
n
a
M
a
li
k
re
c
e
iv
e
d
t
h
e
B.
S
c
.
a
n
d
M
.
S
c
.
d
e
g
re
e
s
i
n
M
a
th
e
m
a
ti
c
s
fro
m
Un
iv
e
rsitas
In
d
o
n
e
sia
(UI),
In
d
o
n
e
sia
,
a
n
d
th
e
P
h
.
D.
d
e
g
re
e
in
M
a
th
e
m
a
ti
c
s
fro
m
Un
iv
e
rsiti
S
u
lt
a
n
Za
in
a
l
Ab
id
i
n
(Un
i
S
ZA),
M
a
lay
sia
.
He
is
c
u
rre
n
tl
y
a
n
A
ss
istan
t
P
ro
fe
ss
o
r
wit
h
t
h
e
De
p
a
rtme
n
t
o
f
M
a
t
h
e
m
a
ti
c
s
Un
iv
e
rsitas
In
d
o
n
e
sia
.
He
h
a
s
a
u
th
o
re
d
a
n
d
c
o
a
u
th
o
re
d
a
n
u
m
b
e
r
o
f
re
sa
rc
h
a
r
ti
c
les
in
h
ig
h
imp
a
c
t
jo
u
r
n
a
ls.
His
c
u
rre
n
t
re
se
a
rc
h
in
te
re
st
it
e
ra
ti
v
e
a
lg
o
rit
h
m
s
fo
r
so
lv
i
n
g
n
o
n
l
in
e
a
r
o
p
t
imiz
a
ti
o
n
,
su
c
h
a
s
c
o
n
ju
g
a
te
g
ra
d
ien
t
m
e
th
o
d
with
a
p
p
li
c
a
ti
o
n
i
n
p
o
rtf
o
li
o
se
lec
ti
o
n
,
ro
b
o
ti
c
m
o
ti
o
n
c
o
n
tro
l,
ima
g
e
re
sto
ra
ti
o
n
,
si
g
n
a
l
re
c
o
v
e
ry
,
a
n
d
c
a
rb
o
n
e
m
issio
n
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
.
m
a
li
k
@s
c
i.
u
i.
a
c
.
id
.
Wa
h
y
u
Nury
a
n
in
g
r
u
m
sh
e
is
a
stu
d
e
n
t
a
t
De
p
a
rtme
n
t
o
f
M
a
t
h
e
m
a
ti
c
s,
F
a
c
u
lt
y
o
f
M
a
th
e
m
a
ti
c
s
a
n
d
Na
tu
ra
l
S
c
i
e
n
c
e
s,
Un
iv
e
rsitas
In
d
o
n
e
sia
,
De
p
o
k
,
In
d
o
n
e
sia
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
wa
h
y
u
.
n
u
r
y
a
n
in
g
r
u
m
1
7
9
@g
m
a
il
.
c
o
m
.
Ag
u
stia
n
i
Pu
tr
i
is
a
P
h
.
D.
c
a
n
d
id
a
te
a
t
Un
iv
e
rsitas
Ne
g
e
ri
M
a
lan
g
,
I
n
d
o
n
e
sia
.
S
h
e
a
lwa
y
s
c
o
n
c
e
n
trate
d
o
n
m
a
t
h
e
m
a
ti
c
s
e
d
u
c
a
ti
o
n
d
u
ri
n
g
h
e
r
h
i
g
h
e
r
e
d
u
c
a
ti
o
n
.
S
h
e
e
a
rn
e
d
B.
Ed
.
fro
m
Un
i
v
e
rsitas
Ne
g
e
ri
Ja
k
a
rta,
In
d
o
n
e
sia
,
a
n
d
M
.
E
d
.
fro
m
Un
iv
e
rsitas
Ne
g
e
ri
M
a
lan
g
.
S
h
e
is
c
u
rre
n
tl
y
o
n
a
re
se
a
rc
h
fe
ll
o
ws
h
ip
a
t
De
a
k
in
Un
i
v
e
rsity
,
M
e
lb
o
u
rn
e
,
Au
stra
li
a
.
S
h
e
a
lso
h
a
s
b
e
e
n
in
v
o
l
v
e
d
in
m
a
th
e
m
a
ti
c
s
a
n
d
e
d
u
c
a
ti
o
n
re
se
a
rc
h
b
o
th
q
u
a
n
ti
tati
v
e
ly
a
n
d
q
u
a
li
tativ
e
l
y
.
S
h
e
h
a
s
p
u
b
li
sh
e
d
m
a
n
y
w
o
rk
s
b
o
th
in
re
p
u
tab
le
in
ter
n
a
ti
o
n
a
l
j
o
u
r
n
a
ls
in
d
e
x
e
d
b
y
S
c
o
p
u
s
a
n
d
n
a
ti
o
n
a
l
jo
u
rn
a
ls.
S
h
e
c
a
n
b
e
c
o
n
t
a
c
ted
a
t
e
m
a
il
:
a
g
u
stian
i
p
u
tri
1
5
@
g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.