I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
6
,
No
.
6
,
Dec
em
b
er
201
6
,
p
p
.
3
1
9
6
~
3
2
0
4
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
6i
6
.
1
3
3
2
3
3196
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
jo
u
r
n
a
l.c
o
m/o
n
lin
e/in
d
ex
.
p
h
p
/I
JE
C
E
Perf
o
r
m
a
n
ce
For
ecas
ting o
f
Sha
re
M
a
rk
et
u
sing
Ma
chine
Lea
rning
Techni
ques:
A
Rev
iew
Sa
chin K
a
m
ley
1
, S
ha
iles
h
J
a
lo
re
e
2
,
R.
S.
T
ha
ku
r
3
1
De
p
a
rt
m
e
n
t
o
f
Co
m
p
u
ter
A
p
p
li
c
a
ti
o
n
s
,
S
.
A
.
T
.
I.
,
V
i
d
ish
a
,
I
n
d
ia
2
De
p
a
rtme
n
t
o
f
A
p
p
li
e
d
M
a
th
’s
&
Co
m
p
u
ter S
c
ien
c
e
,
S
.
A
.
T
.
I.
,
V
i
d
ish
a
,
I
n
d
ia
3
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter A
p
p
li
c
a
ti
o
n
s,
M
.
A
.
N.I.
T
.
,
Bh
o
p
a
l,
I
n
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Au
g
2
0
,
2
0
1
6
R
ev
i
s
ed
No
v
1
2
,
201
6
A
cc
ep
ted
No
v
26
,
201
6
F
o
re
c
a
stin
g
sh
a
re
p
e
rf
o
r
m
a
n
c
e
b
e
c
o
m
e
s
m
o
re
c
h
a
ll
e
n
g
in
g
issu
e
d
u
e
to
th
e
e
n
o
rm
o
u
s
a
m
o
u
n
t
o
f
v
a
lu
a
b
le
trad
in
g
d
a
ta
sto
re
d
in
th
e
sto
c
k
d
a
tab
a
se
.
Cu
rre
n
tl
y
,
e
x
isti
n
g
f
o
re
c
a
stin
g
m
e
th
o
d
s
a
re
in
su
f
f
icie
n
t
to
a
n
a
ly
z
e
th
e
sh
a
re
p
e
rf
o
r
m
a
n
c
e
a
c
c
u
ra
tel
y
.
T
h
e
r
e
a
r
e
tw
o
m
a
in
re
a
so
n
s
f
o
r
th
a
t:
F
irst
,
th
e
stu
d
y
of
e
x
isti
n
g
f
o
re
c
a
stin
g
m
e
th
o
d
s
is
stil
l
in
su
f
f
icie
n
t
to
id
e
n
ti
f
y
th
e
m
o
st
su
it
a
b
le m
e
th
o
d
s f
o
r
sh
a
re
p
rice
p
re
d
ictio
n
.
S
e
c
o
n
d
,
t
h
e
lac
k
o
f
in
v
e
stig
a
ti
o
n
s
m
a
d
e
o
n
th
e
f
a
c
to
rs a
ff
e
c
ti
n
g
th
e
sh
a
re
p
e
rf
o
r
m
a
n
c
e
.
In
th
is
re
g
a
rd
,
th
is
stu
d
y
p
re
se
n
ts
a
sy
ste
m
a
ti
c
re
v
ie
w
o
f
th
e
las
t
f
if
tee
n
y
e
a
rs
o
n
v
a
rio
u
s
m
a
c
h
in
e
lea
rn
in
g
tec
h
n
iq
u
e
s
in
o
r
d
e
r
to
a
n
a
ly
z
e
sh
a
re
p
e
rf
o
r
m
a
n
c
e
a
c
c
u
ra
tel
y
.
T
h
e
o
n
ly
o
b
jec
ti
v
e
o
f
th
is
stu
d
y
is
to
p
ro
v
id
e
a
n
o
v
e
rv
ie
w
o
f
th
e
m
a
c
h
in
e
lea
rn
in
g
tec
h
n
iq
u
e
s
th
a
t
h
a
v
e
b
e
e
n
u
se
d
to
f
o
re
c
a
st
sh
a
re
p
e
rf
o
rm
a
n
c
e
.
T
h
is
p
a
p
e
r
a
lso
h
ig
h
li
g
h
ts
a
h
o
w
th
e
p
re
d
ict
io
n
a
lg
o
rit
h
m
s
c
a
n
b
e
u
se
d
to
id
e
n
ti
fy
th
e
m
o
st
i
m
p
o
rtan
t
v
a
riab
les
in
a
sh
a
re
m
a
rk
e
t
d
a
ta
se
t.
F
in
a
ll
y
,
we
c
o
u
l
d
h
a
v
e
su
c
c
e
e
d
e
d
to
a
n
a
ly
z
e
sh
a
re
p
e
rfo
rm
a
n
c
e
e
ffe
c
ti
v
e
l
y
.
It
c
o
u
ld
b
ri
n
g
b
e
n
e
f
it
s
a
n
d
im
p
a
c
ts
to
re
se
a
rc
h
e
rs,
so
c
iety
,
b
ro
k
e
rs an
d
f
in
a
n
c
ial
a
n
a
ly
st
s.
K
ey
w
o
r
d
:
Ma
ch
i
n
e
lear
n
i
n
g
P
er
f
o
r
m
a
n
ce
f
o
r
ec
asti
n
g
Sh
ar
e
m
ar
k
et
Co
p
y
rig
h
t
©
2
0
1
6
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
All
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Sach
i
n
Ka
m
le
y
,
Dep
ar
te
m
en
t o
f
C
o
m
p
u
ter
A
p
p
licatio
n
s
,
S.A
.
T
.
I
.
,
B
.
T
.
I
.
R
o
ad
,
Sh
er
p
u
r
a,
Vid
is
h
a
,
4
6
4
0
0
1
,
MP
.
I
n
d
ia.
E
m
ail:
s
k
a
m
le
y
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
No
w
a
d
a
y
,
s
h
ar
e
p
r
ice
p
r
e
d
ictio
n
is
an
i
m
p
o
r
tan
t
co
n
c
er
n
f
o
r
p
o
lic
y
m
a
k
er
s
,
r
esea
r
ch
er
s
an
d
in
v
e
s
to
r
s
b
ec
au
s
e
ac
cu
r
ate
p
r
ice
p
r
ed
ictio
n
p
lay
s
k
e
y
r
o
le
in
in
v
est
m
e
n
t
d
ec
is
io
n
m
a
k
i
n
g
.
I
n
g
en
er
al,
s
to
ck
m
ar
k
et
n
atu
r
e
is
co
n
s
id
er
ed
to
b
e
ch
ao
tic
an
d
co
m
p
licated
,
b
u
t
it
h
as
b
ee
n
in
f
lu
e
n
ce
d
b
y
s
ev
er
al
ec
o
n
o
m
ic
an
d
ex
t
er
n
a
l
en
v
ir
o
n
m
e
n
tal
f
a
cto
r
s
.
T
h
er
ef
o
r
e,
s
h
ar
e
m
ar
k
et
an
al
y
s
es
h
av
e
b
ee
n
u
s
in
g
s
o
m
e
ap
p
r
o
ac
h
es
f
o
r
p
r
ed
ictin
g
s
h
ar
e
p
r
ices
.
T
h
e
r
an
d
o
m
w
alk
th
eo
r
y
s
tate
s
th
a
t
s
h
ar
e
p
r
ice
m
o
v
e
m
e
n
t
s
ar
e
in
d
ep
en
d
en
t
o
f
ea
ch
o
th
er
an
d
p
r
ice
m
o
v
e
m
e
n
ts
d
o
n
o
t
f
o
llo
w
a
n
y
p
atter
n
s
o
r
tr
en
d
s
[
1
]
.
T
h
u
s
,
it
is
p
r
ac
ticall
y
i
m
p
o
s
s
ib
le
t
o
p
r
ed
ict
th
e
f
u
t
u
r
e
p
r
ice
m
o
v
e
m
e
n
t
s
b
ased
o
n
th
e
h
is
to
r
ical
d
ata.
On
t
h
e
o
t
h
er
h
an
d
,
tec
h
n
ical
an
al
y
s
is
ca
n
b
e
u
s
ed
to
id
e
n
ti
f
y
t
h
e
p
atter
n
s
a
n
d
tr
en
d
s
b
as
ed
o
n
t
h
e
h
is
to
r
ic
p
r
ices
[
1
]
.
So
th
er
e
f
o
r
e,
f
u
t
u
r
e
p
r
ice
m
o
v
e
m
en
t
s
c
an
b
e
d
o
n
e
b
y
e
x
a
m
i
n
in
g
p
as
t
s
h
ar
e
p
r
ices.
Fo
r
m
an
y
y
ea
r
s
,
tech
n
ical
an
al
y
s
e
s
w
i
th
s
tatis
t
ical
ap
p
r
o
a
ch
es
h
av
e
b
ee
n
w
id
el
y
ap
p
lied
to
th
is
ar
ea
in
o
r
d
er
t
o
d
ev
elo
p
s
o
m
e
co
n
ce
p
ts
an
d
s
tr
ateg
ies to
b
e
h
elp
f
u
l
f
o
r
s
h
ar
e
p
er
f
o
r
m
a
n
ce
f
o
r
ec
asti
n
g
[
1
-
2
]
.
C
u
r
r
en
tl
y
,
th
er
e
ar
e
v
ar
io
u
s
te
ch
n
iq
u
es
h
a
v
e
b
ee
n
p
r
o
p
o
s
ed
to
ev
al
u
ate
s
h
ar
e
p
er
f
o
r
m
an
ce
.
Ma
ch
i
n
e
lear
n
in
g
is
o
n
e
o
f
th
e
co
r
e
ar
ea
s
w
h
ic
h
h
as
b
ee
n
w
id
el
y
u
s
ed
to
an
al
y
ze
s
h
ar
e
p
er
f
o
r
m
an
ce
.
T
h
e
m
ai
n
o
b
j
ec
tiv
e
o
f
m
ac
h
i
n
e
lear
n
in
g
tech
n
iq
u
es
i
s
to
au
to
m
atica
ll
y
lear
n
an
d
r
ec
o
g
n
ize
p
atter
n
s
f
r
o
m
h
u
g
e
a
m
o
u
n
t
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
P
erfo
r
ma
n
ce
F
o
r
ec
a
s
tin
g
o
f S
h
a
r
e
Ma
r
ke
t U
s
in
g
Ma
ch
in
e
Lea
r
n
in
g
Tech
n
iq
u
es:
A
R
ev
iew
(
S
a
ch
in
K
a
mley
)
3197
o
f
d
ata
[
3
]
.
H
o
w
ev
er
,
th
e
s
e
p
atter
n
s
a
n
d
tr
en
d
s
ca
n
b
e
h
el
p
f
u
l
f
o
r
p
r
ed
ictin
g
s
h
ar
e
p
er
f
o
r
m
a
n
ce
ef
f
ec
ti
v
el
y
an
d
ass
i
s
t f
in
a
n
cial
a
n
al
y
s
t,
i
n
v
esto
r
s
a
n
d
b
r
o
k
er
s
to
ap
p
r
o
p
r
iate
s
h
ar
e
s
elec
tio
n
.
So
th
er
e
f
o
r
e,
ap
p
licatio
n
o
f
m
ac
h
in
e
lear
n
i
n
g
tec
h
n
iq
u
es
i
n
s
h
ar
e
m
ar
k
et
r
esear
ch
ca
n
b
e
ad
d
r
ess
ed
w
it
h
d
i
f
f
er
e
n
t
en
titi
e
s
.
I
n
o
r
d
er
to
en
co
u
n
ter
t
h
e
p
r
o
b
lem
,
a
s
y
s
te
m
at
ic
r
ev
ie
w
i
s
p
r
o
p
o
s
ed
.
T
h
er
ef
o
r
e,
th
e
m
ai
n
o
b
j
ec
tiv
es o
f
p
r
o
p
o
s
ed
r
ev
ie
w
ar
e:
1
)
T
o
i
d
en
tify
t
h
e
r
esear
ch
g
a
p
s
in
ex
i
s
ti
n
g
p
r
ed
ictio
n
m
et
h
o
d
s
.
2
)
T
o
s
tu
d
y
a
n
d
id
en
ti
f
y
v
ar
ia
b
les
w
h
ic
h
af
f
ec
t s
h
ar
e
p
er
f
o
r
m
an
ce
.
3
)
T
o
s
tu
d
y
t
h
e
ex
is
ti
n
g
p
r
ed
ictio
n
m
et
h
o
d
s
i
n
o
r
d
er
to
an
aly
ze
s
h
ar
e
p
er
f
o
r
m
a
n
ce
.
T
h
e
n
ex
t
s
ec
tio
n
d
is
c
u
s
s
es
th
e
m
e
th
o
d
o
lo
g
y
o
f
s
u
r
v
e
y
in
p
r
ed
ictin
g
s
h
ar
e
p
er
f
o
r
m
a
n
ce
.
Sectio
n
3
d
is
cu
s
s
es
o
n
i
m
p
o
r
tan
t
f
ac
to
r
s
in
p
r
ed
ictin
g
s
h
ar
e
p
er
f
o
r
m
a
n
ce
.
Sectio
n
4
d
is
cu
s
s
es
d
etail
r
esu
lts
o
n
e
x
is
ti
n
g
p
r
ed
ictio
n
m
eth
o
d
s
a
n
d
at
last
s
ec
tio
n
5
d
is
cu
s
s
e
s
co
n
cl
u
s
io
n
an
d
f
u
tu
r
e
s
co
p
es o
f
s
tu
d
y
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
I
n
th
i
s
co
n
te
x
t,
th
e
s
y
s
te
m
at
ic
r
elatio
n
al
r
ev
ie
w
i
s
to
b
e
d
o
n
e
to
f
in
d
o
u
t
s
u
itab
le
m
eth
o
d
s
f
o
r
ex
is
t
in
g
p
ar
a
m
eter
s
as
w
ell
a
s
to
f
u
l
f
ills
t
h
e
g
o
al
s
in
ex
is
ti
n
g
r
esear
ch
an
d
to
p
lace
a
n
e
w
r
esear
ch
ac
tiv
i
t
y
i
n
th
e
s
u
itab
le
co
n
te
x
t [
4
]
.
T
h
e
m
ai
n
ai
m
o
f
s
y
s
te
m
at
ic
r
ev
ie
w
o
f
t
h
e
c
u
r
r
en
t
liter
atu
r
e
is
to
s
u
p
p
o
r
t th
e
p
r
o
p
o
s
ed
r
esear
ch
q
u
est
io
n
s
.
Ne
x
t,
s
u
b
s
ec
tio
n
s
w
ill
b
e
id
en
ti
f
y
i
n
g
th
e
r
esear
ch
q
u
est
io
n
s
to
g
u
id
e
th
e
r
es
u
lts
.
T
h
is
i
s
v
er
y
u
s
e
f
u
l to
id
en
ti
f
y
t
h
e
s
co
p
e
an
d
o
b
j
ec
tiv
es o
f
th
e
r
esear
ch
s
t
u
d
y
.
2
.
1
.
Rese
a
rc
h Q
ues
t
io
ns
R
esear
ch
q
u
es
tio
n
s
ar
e
v
er
y
i
m
p
o
r
ta
n
t
cr
iter
ia
to
u
n
d
er
s
tan
d
th
e
e
x
is
ti
n
g
s
tu
d
ie
s
o
f
f
o
r
ec
asti
n
g
s
h
ar
e
p
er
f
o
r
m
a
n
ce
.
T
h
e
Kitch
e
n
h
a
m
s
s
tep
s
ar
e
u
s
ed
f
o
r
s
tr
u
c
tu
r
in
g
t
h
e
r
esear
ch
q
u
e
s
tio
n
s
w
h
ic
h
co
n
s
i
s
t
o
f
P
o
p
u
latio
n
,
I
n
ter
v
en
tio
n
,
O
u
tc
o
m
e
a
n
d
C
o
n
tex
t (
P
I
OC
)
[
4
]
.
T
ab
le
1
s
h
o
w
s
t
h
e
cr
iter
ia
o
f
r
esear
ch
q
u
es
tio
n
s
.
T
ab
le
1
.
R
esear
ch
Qu
es
tio
n
s
C
r
iter
ia
C
r
i
t
e
r
i
a
D
e
scri
p
t
i
o
n
s
P
o
p
u
l
a
t
i
o
n
S
t
o
c
k
M
a
r
k
e
t
D
a
t
a
se
t
I
n
t
e
r
v
e
n
t
i
o
n
M
e
t
h
o
d
s/
T
e
c
h
n
i
q
u
e
s fo
r
P
r
e
d
i
c
t
i
o
n
O
u
t
c
o
me
P
r
e
d
i
c
t
i
o
n
A
c
c
u
r
a
c
y
,
S
u
c
c
e
ssf
u
l
P
r
e
d
i
c
t
i
o
n
T
e
c
h
n
i
q
u
e
s
C
o
n
t
e
x
t
I
n
d
i
v
i
d
u
a
l
S
h
a
r
e
P
e
r
f
o
r
man
c
e
,
A
l
l
Ty
p
e
s o
f
Emp
i
r
i
c
a
l
S
t
u
d
i
e
s s
u
c
h
a
s C
a
se
S
t
u
d
y
,
Q
u
e
st
i
o
n
n
a
i
r
e
s,
S
u
r
v
e
y
s
a
n
d
Ex
p
e
r
i
me
n
t
s.
I
n
th
i
s
s
t
u
d
y
,
t
h
er
ef
o
r
e
t
w
o
b
a
s
ic
r
esear
ch
q
u
e
s
tio
n
s
ar
e
p
r
o
p
o
s
ed
.
Q1
:
w
h
at
ar
e
th
e
i
m
p
o
r
tan
t
v
a
r
iab
les u
s
ed
in
f
o
r
ec
ast s
h
ar
e
p
er
f
o
r
m
a
n
ce
?
Q2
:
w
h
at
ar
e
th
e
p
r
ed
ictio
n
m
eth
o
d
s
u
s
ed
f
o
r
ev
al
u
atio
n
o
f
s
h
ar
e
p
er
f
o
r
m
an
ce
?
B
ef
o
r
e
g
o
in
g
to
th
e
d
ep
th
o
f
t
h
e
s
tu
d
y
t
h
e
n
ex
t
s
u
b
s
ec
tio
n
d
is
cu
s
s
es
s
ea
r
ch
s
tr
ate
g
y
f
o
r
co
n
d
u
cti
n
g
r
ev
ie
w
p
u
r
p
o
s
e.
T
h
e
m
a
in
co
n
ce
r
n
o
f
th
is
s
t
u
d
y
is
to
in
v
e
s
ti
g
ate
t
h
e
ap
p
r
o
p
r
iaten
ess
o
f
th
e
r
esear
ch
q
u
esti
o
n
s
w
it
h
t
h
e
o
b
j
ec
tiv
es o
f
th
e
s
t
u
d
y
.
2
.
2
.
Sea
rc
h St
ra
t
eg
y
A
w
el
l
p
lan
n
ed
s
ea
r
c
h
s
tr
ate
g
y
p
la
y
s
v
er
y
i
m
p
o
r
ta
n
t
r
o
le
in
a
s
y
s
te
m
atic
r
ev
ie
w
b
ec
a
u
s
e
e
v
er
y
r
elev
an
t p
iece
o
f
w
o
r
k
ca
n
b
e
f
o
u
n
d
in
th
e
s
ea
r
ch
r
es
u
lt
s
.
T
h
er
ef
o
r
e,
an
ex
te
n
s
iv
e
r
esear
c
h
f
o
r
r
esear
ch
p
ap
er
s
w
a
s
co
n
d
u
c
ted
to
tr
y
a
n
s
w
er
i
n
g
th
e
p
r
o
p
o
s
ed
r
esear
ch
q
u
e
s
tio
n
s
.
I
n
o
r
d
er
to
id
en
ti
f
y
p
u
b
lis
h
ed
ar
ticles
o
n
m
ac
h
in
e
lear
n
in
g
tec
h
n
iq
u
es
w
h
ic
h
w
er
e
s
p
ec
if
ica
ll
y
ap
p
li
ed
in
eith
e
r
h
y
b
r
id
o
r
in
d
iv
id
u
al
f
o
r
m
to
p
r
ed
ict
s
h
ar
e
p
r
ices.
I
n
t
h
is
s
t
u
d
y
,
t
h
e
liter
at
u
r
e
s
ea
r
ch
co
v
er
ed
th
e
p
er
io
d
o
f
p
u
b
licatio
n
s
f
r
o
m
2
0
0
0
to
2
0
1
5
.
Ho
w
e
v
er
,
th
e
o
n
lin
e
s
ea
r
ch
w
a
s
b
ased
o
n
s
u
ch
k
e
y
w
o
r
d
s
as
d
ec
is
io
n
tr
ee
,
n
eu
r
al
n
et
wo
r
k
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e,
g
e
n
etic
al
g
o
r
ith
m
,
B
ay
e
s
ian
n
et
w
o
r
k
,
etc.
an
d
e
ac
h
o
f
t
h
e
k
e
y
w
o
r
d
is
attac
h
ed
w
it
h
s
h
ar
e
p
r
ice
p
r
ed
ictio
n
.
Mo
r
eo
v
er
,
th
e
to
tal
1
0
0
ar
ticles
p
u
b
lis
h
ed
o
v
er
th
e
p
er
io
d
,
b
u
t
o
n
l
y
7
1
r
elev
an
t
p
u
b
licat
io
n
s
i
n
liter
atu
r
e
r
e
v
ie
w
co
u
ld
b
e
id
e
n
ti
f
ied
.
T
ab
le
2
s
h
o
w
s
a
d
escr
ip
tio
n
o
f
r
esear
ch
liter
at
u
r
e
wh
ich
w
er
e
id
e
n
ti
f
ied
th
r
o
u
g
h
o
n
lin
e
s
ea
r
ch
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
6
,
No
.
6
,
Dec
em
b
er
2
0
1
6
:
3
196
–
3
204
3198
T
ab
le
2
.
Descr
ip
tio
n
o
f
Sear
ch
Data
b
ases
S
.
N
o
.
D
a
t
a
B
a
se
1
S
c
i
e
n
c
e
D
i
r
e
c
t
2
S
c
o
p
u
s
3
S
p
r
i
n
g
e
r
4
G
o
o
g
l
e
S
c
h
o
l
a
r
5
I
EEE
X
p
l
o
r
e
6
M
i
c
r
o
so
f
t
A
c
a
d
e
my
S
e
a
r
c
h
7
W
e
b
o
f
S
c
i
e
n
c
e
8
D
O
A
J
9
P
r
o
Q
u
e
st
10
T
a
y
l
o
r
s &
F
r
a
n
c
i
s
3.
I
M
P
O
RT
ANT F
ACTOR
S O
N
P
RE
DI
CT
I
N
G
SH
ARE M
ARK
E
T
P
E
RF
O
RM
ANCE
T
h
is
s
ec
tio
n
m
a
in
l
y
h
i
g
h
lig
h
t
s
th
e
i
m
p
o
r
tan
t
f
ac
to
r
s
i
n
p
r
ed
ictin
g
s
h
ar
e
m
ar
k
et
p
er
f
o
r
m
a
n
ce
.
T
h
er
e
ar
e
t
w
o
k
e
y
f
ac
to
r
s
i
n
p
r
ed
ictin
g
s
h
ar
e
p
er
f
o
r
m
a
n
ce
s
w
h
ic
h
ar
e
v
ar
iab
les
a
n
d
p
r
ed
ictio
n
m
eth
o
d
s
.
T
h
er
ef
o
r
e,
th
e
n
ex
t
s
u
b
s
ec
tio
n
s
w
ill
b
e
f
o
cu
s
ed
o
n
th
e
i
m
p
o
r
tan
t
v
ar
ia
b
les
an
d
p
r
ed
ictio
n
m
et
h
o
d
s
u
s
ed
in
s
to
c
k
m
ar
k
et
s
tu
d
y
.
3
.
1
.
T
he
I
m
po
rt
a
nt
Va
ria
bles
Us
ed
in P
re
dict
ing
Sh
a
re
P
er
f
o
r
m
a
nce
I
n
th
is
s
t
u
d
y
,
t
h
e
s
y
s
te
m
at
ic
r
ev
ie
w
i
s
u
s
ed
to
id
en
ti
f
y
t
h
e
i
m
p
o
r
tan
t
v
ar
iab
les
in
p
r
ed
ic
tin
g
s
h
ar
e
p
er
f
o
r
m
a
n
ce
.
I
n
g
e
n
er
al,
th
e
v
ar
iab
les
th
at
h
a
v
e
b
ee
n
f
r
eq
u
e
n
tl
y
u
s
ed
b
y
r
esear
c
h
er
s
w
h
ic
h
ar
e
f
u
n
d
a
m
e
n
tal,
tech
n
ical,
m
ac
r
o
ec
o
n
o
m
ical
an
d
lag
g
ed
in
d
ex
.
T
w
el
v
e
o
f
t
h
e
th
ir
t
y
p
ap
er
s
h
a
v
e
u
s
ed
p
r
ice
ea
r
n
in
g
s
r
atio
,
ea
r
n
in
g
s
p
er
s
h
ar
e,
Net
A
s
s
et
Valu
e,
Gen
er
al
I
n
d
ex
(
GI
)
,
s
h
ar
e
v
o
lu
m
e,
p
r
ice
p
er
an
n
u
m
,
b
o
o
k
v
alu
e,
f
ac
e
v
alu
e,
f
in
a
n
cial
s
tat
u
s
o
f
co
m
p
a
n
y
,
s
to
ck
b
u
y
/s
ell
n
e
w
s
,
d
iv
id
en
d
y
ield
,
tr
ea
s
u
r
y
b
ill
r
ate,
cu
r
r
en
t
r
atio
,
f
i
n
an
cia
l
le
v
er
ag
e
r
atio
,
in
co
m
e
s
tate
m
en
t,
r
ev
e
n
u
e
g
r
o
w
t
h
,
Gr
o
w
t
h
i
n
n
et
s
ale
s
,
Gr
o
w
th
in
n
et
p
r
o
f
i
t,
R
et
u
r
n
o
n
E
q
u
it
y
,
Net
P
r
o
f
it
Ma
r
g
i
n
(
NP
M)
,
P
r
ice/Sales
r
atio
etc.
as
th
eir
m
ai
n
attr
ib
u
te
s
to
p
r
ed
ict
s
h
ar
e
m
ar
k
et
p
er
f
o
r
m
a
n
ce
[
5
-
1
9
]
.
T
h
e
m
ai
n
p
u
r
p
o
s
e
o
f
u
s
in
g
th
e
s
e
v
ar
iab
les
is
b
ec
au
s
e
it
d
ea
ls
w
i
t
h
th
e
v
al
u
e
o
f
th
e
co
m
p
a
n
y
s
to
ck
w
i
th
r
e
g
ar
d
s
to
its
p
o
ten
tial
g
r
o
w
t
h
in
f
u
tu
r
e
ea
r
n
in
g
s
.
I
t
ca
n
al
s
o
b
e
co
n
s
id
er
ed
as
an
in
d
icatio
n
o
f
r
ea
lizin
g
s
h
ar
e
g
r
o
w
t
h
p
o
ten
tial [
1
]
,
[
6
]
,
[
17
]
.
Nex
t,
t
h
e
m
o
s
t
o
f
te
n
v
ar
iab
les
u
s
ed
b
y
r
esear
c
h
er
s
ar
e
tec
h
n
ical
i
n
d
icato
r
s
.
T
h
e
tech
n
ical
in
d
icato
r
in
cl
u
d
es
Mo
v
i
n
g
Av
er
ag
e
(
M
A
)
,
E
x
p
o
n
e
n
tia
l
Mo
v
i
n
g
Av
e
r
ag
e
(
E
MA
)
,
R
elati
v
e
S
tr
en
g
t
h
I
n
d
e
x
(
R
SI)
a
n
d
Mo
v
in
g
A
v
er
a
g
e
C
o
n
v
er
g
e
n
c
e
Div
er
g
e
n
ce
(
MA
C
D)
,
B
o
llin
g
er
B
an
d
s
,
Sto
ch
a
s
t
ic
Oscil
lato
r
,
Mo
m
en
tu
m
,
s
lo
w
%D,
W
illi
a
m
R
%,
P
r
ice
R
ate
o
f
C
h
an
g
e
(
R
O
C
)
,
Dis
p
a
r
it
y
(
5
-
1
0
)
,
Pric
e
Oscill
ato
r
(
O
SC
P
)
,
C
o
m
m
o
d
it
y
C
h
a
n
n
el
I
n
d
ex
(
C
C
I
)
,
P
r
ice
an
d
Vo
lu
m
e
T
r
en
d
(
P
V
T
)
,
On
B
ala
n
ce
Vo
l
u
m
e
(
OB
V)
,
Ma
s
s
I
n
d
ex
(
MI
)
,
Av
er
ag
e
T
r
u
e
R
an
g
e
(
A
T
R
)
,
Mo
m
en
tu
m
,
C
h
a
ik
i
n
Mo
n
e
y
Flo
w
(
C
MF)
,
etc.
[
2
]
,
[
6
]
,
[
1
2
-
1
3
]
,
[
20
-
3
7
]
.
T
h
e
m
ai
n
id
ea
b
eh
in
d
u
s
i
n
g
t
h
es
e
in
d
icato
r
s
i
s
to
e
v
al
u
ate
s
t
o
ck
p
r
ice
m
o
v
e
m
e
n
t
s
b
ased
o
n
h
i
s
to
r
ical
p
r
ice
p
atter
n
s
an
d
v
o
l
u
m
es.
Mo
s
t
o
f
t
h
e
r
esear
c
h
er
s
h
a
v
e
also
u
s
ed
m
ac
r
o
ec
o
n
o
m
ic
in
d
i
ca
to
r
s
f
o
r
ev
al
u
ati
n
g
s
h
ar
e
p
er
f
o
r
m
a
n
ce
.
T
h
ese
v
ar
iab
les
in
cl
u
d
e
s
h
o
r
t
ter
m
an
d
lo
n
g
ter
m
i
n
ter
est
r
ates,
in
f
la
tio
n
r
ate,
Fo
r
eig
n
Dir
ec
t
I
n
v
est
m
e
n
t
(
FDI
)
,
u
n
e
m
p
lo
y
m
en
t
r
ate,
Gr
o
s
s
Do
m
e
s
tic
P
r
o
d
u
ct
(
GDP
)
,
C
o
n
s
u
m
er
P
r
ice
I
n
d
ex
(
C
P
I
)
,
I
n
d
u
s
tr
ial
P
r
o
d
u
ctio
n
(
I
P
)
,
Go
v
er
n
m
en
t
C
o
n
s
u
m
p
tio
n
(
G
C
)
,
P
r
iv
ate
C
o
n
s
u
m
p
tio
n
(
P
C
)
,
Gr
o
s
s
Natio
n
al
P
r
o
d
u
ct
(
GNP
)
,
Mo
n
e
y
S
u
p
p
l
y
,
Oil P
r
ices,
E
x
ch
an
g
e
R
a
tes etc
.
[
1
3
],
[
2
2
]
,
[
2
7
]
,
[
39
-
4
8
]
.
3
.
2
.
T
he
P
re
dict
io
n M
et
ho
ds
Use
d f
o
r
Sh
a
re
P
er
f
o
rm
a
nce
I
n
t
h
e
s
h
ar
e
m
ar
k
et,
p
r
ed
ictiv
e
m
o
d
eli
n
g
is
u
s
u
a
ll
y
u
s
ed
to
p
r
ed
ict
s
h
ar
e
p
er
f
o
r
m
a
n
ce
.
I
n
o
r
d
er
to
b
u
ild
p
r
ed
ictiv
e
m
o
d
eli
n
g
,
t
h
e
r
e
ar
e
s
ev
er
al
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
e
s
ar
e
u
s
ed
w
h
ich
a
r
e
n
eu
r
al
n
et
w
o
r
k
,
s
u
p
p
o
r
t v
ec
to
r
m
ac
h
in
e
a
n
d
g
en
etic
a
lg
o
r
it
h
m
,
etc.
to
co
v
er
all
m
ac
h
i
n
e
lear
n
i
n
g
al
g
o
r
ith
m
s
is
n
o
t
p
o
s
s
ib
le
s
o
w
e
h
a
v
e
u
s
ed
f
e
w
p
o
p
u
lar
alg
o
r
ith
m
s
s
u
c
h
as
d
ec
is
io
n
tr
ee
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e,
n
eu
r
a
l
n
et
w
o
r
k
,
g
e
n
etic
alg
o
r
ith
m
,
B
a
y
es
ian
n
et
w
o
r
k
f
o
r
s
h
ar
e
p
r
ice
p
r
ed
ictio
n
.
T
h
e
n
ex
t
s
u
b
s
ec
tio
n
d
escr
ib
es t
h
e
ap
p
licatio
n
o
f
th
e
s
e
alg
o
r
ith
m
s
i
n
d
e
tail.
.
3
.
2
.
1
.
Dec
is
io
n T
re
e
T
h
e
d
ec
is
io
n
tr
ee
is
o
n
e
o
f
th
e
w
el
l
k
n
o
w
n
clas
s
i
f
icatio
n
al
g
o
r
ith
m
s
u
s
ed
in
d
ata
m
in
i
n
g
an
d
m
ac
h
in
e
lear
n
i
n
g
to
cr
ea
te
k
n
o
w
led
g
e
s
tr
u
ct
u
r
es
t
h
at
g
u
id
e
th
e
d
ec
is
io
n
m
a
k
i
n
g
p
r
o
ce
s
s
[
1
2
-
1
3
]
.
Fo
r
th
e
co
u
p
le
o
f
y
ea
r
s
v
ar
io
u
s
r
esear
ch
er
s
h
a
v
e
u
s
ed
th
is
tech
n
iq
u
e
d
u
e
to
its
s
im
p
lic
it
y
a
n
d
ca
p
ab
ilit
y
to
u
n
co
v
er
s
m
al
l
o
r
lar
g
e
d
ata
s
a
m
p
les
a
n
d
p
r
ed
ict
th
e
v
al
u
e.
T
h
er
ef
o
r
e,
th
er
e
ar
e
ap
p
r
o
x
i
m
ate
l
y
te
n
(
1
1
)
p
ap
er
s
th
at
h
av
e
u
s
ed
a
d
ec
is
io
n
tr
ee
al
g
o
r
ith
m
to
e
v
alu
a
te
s
h
ar
e
p
er
f
o
r
m
an
ce
.
T
ab
le
3
s
h
o
w
s
a
d
escr
ip
tio
n
o
f
t
h
e
d
ec
is
io
n
tr
ee
tech
n
iq
u
e
a
s
s
ele
cted
b
y
m
o
s
t o
f
t
h
e
au
t
h
o
r
s
f
o
r
s
h
ar
e
f
o
r
ec
asti
n
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
P
erfo
r
ma
n
ce
F
o
r
ec
a
s
tin
g
o
f S
h
a
r
e
Ma
r
ke
t U
s
in
g
Ma
ch
in
e
Lea
r
n
in
g
Tech
n
iq
u
es:
A
R
ev
iew
(
S
a
ch
in
K
a
mley
)
3199
T
ab
le
3
.
P
er
f
o
r
m
a
n
ce
A
cc
u
r
ac
y
o
f
Dec
i
s
io
n
T
r
ee
Me
th
o
d
M
e
t
h
o
d
R
e
su
l
t
s
A
u
t
h
o
r
s
D
e
c
i
si
o
n
T
r
e
e
8
5
.
9
4
%
C
h
a
n
g
[
6
]
D
e
c
i
si
o
n
T
r
e
e
8
1
%
S
h
a
i
f
e
e
e
t
a
l
.
[
7
]
D
e
c
i
si
o
n
T
r
e
e
7
1
%
G
e
p
p
e
t
a
l
.
[
9
]
D
e
c
i
si
o
n
T
r
e
e
8
1
%
W
u
e
t
a
l
.
[
1
0
]
H
y
b
r
i
d
D
e
c
i
si
o
n
T
r
e
e
8
6
%
T
sai
e
t
a
l
.
[
1
1
]
D
e
c
i
si
o
n
T
r
e
e
8
2
%
R
e
n
e
t
a
l
.
[
1
2
]
D
e
c
i
si
o
n
T
r
e
e
6
5
.
4
1
%
T
sai
e
t
a
l
.
[
1
3
]
H
y
b
r
i
d
D
e
c
i
si
o
n
T
r
e
e
8
8
%
W
a
n
g
e
t
a
l
.
[
2
6
]
D
e
c
i
si
o
n
T
r
e
e
8
5
.
7
1
%
C
h
e
n
e
t
a
l
.
[
17
]
D
e
c
i
si
o
n
T
r
e
e
7
3
.
6
0
%
K
i
r
k
o
s e
t
a
l
.
[
18
]
H
y
b
r
i
d
D
e
c
i
si
o
n
T
r
e
e
8
0
.
2
4
%
B
a
r
a
k
e
t
a
l
.
[
19
]
3
.
2
.
2
.
Neura
l N
et
w
o
rk
(
NN)
Neu
r
al
Net
w
o
r
k
is
an
o
t
h
er
m
o
s
t
p
o
p
u
lar
tech
n
iq
u
e
w
h
ich
h
as
b
ee
n
e
x
te
n
s
i
v
el
y
u
s
ed
f
o
r
s
h
ar
e
p
r
ice
p
r
ed
ictio
n
.
T
h
e
ad
v
an
ta
g
e
o
f
u
s
i
n
g
NN
is
t
h
at
it
h
as
t
h
e
ca
p
ab
ilit
y
to
r
ep
r
esen
t
o
r
m
o
d
ellin
g
co
m
p
le
x
n
o
n
-
lin
ea
r
in
p
u
t/o
u
tp
u
t
r
elatio
n
s
h
i
p
s
.
Ho
w
e
v
er
,
th
e
NN
s
y
s
te
m
co
m
p
o
s
ed
o
f
m
a
n
y
s
i
m
p
le
p
r
o
ce
s
s
in
g
ele
m
en
t
s
o
p
er
atin
g
in
p
ar
allel
w
h
o
s
e
f
u
n
ct
io
n
is
d
eter
m
in
ed
b
y
t
h
e
n
et
w
o
r
k
s
tr
u
ct
u
r
e,
co
n
n
ec
tio
n
s
tr
en
g
th
s
,
an
d
th
e
p
r
o
ce
s
s
in
g
p
er
f
o
r
m
ed
at
co
m
p
u
tin
g
ele
m
e
n
ts
o
r
n
o
d
es
[
49
]
.
I
n
t
h
is
s
t
u
d
y
,
N
N
i
s
s
elec
ted
as
o
n
e
o
f
t
h
e
b
e
s
t
p
r
ed
ictio
n
m
et
h
o
d
.
T
h
o
u
g
h
,
t
h
e
m
eta
-
a
n
al
y
s
is
s
t
u
d
y
te
n
(
1
0
)
p
ap
er
s
h
av
e
b
ee
n
u
s
ed
NN
f
o
r
s
h
ar
e
p
r
ice
p
r
ed
ictio
n
.
T
a
b
le
4
s
h
o
w
s
t
h
e
d
escr
ip
tio
n
o
f
th
e
NN
tech
n
i
q
u
e
as
s
elec
ted
b
y
m
o
s
t
o
f
th
e
au
th
o
r
s
f
o
r
s
h
ar
e
f
o
r
ec
asti
n
g
.
T
ab
le
4
.
P
er
f
o
r
m
a
n
ce
A
cc
u
r
ac
y
o
f
NN
Me
t
h
o
d
M
e
t
h
o
d
R
e
su
l
t
s
A
u
t
h
o
r
s
N
e
u
r
a
l
N
e
t
w
o
r
k
7
1
%
P
h
u
a
e
t
a
l
.
[
2
]
H
y
b
r
i
d
D
y
n
a
mi
c
A
N
N
9
6
%
B
i
so
i
e
t
a
l
.
[
20
]
N
e
u
r
a
l
N
e
t
w
o
r
k
9
1
%
M
a
so
d
[
50
]
N
e
u
r
a
l
N
e
t
w
o
r
k
9
0
%
O
l
a
t
u
n
j
i
e
t
a
l
.
[
21
]
H
y
b
r
i
d
M
o
d
e
l
(
B
P
N
N
+
S
V
M
+
C
4
.
5
+
L
R
+
K
N
N
)
7
6
.
0
6
%
H
u
a
n
g
e
t
a
l
.
[
43
]
N
e
u
r
a
l
N
e
t
w
o
r
k
5
9
.
3
8
%
B
o
l
a
e
t
a
l
.
[
3
0
]
N
e
u
r
a
l
N
e
t
w
o
r
k
8
7
.
5
0
%
O
l
i
v
e
r
a
e
t
a
l
.
[
3
1
]
H
y
b
r
i
d
M
o
d
e
l
(
P
N
N
+
C
4
.
5
+
R
o
u
g
h
S
e
t
)
7
6
%
C
h
e
n
g
e
t
a
l
.
[
3
2
]
M
u
l
t
i
L
a
y
e
r
P
e
r
c
e
p
t
r
o
n
(
M
L
P
)
7
5
%
T
sai
e
t
a
l
.
[
49
]
P
N
N
w
i
t
h
S
t
r
a
t
e
g
y
8
8
.
8
4
%
L
a
h
mi
r
i
[
51
]
3
.
2
.
3
.
Su
pp
o
rt
Vec
t
o
r
M
a
chine (
SVM
)
Su
p
p
o
r
t
Vec
to
r
Ma
ch
i
n
e
(
SV
M)
is
a
n
o
th
er
w
el
l
k
n
o
w
n
m
a
ch
in
e
lear
n
i
n
g
tec
h
n
iq
u
es
u
s
e
d
f
o
r
d
ata
class
i
f
icatio
n
b
ased
o
n
s
tati
s
ti
ca
l
th
eo
r
y
.
I
t
is
a
s
u
p
er
v
is
ed
l
ea
r
n
in
g
al
g
o
r
ith
m
a
n
d
i
n
itiall
y
it
w
as
d
esi
g
n
ed
to
s
o
lv
e
p
atter
n
r
ec
o
g
n
itio
n
p
r
o
b
lem
s
,
b
u
t
it
h
as
r
en
d
er
ed
to
s
o
lv
e
n
o
n
–
li
n
ea
r
r
eg
r
ess
io
n
p
r
o
b
le
m
s
a
s
w
ell
[
23
],
[
5
2
]
.
T
ab
le
5
s
h
o
w
s
th
e
d
escr
ip
tio
n
o
f
t
h
e
SVM
tech
n
iq
u
e
as
s
elec
ted
b
y
m
o
s
t
o
f
th
e
a
u
t
h
o
r
s
f
o
r
s
h
ar
e
f
o
r
ec
ast
in
g
.
T
ab
le
5
.
P
er
f
o
r
m
a
n
ce
A
cc
u
r
ac
y
o
f
SVM
Me
t
h
o
d
M
e
t
h
o
d
R
e
su
l
t
s
A
u
t
h
o
r
s
S
V
M
7
9
.
4
0
%
C
h
a
n
d
w
a
n
i
e
t
a
l
.
[
23
]
S
V
M
w
i
t
h
M
a
c
r
o
e
c
o
n
o
mi
c
6
4
%
L
a
h
mi
i
r
i
[
51
]
S
V
M
7
3
%
H
u
a
n
g
a
e
t
a
l
.
[
53
]
S
V
M
6
4
.
7
5
%
K
i
m [
52
]
H
y
b
r
i
d
S
V
M
w
i
t
h
G
A
6
1
.
7
3
%
C
h
o
u
d
h
a
r
y
e
t
a
l
.
[
54
]
H
y
b
r
i
d
S
V
M
w
i
t
h
G
A
9
6
.
4
6
%
K
h
a
t
i
b
i
e
t
a
l
.
[
55
]
S
V
M
9
1
%
C
a
o
.
e
t
a
l
.
[
56
]
H
y
b
r
i
d
S
V
M
w
i
t
h
S
O
M
8
0
.
2
6
%
C
a
o
e
t
a
l
.
[
57
]
S
V
M
7
2
%
S
a
p
a
n
k
e
v
y
c
h
e
t
a
l
.
[
58
]
S
V
M
(
P
o
l
y
n
o
mi
a
l
)
8
4
.
4
0
%
T
i
mo
r
e
t
a
l
.
[
59
]
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
6
,
No
.
6
,
Dec
em
b
er
2
0
1
6
:
3
196
–
3
204
3200
3
.
2
.
4
.
G
enet
ic
Alg
o
rit
h
m
s
(
G
A
s
)
Gen
etic
A
l
g
o
r
ith
m
s
ar
e
g
e
n
er
al
p
u
r
p
o
s
e
ad
ap
ti
v
e
h
eu
r
is
tic
s
ea
r
ch
tech
n
iq
u
e
s
b
as
ed
o
n
t
h
e
m
ec
h
a
n
i
s
m
s
o
f
n
a
tu
r
al
s
elec
ti
o
n
an
d
g
en
et
ics.
Ho
w
ev
er
,
th
e
m
a
in
id
ea
o
f
G
A
s
i
s
to
s
tar
t
w
it
h
a
p
o
p
u
latio
n
o
f
s
o
lu
tio
n
s
to
a
p
r
o
b
le
m
an
d
att
e
m
p
t to
p
r
o
d
u
ce
n
e
w
g
e
n
er
ati
o
n
s
o
f
s
o
lu
tio
n
s
w
h
ic
h
ar
e
b
ett
er
th
an
t
h
e
p
r
ev
io
u
s
o
n
es
[
3
]
.
GAs
r
eq
u
ir
es
o
n
l
y
f
itn
es
s
i
n
f
o
r
m
atio
n
,
n
o
t
g
r
ad
ie
n
t
i
n
f
o
r
m
atio
n
o
r
o
th
er
i
n
ter
n
al
k
n
o
w
led
g
e
o
f
a
p
r
o
b
lem
.
GA
s
h
a
s
tr
ad
itio
n
all
y
b
ee
n
u
s
ed
i
n
o
p
ti
m
izatio
n
b
u
t,
w
i
th
a
f
e
w
en
h
a
n
ce
m
en
ts
,
ca
n
p
er
f
o
r
m
class
i
f
icatio
n
an
d
p
r
ed
ictio
n
a
s
w
ell
[
3
]
,
[
60
]
.
T
ab
le
6
s
h
o
w
s
th
e
d
e
s
cr
ip
tio
n
o
f
th
e
G
As
te
ch
n
iq
u
e
as
s
elec
ted
b
y
m
o
s
t o
f
th
e
a
u
th
o
r
s
f
o
r
s
h
ar
e
f
o
r
ec
asti
n
g
.
T
ab
le
6
.
P
er
f
o
r
m
an
ce
A
cc
u
r
a
c
y
o
f
G
As M
eth
o
d
M
e
t
h
o
d
R
e
su
l
t
s
A
u
t
h
o
r
s
G
A
w
i
t
h
A
N
N
9
4
%
Jad
a
v
e
t
a
l
.
[
2
5
]
H
y
b
r
i
d
G
A
w
i
t
h
S
V
M
8
4
.
5
7
%
Y
u
e
t
a
l
.
[
61
]
GA
9
7
%
S
h
e
t
a
e
t
a
l
.
[
62
]
H
y
b
r
i
d
G
A
-
RBF
8
5
%
M
a
j
h
i
e
t
a
l
.
[
63
]
GA
9
5
%
S
a
ma
n
t
[
60
]
GA
9
5
%
W
e
i
[
64
]
GA
7
7
.
8
4
%
S
e
x
t
o
n
e
t
a
l
.
[
65
]
G
A
w
i
t
h
G
M
D
H
Ty
p
e
9
4
%
F
a
l
l
a
h
i
e
t
a
l
.
[
6
6
]
H
y
b
r
i
d
G
A
9
3
%
H
a
ssan
e
t
a
l
.
[
6
7
]
3
.
2
.
5
.
B
a
y
esia
n Ne
t
w
o
rk
(
B
N)
B
ay
e
s
ian
Net
w
o
r
k
(
B
N)
h
as
g
ain
ed
s
o
m
u
c
h
p
o
p
u
lar
it
y
in
f
i
n
an
ce
as
m
o
d
elli
n
g
to
o
ls
h
av
i
n
g
ab
ilit
y
to
s
o
lv
e
co
m
p
lex
p
r
o
b
le
m
s
in
v
o
l
v
i
n
g
t
h
e
p
r
o
b
ab
ilis
tic
a
n
al
y
s
i
s
u
n
d
er
u
n
ce
r
tai
n
t
y
.
B
N
is
p
r
o
b
ab
ilis
tic
g
r
ap
h
ical
m
o
d
els
t
h
at
r
ep
r
ese
n
t
a
s
et
o
f
r
a
n
d
o
m
v
ar
iab
les
f
o
r
a
g
i
v
e
n
p
r
o
b
lem
,
a
n
d
u
s
e
d
to
r
ep
r
esen
t
th
e
p
r
o
b
a
b
ilis
t
ic
r
elatio
n
s
h
ip
b
et
w
ee
n
t
h
e
m
[
3
0
]
,
[
68
]
.
Ho
w
e
v
er
,
th
e
B
N
s
tr
u
c
tu
r
e
ca
n
b
e
u
s
ed
to
p
r
ed
ict
th
e
p
o
s
s
ib
ilit
y
o
f
r
is
in
g
o
r
f
alli
n
g
m
ar
k
e
t
i
n
d
ex
o
r
s
to
c
k
p
r
ices
o
v
er
ti
m
e.
T
ab
le
7
s
h
o
w
s
t
h
e
d
escr
ip
tio
n
o
f
t
h
e
B
N
tech
n
iq
u
e
as
s
elec
ted
b
y
m
o
s
t
o
f
t
h
e
au
t
h
o
r
s
f
o
r
s
h
ar
e
f
o
r
ec
asti
n
g.
F
ig
u
r
e
1
s
h
o
w
s
p
r
ed
ictio
n
ac
cu
r
ac
y
o
f
alg
o
r
ith
m
s
s
i
n
ce
2
0
0
0
-
2
0
1
5
.
T
ab
le
7
.
P
er
f
o
r
m
a
n
ce
A
cc
u
r
ac
y
o
f
B
N
Me
th
o
d
M
e
t
h
o
d
R
e
su
l
t
s
A
u
t
h
o
r
s
D
B
N
8
9
%
W
a
n
g
e
t
a
l
.
[
2
6
]
BN
7
8
.
1
3
%
B
o
l
a
e
t
a
l
.
[
3
0
]
BN
9
2
%
N
a
sl
mo
sav
i
e
t
a
l
.
[
69
]
BN
6
0
%
Z
u
o
e
t
a
l
.
[
67
]
BN
8
2
.
4
6
%
K
i
t
a
e
t
a
l
.
[
37
]
BN
7
6
%
B
o
g
l
e
e
t
a
l
.
[
70
]
B
N
`
8
6
%
P
a
t
e
l
e
t
a
l
.
[
71
]
Fig
u
r
e
1
.
P
r
e
d
ictio
n
A
cc
u
r
ac
y
Gr
o
u
p
ed
b
y
A
l
g
o
r
it
h
m
s
Si
n
ce
2
0
0
0
-
2015
88
93
96.46
97
92
0
10
20
30
40
50
60
70
80
90
100
D
e
c
i
si
o
n
Tr
e
e
N
e
u
r
a
l
N
e
t
w
o
r
k
S
V
M
G
e
n
e
t
i
c
A
l
g
o
r
i
t
h
m
B
a
y
e
si
a
n
N
e
t
w
o
r
k
A
c
c
u
r
a
c
y
(
%
)
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
T
e
c
h
n
i
q
u
e
s
Pr
e
d
i
c
t
i
o
n
A
c
c
u
r
a
c
y
Gro
u
p
e
d
b
y
A
l
g
o
r
i
t
h
m
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
P
erfo
r
ma
n
ce
F
o
r
ec
a
s
tin
g
o
f S
h
a
r
e
Ma
r
ke
t U
s
in
g
Ma
ch
in
e
Lea
r
n
in
g
Tech
n
iq
u
es:
A
R
ev
iew
(
S
a
ch
in
K
a
mley
)
3201
4.
DIS
CU
SS
I
O
N
I
n
t
h
is
s
ec
tio
n
,
w
e
w
i
ll
d
is
c
u
s
s
t
h
e
r
es
u
lt
a
n
al
y
s
i
s
o
f
r
ec
en
t
w
o
r
k
s
i
n
p
r
ed
ictin
g
s
h
ar
e
p
er
f
o
r
m
a
n
ce
.
T
h
is
r
esear
ch
s
t
u
d
y
m
a
in
l
y
b
a
s
ed
o
n
th
e
h
i
g
h
est
ac
c
u
r
ac
y
o
f
p
r
ed
ictio
n
m
et
h
o
d
s
an
d
also
t
h
e
m
o
s
t
i
m
p
o
r
tan
t
f
ac
to
r
s
t
h
at
m
a
y
i
n
f
lu
e
n
ce
t
h
e
s
h
ar
e
p
er
f
o
r
m
an
c
e.
Fi
g
u
r
e
1
clea
r
l
y
s
ta
tes
t
h
at
th
e
g
e
n
e
tic
alg
o
r
it
h
m
(
G
A
)
m
et
h
o
d
h
as
t
h
e
h
i
g
h
e
s
t
p
r
ed
ictio
n
ac
c
u
r
ac
y
b
y
(
9
7
%)
f
o
llo
w
ed
b
y
S
u
p
p
o
r
t
Vec
to
r
Ma
ch
i
n
e
(
SVM)
b
y
(
9
6
.
4
6
%).
Nex
t,
Neu
r
al
Net
w
o
r
k
(
NN)
h
as
th
e
9
6
%
p
r
ed
ic
tio
n
ac
cu
r
ac
y
w
h
ic
h
is
s
li
g
h
tl
y
lo
w
er
th
a
n
SVM
m
et
h
o
d
.
Nex
t,
B
ay
e
s
ian
Net
wo
r
k
(
B
N)
h
as
th
e
9
2
%
p
r
e
d
ictio
n
ac
cu
r
ac
y
.
L
astl
y
,
th
e
m
et
h
o
d
th
at
h
as
lo
w
es
t
p
r
ed
ictio
n
ac
cu
r
ac
y
is
a
d
ec
i
s
io
n
tr
ee
b
y
(
8
8
%).
Ho
w
ev
er
,
th
e
r
es
u
lt
s
o
n
p
r
ed
ictio
n
ac
cu
r
ac
y
ar
e
d
ep
en
d
in
g
o
n
th
e
v
ar
iab
le
s
o
r
f
ea
tu
r
es t
h
at
w
er
e
u
s
ed
d
u
r
in
g
t
h
e
p
r
ed
ictio
n
p
r
o
ce
s
s
.
GA
m
eth
o
d
g
av
e
t
h
e
h
ig
h
es
t
p
r
ed
ictio
n
ac
cu
r
ac
y
.
T
h
e
m
a
in
attr
ib
u
tes
u
s
ed
d
u
r
i
n
g
t
h
e
p
r
ed
ictio
n
p
r
o
ce
s
s
ar
e
f
u
n
d
a
m
e
n
tal
v
ar
ia
b
les
w
h
ich
ar
e
1
y
ea
r
T
r
ea
s
u
r
y
B
ill
Yield
,
t
h
e
ea
r
n
in
g
s
p
er
s
h
ar
e,
d
i
v
id
en
d
p
er
s
h
ar
e
f
o
r
th
e
S
&
P
5
0
0
an
d
t
h
e
cu
r
r
en
t
w
ee
k
’
s
S
&
P
5
0
0
[
25
]
.
Nex
t,
SVM
m
et
h
o
d
h
as
th
e
s
ec
o
n
d
h
i
g
h
est
p
r
ed
ictio
n
ac
cu
r
ac
y
w
h
ich
u
s
e
d
th
e
tec
h
n
ical
p
ar
a
m
eter
s
a
s
p
r
ed
ictio
n
p
r
o
ce
s
s
.
T
h
e
m
ai
n
p
ar
am
eter
s
o
f
SV
M
m
et
h
o
d
ar
e
Mo
m
e
n
t
u
m
,
W
illi
a
m
s
’
s
%
R
,
R
ate
o
f
C
h
a
n
g
e
(
R
OC
)
,
5
d
a
y
d
is
p
ar
it
y
,
1
0
d
a
y
d
is
p
ar
it
y
,
Sto
c
h
asti
c
%K
an
d
P
r
ice
Vo
lu
m
e
T
r
en
d
(
P
V
T
)
[
51
],
[
5
3
],
[
59
]
.
Nex
t
is
a
NN
m
et
h
o
d
w
it
h
t
h
e
p
er
f
o
r
m
a
n
ce
ac
cu
r
ac
y
ar
o
u
n
d
(
9
6
%).
T
h
e
m
ain
p
ar
a
m
eter
s
u
s
ed
d
u
r
i
n
g
t
h
e
p
r
ed
ictio
n
p
r
o
ce
s
s
ar
e
Mo
v
in
g
Av
er
ag
e
(
M
A
)
,
s
to
ch
as
tic
lin
e,
W
MS
%R
in
d
ic
ato
r
(
R
-
i
n
d
ex
)
an
d
2
5
-
6
5
d
a
y
s
lag
g
ed
i
n
d
ex
d
ata
as
tec
h
n
ical
in
d
icat
o
r
s
[
5
1
]
.
Nex
t
is
th
e
B
N
m
et
h
o
d
w
it
h
t
h
e
p
er
f
o
r
m
a
n
ce
ac
c
u
r
ac
y
ar
o
u
n
d
(
9
2
%).
T
h
e
p
ar
a
m
eter
s
u
s
ed
d
u
r
i
n
g
t
h
e
p
r
ed
ictio
n
p
r
o
ce
s
s
ar
e
f
u
n
d
a
m
en
tal
p
ar
a
m
eter
s
ar
e
liq
u
id
it
y
r
atio
s
,
lev
er
a
g
e
r
at
io
s
,
p
r
o
f
itab
ilit
y
r
atio
s
a
n
d
o
th
er
f
ac
to
r
s
li
k
e
f
ir
m
's
s
ize
a
n
d
th
e
au
d
ito
r
'
s
o
p
in
io
n
.
Ot
h
er
s
,
p
ar
a
m
eter
s
ar
e
u
s
ed
d
u
r
in
g
t
h
e
B
N
p
r
ed
icti
o
n
p
r
o
ce
s
s
is
d
ail
y
up
-
d
o
w
n
on
t
h
e
s
to
c
k
in
d
e
x
o
n
th
e
n
ex
t d
a
y
as ta
k
en
a
s
r
an
d
o
m
v
ar
iab
les
f
o
r
th
e
B
N
m
o
d
el
[
68
]
.
L
ast
l
y
,
t
h
e
m
et
h
o
d
h
as
t
h
e
l
o
w
est
p
r
ed
ictio
n
ac
cu
r
ac
y
is
a
Dec
is
io
n
T
r
ee
(
D
T
)
b
y
(
8
8
%).
T
h
e
v
ar
iab
les
u
s
ed
ar
e
i
n
co
m
e
s
ta
te
m
e
n
t
o
f
t
h
e
las
t
t
w
o
y
ea
r
s
,
ex
p
o
r
t
g
r
o
w
th
r
ate,
i
m
p
o
r
t
g
r
o
w
t
h
r
ate,
ea
r
n
in
g
af
ter
tax
m
ar
g
i
n
,
cu
r
r
e
n
t
r
atio
,
Mo
v
in
g
A
v
er
a
g
e
(
M
A
)
,
R
el
ativ
e
Stre
n
g
th
I
n
d
e
x
(
R
SI)
,
E
x
p
o
n
en
t
ial
Mo
v
i
n
g
Av
er
ag
e
(
E
M
A
)
,
lo
n
g
ter
m
i
n
ter
est
r
ates,
a
n
d
Gr
o
s
s
Do
m
est
ic
P
r
o
d
u
ct
(
GDP
)
etc
[
48
]
.
Ho
w
ev
er
,
th
e
s
e
attr
ib
u
tes
ar
e
also
u
s
ed
a
m
o
n
g
all
p
r
ed
ictio
n
m
eth
o
d
s
,
b
u
t
th
e
r
es
u
lt
s
h
o
w
ed
th
at
DT
m
eth
o
d
g
av
e
h
i
g
h
es
t
p
r
ed
i
ctio
n
ac
cu
r
ac
y
as
co
m
p
a
r
ed
to
o
th
er
m
e
th
o
d
s
.
T
h
is
is
b
ec
au
s
e
f
o
r
s
h
o
r
t
ter
m
f
o
r
ec
asti
n
g
DT
m
e
th
o
d
p
er
f
o
r
m
s
o
u
ts
ta
n
d
i
n
g
an
d
v
a
r
iab
les
u
s
ed
ar
e
s
ig
n
i
f
ica
n
t
w
it
h
ea
ch
o
th
er
w
h
e
n
th
e
D
T
m
o
d
el
u
s
i
n
g
a
s
a
p
r
ed
ictio
n
p
r
o
ce
s
s
.
4.
CO
NCLU
SI
O
N
AND
F
U
T
U
RE
SCO
P
E
S
Sh
ar
e
p
r
ice
f
o
r
ec
asti
n
g
is
an
i
m
p
o
r
ta
n
t
is
s
u
e
i
n
f
i
n
a
n
ce
b
ec
au
s
e
it
w
ill
b
e
m
o
ti
v
ati
n
g
i
n
v
esto
r
s
an
d
b
r
o
k
er
s
to
in
v
est
m
o
n
e
y
i
n
th
e
m
ar
k
et.
T
h
is
r
esear
ch
s
tu
d
y
m
ain
l
y
r
ev
ie
w
ed
p
r
ev
io
u
s
s
t
u
d
ies
o
n
f
o
r
ec
asti
n
g
s
h
ar
e
p
er
f
o
r
m
a
n
ce
w
it
h
v
ar
io
u
s
p
r
ed
ictio
n
m
et
h
o
d
s
an
d
s
t
u
d
y
r
e
v
ea
ls
t
h
at
m
o
s
t
o
f
th
e
r
es
ea
r
ch
er
s
h
a
v
e
u
s
ed
tech
n
ical
p
ar
a
m
e
ter
s
a
s
p
r
ed
ictio
n
p
r
o
ce
s
s
.
O
th
er
s
h
av
e
u
s
e
d
f
u
n
d
a
m
en
tal
a
n
d
m
ac
r
o
ec
o
n
o
m
ic
p
ar
a
m
eter
s
a
s
p
r
ed
ictio
n
p
r
o
ce
s
s
.
So
m
e
r
es
ea
r
ch
er
s
h
a
v
e
a
ls
o
u
s
ed
la
g
g
ed
in
d
e
x
v
ar
iab
les
as
d
ata
s
et.
T
h
er
ef
o
r
e
,
th
e
p
r
ed
ictio
n
tech
n
iq
u
e
s
G
A
,
SV
M
an
d
NN
h
a
v
e
b
ee
n
f
r
eq
u
e
n
tl
y
u
s
ed
b
y
r
esear
ch
er
s
i
n
t
h
e
s
h
ar
e
m
ar
k
et
ar
ea
.
B
ased
o
n
t
h
e
a
n
al
y
s
is
,
it
i
s
al
s
o
o
b
s
er
v
ed
th
at
a
h
y
b
r
id
m
o
d
e
l
h
a
s
a
b
etter
p
r
ed
ictio
n
ac
cu
r
ac
y
as
co
m
p
ar
ed
to
in
d
iv
id
u
al
m
o
d
el.
A
t
last
,
t
h
is
r
e
s
ea
r
ch
s
t
u
d
y
w
i
ll
b
e
m
o
t
iv
ated
to
ca
r
r
y
o
u
t
f
u
r
th
er
r
esear
ch
o
n
s
h
ar
e
m
ar
k
e
t
p
r
o
b
lem
as
w
e
ll a
s
m
o
t
iv
at
in
g
t
h
e
s
h
ar
e
u
s
er
s
to
m
o
n
ito
r
th
e
s
h
ar
e
p
er
f
o
r
m
an
ce
i
n
a
s
y
s
te
m
at
ic
w
a
y
.
RE
F
E
R
E
NC
E
S
[1
]
A.
P
.
Da
s,
“
S
e
c
u
rit
y
a
n
a
l
y
sis
a
n
d
p
o
rtf
o
li
o
M
a
n
a
g
e
m
e
n
t
,
”
I.
K.
In
ter
n
a
ti
o
n
a
l
Pu
b
li
c
a
ti
o
n
,
3
rd
E
d
it
i
o
n
,
Ne
w
De
lh
i
,
In
d
ia,
2
0
0
8
.
[2
]
P
.
K.
P
h
u
a
,
e
t
a
l
.
,
“
F
o
re
c
a
stin
g
S
to
c
k
In
d
e
x
In
c
re
m
e
n
ts
Us
in
g
Ne
u
ra
l
Ne
tw
o
rk
s
w
it
h
T
ru
st
Re
g
io
n
M
e
t
h
o
d
s
,
”
Pro
c
e
e
d
in
g
s
o
f
t
h
e
In
ter
n
a
ti
o
n
a
l
J
o
in
t
C
o
n
fer
e
n
c
e
o
n
Ne
u
r
a
l
Ne
tw
o
rk
s
,
v
o
l.
1
,
p
p
.
2
6
0
-
2
6
5
,
2
0
0
3
.
[3
]
S
.
Ra
jas
e
k
a
r
a
n
,
e
t
a
l
.
,
“
Ne
u
ra
l
Ne
tw
o
rk
s,
F
u
z
z
y
L
o
g
ic,
a
n
d
Ge
n
e
ti
c
A
l
g
o
rit
h
m
s
S
y
n
th
e
sis
a
n
d
A
p
p
li
c
a
ti
o
n
s
,
”
PHI
L
e
a
rn
in
g
Priv
a
te L
imit
e
d
,
10
th
Ed
it
io
n
,
Ne
w
De
lh
i
,
In
d
ia,
2
0
0
8
.
[4
]
B.
Kitch
e
n
h
a
m
,
e
t
a
l
.
,
“
S
y
ste
m
a
ti
c
L
it
e
ra
tu
re
Re
v
ie
ws
in
S
o
f
tw
a
re
En
g
i
n
e
e
rin
g
-
A
T
e
rti
a
r
y
S
tu
d
y
,
”
In
f.
S
o
ft
w.
T
e
c
h
n
o
l
.
,
v
ol
/
issu
e
:
5
2
(8
)
,
p
p
.
7
9
2
-
8
0
5
,
2
0
1
0
.
[5
]
Z.
H.
K
h
a
n
,
e
t
a
l
.
,
“
P
rice
P
re
d
i
c
ti
o
n
o
f
S
h
a
re
M
a
rk
e
t
Us
in
g
A
rti
f
icia
l
Ne
u
ra
l
Ne
t
w
o
rk
(A
N
N)
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
Co
m
p
u
ter
A
p
p
l
ica
ti
o
n
s,
v
ol
/i
ss
u
e
:
22
(
2
),
p
p
.
5
6
-
6
1
,
2
0
1
1
.
[6
]
T.
S
.
Ch
a
n
g
,
“
A
Co
m
p
a
ra
ti
v
e
S
t
u
d
y
o
f
A
rti
f
icia
l
Ne
u
ra
l
Ne
t
w
o
rk
s
a
n
d
De
c
isio
n
T
r
e
e
s
f
o
r
Dig
it
a
l
G
a
m
e
Co
n
ten
t
S
to
c
k
s P
rice
P
re
d
icti
o
n
,
”
Ex
p
e
rt
S
y
ste
ms
wit
h
Ap
p
li
c
a
ti
o
n
s,
v
o
l
.
3
8
,
p
p
.
1
4
8
4
6
-
1
4
8
5
1
,
2
0
1
1
.
[7
]
M
.
S
h
a
f
iee
,
e
t
a
l
.
,
“
F
o
re
c
a
stin
g
S
to
c
k
Re
tu
rn
s
Us
i
n
g
S
u
p
p
o
rt
V
e
c
t
o
r
M
a
c
h
i
n
e
a
n
d
De
c
isio
n
T
re
e
:
A
Ca
se
S
tu
d
y
in
Ira
n
S
to
c
k
Ex
c
h
a
n
g
e
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Eco
n
o
my
,
M
a
n
a
g
e
me
n
t
a
n
d
S
o
c
ia
l
S
c
ien
c
e
s,
v
ol
/i
ss
u
e
:
2
(9
),
p
p
.
746
-
7
5
1
,
2
0
1
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
6
,
No
.
6
,
Dec
em
b
er
2
0
1
6
:
3
196
–
3
204
3202
[8
]
P
.
C.
C
h
a
n
g
,
e
t
a
l
.
,
“
A
n
in
v
e
sti
g
a
ti
o
n
o
f
th
e
Hy
b
rid
F
o
re
c
a
stin
g
M
o
d
e
ls
f
o
r
S
to
c
k
P
rice
V
a
riati
o
n
i
n
T
a
iw
a
n
,
”
J
o
u
rn
a
l
o
f
th
e
C
h
i
n
e
se
In
stit
u
te o
f
In
d
u
stria
l
En
g
in
e
e
rin
g
,
v
ol
/i
ss
u
e
:
21
(
4
),
p
p
.
3
5
8
–
3
6
8
,
2
0
0
4
.
[9
]
A
.
Ge
p
p
,
e
t
a
l
.
,
“
P
re
d
ictin
g
F
i
n
a
n
c
ial
Distre
ss
:
A
Co
m
p
a
riso
n
o
f
S
u
rv
iv
a
l
A
n
a
l
y
si
s
a
n
d
De
c
isio
n
T
re
e
T
e
c
h
n
iq
u
e
s
,
”
El
e
v
e
n
th
In
ter
n
a
ti
o
n
a
l
M
u
lt
i
-
C
o
n
fer
e
n
c
e
o
n
In
fo
rm
a
t
io
n
Pro
c
e
ss
in
g
,
2
0
1
5
,
IM
CIP
2
0
1
5
.
P
ro
c
e
d
ia
Co
m
p
u
ter
S
c
ien
c
e
,
v
o
l.
5
4
,
p
p
.
3
9
6
–
4
0
4
,
2
0
1
5
.
[1
0
]
M
.
C.
W
u
,
e
t
a
l
.
,
“
A
n
Ef
fe
c
ti
v
e
A
p
p
li
c
a
ti
o
n
o
f
De
c
isio
n
T
re
e
to
S
to
c
k
T
ra
d
in
g
,
”
Exp
e
rt
S
y
ste
ms
wi
th
A
p
p
l
ica
ti
o
n
s,
v
o
l.
3
1
,
p
p
.
2
7
0
–
2
7
4
,
2
0
0
6
.
[1
1
]
C.
F
.
T
sa
i
,
et
al
.
,
“
Co
m
b
in
in
g
M
u
lt
ip
le
F
e
a
tu
re
S
e
lec
ti
o
n
M
e
t
h
o
d
s
f
o
r
S
to
c
k
P
re
d
icti
o
n
:
Un
io
n
,
in
ters
e
c
ti
o
n
,
a
n
d
M
u
lt
i
In
ters
e
c
ti
o
n
A
p
p
ro
a
c
h
e
s
,
”
De
c
isio
n
S
u
p
p
o
rt
S
y
ste
ms
,
v
o
l.
5
0
,
p
p
.
2
5
8
-
2
6
9
,
2
0
1
0
.
[1
2
]
N.
Re
n
,
e
t
a
l
.
,
“
A
De
c
isio
n
T
r
e
e
b
a
se
d
Clas
si
f
ica
ti
o
n
A
p
p
ro
a
c
h
to
Ru
le
Ex
trac
ti
o
n
f
o
r
S
e
c
u
rit
y
A
n
a
l
y
sis
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
I
n
fo
rm
a
t
io
n
T
e
c
h
n
o
lo
g
y
a
n
d
De
c
isio
n
M
a
k
in
g
,
v
ol
/i
ss
u
e
:
5
(1
),
p
p
.
2
2
7
-
2
4
0
,
2
0
0
6
.
[1
3
]
C.
F.
T
sa
i
,
e
t
a
l
.
,
“
De
term
in
a
n
ts
o
f
In
tan
g
ib
le
A
ss
e
ts
V
a
lu
e
:
T
h
e
Da
ta
M
in
in
g
A
p
p
ro
a
c
h
,
”
Kn
o
wled
g
e
B
a
se
d
S
y
ste
ms
,
v
o
l.
3
1
,
p
p
.
6
7
-
7
7
,
2
0
1
2
.
[1
4
]
S.
H.
Ch
u
n
,
e
t
a
l
.
,
“
A
u
to
m
a
ted
G
e
n
e
r
a
ti
o
n
o
f
Ne
w
Kn
o
w
led
g
e
to
S
u
p
p
o
rt
M
a
n
a
g
e
rial
De
c
isio
n
M
a
k
in
g
:
Ca
se
S
tu
d
y
in
F
o
re
c
a
stin
g
a
S
to
c
k
M
a
r
k
e
t
,
”
Exp
e
rt S
y
ste
ms
,
v
ol
/i
ss
u
e
:
2
1
(4
),
p
p
.
1
9
2
-
2
0
7
,
2
0
0
4
.
[1
5
]
M
.
Ka
ra
z
m
o
d
e
h
,
e
t
a
l
.
,
“
S
to
c
k
P
rice
F
o
re
c
a
stin
g
Us
in
g
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
s
a
n
d
Im
p
ro
v
e
d
P
a
rti
c
le
S
w
a
r
m
Op
ti
m
iza
ti
o
n
,
”
J
o
u
rn
a
l
o
f
A
u
t
o
ma
ti
o
n
a
n
d
Co
n
tro
l
En
g
in
e
e
rin
g
,
v
ol
/i
ss
u
e
:
1
(2
)
,
p
p
.
1
7
3
-
1
7
6
,
2
0
1
3
.
[1
6
]
R.
A
.
Ri
v
e
ra
,
e
t
a
l
.
,
“
G
e
n
e
ti
c
A
lg
o
rit
h
m
s
a
n
d
Da
r
w
in
ian
A
p
p
ro
a
c
h
e
s
in
F
i
n
a
n
c
ial
A
p
p
li
c
a
ti
o
n
s:
A
s
u
rv
e
y
,
”
Exp
e
rt
S
y
ste
ms
wit
h
Ap
p
li
c
a
ti
o
n
s
,
v
ol
/
issu
e
:
4
2
(2
1
),
p
p
.
7
6
8
4
-
7
6
9
7
,
2
0
1
5
.
[1
7
]
S
.
Ch
e
n
,
e
t
a
l
.
,
“
A
H
y
b
rid
A
p
p
r
o
a
c
h
o
f
S
tep
w
ise
Re
g
re
ss
io
n
,
L
o
g
isti
c
Re
g
re
ss
io
n
,
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
,
a
n
d
De
c
isio
n
T
re
e
f
o
r
F
o
re
c
a
stin
g
F
ra
u
d
u
len
t
F
in
a
n
c
ial
S
tate
m
e
n
ts
,
”
S
c
ien
ti
fi
c
W
o
rld
J
o
u
r
n
a
l
,
p
p
.
1
-
9
,
2
0
1
4
.
[1
8
]
S
.
Kirk
o
s
,
e
t
a
l
.
,
“
Da
ta
M
i
n
in
g
T
e
c
h
n
iq
u
e
s
f
o
r
th
e
De
tec
ti
o
n
o
f
F
ra
u
d
u
le
n
t
F
in
a
n
c
ial
S
tate
m
e
n
ts
,
”
Exp
e
rt
S
y
ste
ms
wit
h
A
p
p
l
ica
ti
o
n
s
,
v
ol
/i
ss
u
e
:
32
(
4
),
p
p
.
9
9
5
–
1
0
0
3
,
2
0
0
7
.
[1
9
]
S
.
Ba
ra
k
,
e
t
a
l
.
,
“
De
v
e
lo
p
in
g
a
n
A
p
p
ro
a
c
h
to
Ev
a
lu
a
te
S
t
o
c
k
s
b
y
F
o
re
c
a
stin
g
Eff
e
c
ti
v
e
F
e
a
tu
re
s
w
i
th
Da
ta
M
in
i
n
g
M
e
th
o
d
s
,
”
Exp
e
rt
S
y
ste
ms
wit
h
A
p
p
li
c
a
ti
o
n
s,
v
o
l
.
4
2
,
p
p
.
1
3
2
5
-
1
3
3
9
,
2
0
1
5
.
[2
0
]
R
Biso
i
,
e
t
a
l
.
,
“
A
H
y
b
rid
Ev
o
lu
ti
o
n
a
ry
D
y
n
a
m
ic
N
e
u
ra
l
Ne
t
w
o
rk
f
o
r
S
to
c
k
M
a
rk
e
t
T
re
n
d
A
n
a
l
y
sis
a
n
d
P
re
d
icti
o
n
Us
in
g
Un
sc
e
n
ted
Ka
lm
a
n
F
il
ter
,
”
Ap
p
li
e
d
S
o
ft
Co
mp
u
ti
n
g
,
v
o
l.
1
9
,
p
p
.
4
1
–
5
6
,
2
0
1
4
.
[2
1
]
S.
O.
Ola
tu
n
ji
,
e
t
al
.
,
“
F
o
re
c
a
stin
g
th
e
S
a
u
d
i
A
ra
b
ia
S
to
c
k
P
rice
s
b
a
se
d
o
n
A
r
ti
f
icia
l
Ne
u
ra
l
N
e
t
w
o
rk
s
M
o
d
e
l
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
I
n
telli
g
e
n
t
In
fo
rm
a
t
io
n
S
y
ste
ms
,
v
ol
/i
ss
u
e
:
2
(5
)
,
p
p
.
7
7
-
8
6
,
2
0
1
3
.
[2
2
]
C.
J.
Hu
a
n
g
,
e
t
a
l
.
,
“
A
p
p
li
c
a
ti
o
n
o
f
W
ra
p
p
e
r
A
p
p
ro
a
c
h
a
n
d
Co
m
p
o
site
Clas
sif
ier
to
t
h
e
S
t
o
c
k
T
re
n
d
P
re
d
icti
o
n
,
”
Exp
e
rt S
y
ste
ms
wit
h
A
p
p
l
ica
ti
o
n
s,
v
o
l.
3
4
,
p
p
.
2
8
7
0
-
2
8
7
8
,
2
0
0
8
.
[2
3
]
D.
Ch
a
n
d
w
a
n
i
,
e
t
a
l
.
,
“
S
to
c
k
Dire
c
ti
o
n
F
o
re
c
a
stin
g
Tec
h
n
iq
u
e
s:
A
n
Em
p
iri
c
a
l
S
tu
d
y
Co
m
b
in
in
g
M
a
c
h
in
e
L
e
a
rn
in
g
S
y
st
e
m
w
it
h
M
a
rk
e
t
In
d
ica
to
rs
i
n
th
e
I
n
d
ia
n
Co
n
tex
t
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
C
o
mp
u
ter
A
p
p
li
c
a
ti
o
n
s,
v
ol
/i
ss
u
e
:
9
2
(
1
1
),
p
p
.
7
8
-
8
4
,
2
0
1
4
.
[2
4
]
A
.
F
a
n
,
e
t
a
l
.
,
“
S
to
c
k
S
e
lec
ti
o
n
Us
in
g
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
s
,
”
In
ter
n
a
ti
o
n
a
l
J
o
i
n
t
Co
n
fer
e
n
c
e
o
n
Ne
u
ra
l
Ne
two
rk
s,
W
a
sh
in
g
to
n
,
IJCN
N 2
0
0
1
.
v
o
l.
3
,
p
p
.
1
7
9
3
-
1
7
9
8
,
2
0
0
1
.
[2
5
]
K.
Ja
d
a
v
,
e
t
a
l
.
,
“
Op
ti
m
izin
g
Weig
h
ts
o
f
A
rti
f
icia
l
Ne
u
ra
l
Ne
t
wo
rk
s
Us
in
g
G
e
n
e
ti
c
A
lg
o
rit
h
m
s
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
Res
e
a
rc
h
i
n
Co
mp
u
ter
S
c
ien
c
e
a
n
d
El
e
c
tro
n
ics
En
g
in
e
e
rin
g
,
v
ol
/i
ss
u
e
:
1
(
1
0
),
p
p
.
4
7
-
5
1
,
2
0
1
2
.
[2
6
]
L
.
W
a
n
g
,
e
t
a
l
.
,
“
S
to
c
k
M
a
rk
e
t
T
re
n
d
P
re
d
icti
o
n
Us
i
n
g
D
y
n
a
m
i
c
Ba
y
e
sia
n
F
a
c
to
r
G
r
a
p
h
,
”
Exp
e
rt
S
y
ste
ms
wit
h
Ap
p
li
c
a
ti
o
n
s
,
v
ol
/i
ss
u
e
:
4
2
(
1
5
-
1
6
)
,
p
p
.
6
2
6
7
-
6
2
7
5
,
2
0
1
5
.
[2
7
]
T
.
H.
Ro
h
,
“
F
o
re
c
a
stin
g
th
e
v
o
l
a
ti
li
ty
o
f
sto
c
k
p
rice
in
d
e
x
,
”
Exp
e
rt
S
y
ste
ms
wit
h
Ap
p
li
c
a
ti
o
n
s:
A
n
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
,
v
o
l
.
3
3
,
p
p
.
9
1
6
-
9
2
2
,
2
0
0
7
.
[2
8
]
A
.
I
.
Diler,
“
P
re
d
ictin
g
Dire
c
ti
o
n
o
f
IS
E
Na
ti
o
n
a
l
-
1
0
0
In
d
e
x
w
it
h
Ba
c
k
P
ro
p
a
g
a
ti
o
n
T
ra
in
e
d
Ne
u
ra
l
Ne
t
w
o
rk
,
”
J
o
u
rn
a
l
o
f
Ista
n
b
u
l
S
to
c
k
Exc
h
a
n
g
e
,
v
ol
/i
ss
u
e
:
7
(2
5
),
p
p
.
6
5
-
8
1
,
2
0
0
3
.
[2
9
]
Y.
Ka
ra
,
e
t
a
l
.
,
“
P
re
d
icti
n
g
Dire
c
ti
o
n
o
f
S
to
c
k
P
rice
In
d
e
x
M
o
v
e
m
e
n
t
U
sin
g
A
rti
f
icia
l
N
e
u
ra
l
Ne
tw
o
rk
s
a
n
d
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
s:
T
h
e
S
a
m
p
le
o
f
th
e
Ista
n
b
u
l
S
t
o
c
k
Ex
c
h
a
n
g
e
,
”
Exp
e
rt
S
y
ste
ms
wit
h
Ap
p
li
c
a
ti
o
n
s,
v
o
l.
3
8
,
p
p
.
5
3
1
1
-
5
3
1
9
,
2
0
1
1
.
[3
0
]
A.
A
.
Bo
la,
e
t
a
l
.
,
“
F
o
re
c
a
stin
g
M
o
v
e
m
e
n
t
o
f
th
e
Nig
e
rian
S
to
c
k
Ex
c
h
a
n
g
e
A
ll
S
h
a
re
In
d
e
x
Us
in
g
A
rti
f
icia
l
Ne
u
ra
l
a
n
d
Ba
y
e
sia
n
Ne
t
w
o
rk
s
,
”
J
o
u
rn
a
l
o
f
Fi
n
a
n
c
e
a
n
d
I
n
v
e
stme
n
t
An
a
ly
sis,
v
ol
/i
ss
u
e
:
2
(1
),
p
p
.
4
1
-
5
9
,
2
0
1
3
.
[3
1
]
D.
Oliv
e
ira
,
e
t
a
l
.
,
“
A
p
p
ly
in
g
Artif
icia
l
Ne
u
ra
l
Ne
t
w
o
rk
s
to
p
re
d
ictio
n
o
f
S
to
c
k
P
rice
a
n
d
Im
p
ro
v
e
m
e
n
t
o
f
th
e
Dire
c
ti
o
n
a
l
P
re
d
icti
o
n
In
d
e
x
-
Ca
se
S
tu
d
y
o
f
P
ET
R4
,
P
e
tro
b
ra
s,
Bra
z
il
,
”
Exp
e
rt
S
y
ste
m
wit
h
Ap
p
li
c
a
ti
o
n
s,
v
o
l.
4
0
,
p
p
.
7
5
9
6
-
7
6
0
6
,
2
0
1
3
.
[3
2
]
J.
H.
Ch
e
n
g
,
e
t
a
l
.
,
“
A
H
y
b
rid
F
o
re
c
a
st
M
a
rk
e
ti
n
g
T
i
m
in
g
M
o
d
e
l
b
a
se
d
o
n
P
r
o
b
a
b
il
isti
c
Ne
u
ra
l
Ne
tw
o
rk
(P
NN
)
,
Ro
u
g
h
se
t
a
n
d
C
4
.
5
,
”
Exp
e
rt S
y
st
e
ms
wit
h
Ap
p
li
c
a
ti
o
n
s,
v
o
l.
3
7
,
p
p
.
1
8
1
4
-
1
8
2
0
,
2
0
1
0
.
[3
3
]
L.
G
.
Ca
o
,
e
t
a
l
.,
“
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
w
it
h
A
d
a
p
ti
v
e
P
a
ra
m
e
ters
in
F
in
a
n
c
ial
T
i
m
e
S
e
ries
F
o
re
c
a
stin
g
,
”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Ne
u
ra
l
Ne
two
rk
s,
v
ol
/i
ss
u
e
:
14
(
6
),
p
p
.
1
5
0
6
-
1
5
1
8
,
2
0
0
3
.
[3
4
]
M
.
Ka
ra
z
m
o
d
e
h
,
e
t
a
l
.
,
“
S
to
c
k
P
rice
F
o
re
c
a
stin
g
Us
in
g
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
s
a
n
d
Im
p
ro
v
e
d
P
a
rti
c
le
S
w
a
r
m
Op
ti
m
iza
ti
o
n
,
”
J
o
u
rn
a
l
o
f
A
u
t
o
ma
ti
o
n
a
n
d
Co
n
tro
l
En
g
in
e
e
rin
g
,
v
ol
/i
ss
u
e
:
1
(2
)
,
p
p
.
1
7
3
-
1
7
6
,
2
0
1
3
.
[3
5
]
R.
A
.
Ri
v
e
ra
,
e
t
a
l
.
,
“
G
e
n
e
ti
c
A
lg
o
rit
h
m
s
a
n
d
Da
r
w
in
ian
A
p
p
ro
a
c
h
e
s
in
F
in
a
n
c
ial
A
p
p
li
c
a
ti
o
n
s:
A
s
u
rv
e
y
,
”
Exp
e
rt
S
y
ste
ms
wit
h
Ap
p
li
c
a
ti
o
n
s,
v
ol
/i
ss
u
e
:
42
(2
1
),
p
p
.
7
6
8
4
-
7
6
9
7
,
2
0
1
5
.
[3
6
]
K.
Kim
,
e
t
a
l
.
,
“
G
e
n
e
ti
c
A
l
g
o
rit
h
m
s
A
p
p
ro
a
c
h
to
F
e
a
t
u
re
Disc
re
ti
z
a
ti
o
n
i
n
A
rti
f
icia
l
N
e
u
ra
l
Ne
tw
o
rk
s
f
o
r
th
e
P
re
d
ictio
n
o
f
S
t
o
c
k
P
r
ice
In
d
e
x
,
”
Exp
e
rt S
y
ste
ms
wit
h
A
p
p
l
ica
ti
o
n
s,
v
ol
/i
ss
u
e
:
19
(2
)
,
p
p
.
1
2
5
-
1
3
2
,
2
0
0
0
.
[3
7
]
E.
Ki
ta
,
e
t
a
l
.
,
“
A
p
p
li
c
a
ti
o
n
o
f
Ba
y
e
sia
n
Ne
t
w
o
rk
to
S
to
c
k
P
rice
P
re
d
ictio
n
,
”
Arti
fi
c
ia
l
In
telli
g
e
n
c
e
Res
e
a
rc
h
,
v
ol
/i
ss
u
e
:
1
(
2
),
p
p
.
1
7
1
-
1
8
4
,
2
0
1
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
P
erfo
r
ma
n
ce
F
o
r
ec
a
s
tin
g
o
f S
h
a
r
e
Ma
r
ke
t U
s
in
g
Ma
ch
in
e
Lea
r
n
in
g
Tech
n
iq
u
es:
A
R
ev
iew
(
S
a
ch
in
K
a
mley
)
3203
[3
8
]
C.
F
.
T
sa
i
,
e
t
a
l
.
,
“
S
to
c
k
P
ric
e
F
o
re
c
a
stin
g
b
y
H
y
b
rid
M
a
c
h
in
e
L
e
a
rn
in
g
T
e
c
h
n
iq
u
e
s
,
”
Pro
c
e
e
d
in
g
s
o
f
th
e
In
ter
n
a
t
io
n
a
l
M
u
lt
i
Co
n
fer
e
n
c
e
o
f
En
g
i
n
e
e
rs
a
n
d
Co
mp
u
ter
S
c
ien
t
ists,
Ho
n
g
Ko
n
g
,
2
0
0
9
,
IM
ECS
2
0
0
9
,
v
o
l.
1
,
p
p
.
57
-
64
,
2
0
0
9
.
[3
9
]
P.
M
.
T
sa
n
g
,
e
t
a
l
.
,
“
De
sig
n
a
n
d
Im
p
le
m
e
n
tatio
n
o
f
NN
5
f
o
r
Ho
n
g
Ko
n
g
S
to
c
k
P
rice
F
o
re
c
a
stin
g
,
”
En
g
in
e
e
ri
n
g
Ap
p
li
c
a
ti
o
n
s
o
f
Arti
f
icia
l
I
n
telli
g
e
n
c
e
,
v
o
l.
2
0
,
p
p
.
4
5
3
-
4
6
1
,
2
0
0
7
.
[4
0
]
S.
R.
S
tan
se
ll
,
e
t
a
l
.
,
“
F
o
re
c
a
sti
n
g
th
e
Dire
c
ti
o
n
o
f
Ch
a
n
g
e
in
S
e
c
to
r
S
to
c
k
In
d
e
x
e
s:
A
n
A
p
p
li
c
a
ti
o
n
o
f
Ne
u
ra
l
Ne
tw
o
rk
s
,
”
J
o
u
rn
a
l
o
f
Asse
t
M
a
n
a
g
e
me
n
t,
v
ol
/i
ss
u
e
:
5
(1
),
p
p
.
3
7
-
4
8
,
2
0
0
4
.
[4
1
]
A.
S.
Ch
e
n
,
e
t
a
l
.
,
“
A
p
p
li
c
a
ti
o
n
o
f
Ne
u
ra
l
Ne
t
w
o
rk
s
to
a
n
Em
e
r
g
in
g
F
in
a
n
c
ial
M
a
rk
e
t:
F
o
re
c
a
stin
g
a
n
d
T
ra
d
in
g
th
e
T
a
i
w
a
n
S
to
c
k
In
d
e
x
,
”
Co
mp
u
t.
Op
e
r.
Res
,
v
ol
/i
ss
u
e
:
3
0
(6
)
,
p
p
.
9
0
1
-
9
2
3
,
2
0
0
3
.
[4
2
]
S.
A
.
Ha
m
id
,
e
t
a
l
.
,
“
Us
in
g
Ne
u
ra
l
Ne
t
w
o
rk
s
f
o
r
F
o
re
c
a
stin
g
V
o
la
ti
li
ty
o
f
S
&
P
5
0
0
I
n
d
e
x
F
u
t
u
re
P
rice
s
,
”
J
o
u
rn
a
l
o
f
B
u
sin
e
ss
Res
e
a
rc
h
,
v
ol
/i
ss
u
e
:
5
7
(1
0
),
p
p
.
1
1
1
6
-
1
1
2
5
,
2
0
0
4
.
[4
3
]
W
.
Hu
a
n
g
,
e
t
a
l
.
,
“
Ne
u
ra
l
Ne
t
w
o
rk
s
in
F
in
a
n
c
e
a
n
d
Eco
n
o
m
ics
F
o
re
c
a
stin
g
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
De
c
isio
n
M
a
k
in
g
,
v
ol
/i
ss
u
e
:
6
(1
),
p
p
.
1
1
3
-
1
4
0
,
2
0
0
7
.
[4
4
]
R.
T
.
G
o
n
z
a
lez
,
e
t
a
l
.
,
“
En
se
m
b
le
S
y
ste
m
b
a
se
d
o
n
G
e
n
e
ti
c
A
lg
o
rit
h
m
f
o
r
S
to
c
k
M
a
rk
e
t
F
o
re
c
a
stin
g
,
”
IEE
E
Co
n
g
re
ss
o
n
Evo
lu
ti
o
n
a
ry
Co
m
p
u
ta
ti
o
n
(
CEC),
S
e
n
d
a
i,
p
p
.
3
1
0
2
-
3
1
0
8
,
2
0
1
5
.
[4
5
]
Q.
Ca
o
,
e
t
a
l
.
,
“
Ne
u
ra
l
Ne
tw
o
rk
Earn
in
g
s
p
e
r
S
h
a
re
F
o
re
c
a
stin
g
M
o
d
e
ls:
A
Co
m
p
a
riso
n
o
f
Ba
c
k
w
a
rd
P
ro
p
a
g
a
ti
o
n
a
n
d
t
h
e
G
e
n
e
ti
c
A
lg
o
rit
h
m
,
”
De
c
i
sio
n
S
u
p
p
o
rt S
y
ste
ms
,
v
ol
/i
ss
u
e
:
4
7
(1
),
p
p
.
3
2
–
4
1
,
2
0
0
9
.
[4
6
]
M
.
Ha
ss
a
n
,
“
S
t
o
c
k
M
a
rk
e
t
F
o
r
e
c
a
stin
g
Us
in
g
Hid
d
e
n
M
a
rk
o
v
M
o
d
e
l:
A
Ne
w
A
p
p
ro
a
c
h
,
”
i
n
IEE
E
Ed
it
o
r
,
Pro
c
e
e
d
in
g
s
o
f
t
h
e
5
th
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
In
tell
ig
e
n
t
S
y
ste
ms
De
sig
n
a
n
d
Ap
p
li
c
a
ti
o
n
s,
2
0
0
5
.
[4
7
]
O.
Ja
n
g
m
in
,
e
t
a
l
.
,
“
S
t
o
c
k
T
ra
d
in
g
b
y
M
o
d
e
ll
in
g
P
rice
T
re
n
d
w
it
h
Dy
n
a
m
ic
B
a
y
e
sia
n
Ne
t
w
o
rk
s
,
”
i
n
IDEAL
,
p
p
.
794
-
7
9
9
,
2
0
0
4
.
[4
8
]
C.
Y.
Hu
a
n
g
,
e
t
a
l
.
,
“
A
p
p
li
c
a
ti
o
n
o
f
In
teg
ra
ted
Da
ta
M
in
i
n
g
T
e
c
h
n
iq
u
e
s
in
S
to
c
k
M
a
rk
e
t
F
o
re
c
a
stin
g
,
”
Co
g
e
n
t
Eco
n
o
mic
s
a
n
d
Fi
n
a
n
c
e
,
v
ol
/i
ss
u
e
:
2
(9
2
9
5
),
p
p
.
1
-
1
8
,
2
0
1
4
.
[4
9
]
C.
F
.
T
sa
i
,
e
t
a
l
.
,
“
De
term
in
a
n
ts
o
f
In
tan
g
ib
le
A
ss
e
ts
V
a
lu
e
:
T
h
e
Da
ta
M
in
in
g
A
p
p
ro
a
c
h
,
”
Kn
o
wled
g
e
B
a
se
d
S
y
ste
ms
,
v
o
l.
3
1
,
p
p
.
67
-
7
7
,
2
0
1
2
.
[5
0
]
N.
M
a
so
u
d
,
“
P
re
d
ictin
g
Dire
c
ti
o
n
o
f
S
to
c
k
P
rice
s
In
d
e
x
M
o
v
e
m
e
n
t
Us
in
g
A
rti
f
i
c
ial
Ne
u
ra
l
N
e
t
w
o
rk
s:
T
h
e
Ca
se
o
f
L
ib
y
a
n
F
in
a
n
c
ial
M
a
rk
e
t
,
”
Brit
ish
J
o
u
rn
a
l
o
f
Eco
n
o
mic
s,
M
a
n
a
g
e
m
e
n
t
&
T
ra
d
e
,
v
ol
/i
ss
u
e
:
4
(
4
),
p
p
.
5
9
7
-
6
1
9
,
2
0
1
4
.
[5
1
]
S
.
L
a
h
m
iri
,
“
A
Co
m
p
a
riso
n
o
f
P
NN
a
n
d
S
VM
f
o
r
S
to
c
k
M
a
rk
e
t
T
re
n
d
P
re
d
icti
o
n
Us
in
g
Eco
n
o
m
ic
a
n
d
T
e
c
h
n
ica
l
In
f
o
rm
a
ti
o
n
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
m
p
u
ter
A
p
p
l
ica
ti
o
n
s,
v
ol
/i
ss
u
e
:
29
(
3
),
p
p
.
2
4
-
3
0
,
2
0
1
1
.
[5
2
]
K.
J.
Kim
,
“
F
in
a
n
c
ial
T
i
m
e
S
e
ri
e
s
F
o
re
c
a
stin
g
Us
in
g
S
u
p
p
o
r
t
Ve
c
to
r
M
a
c
h
in
e
s
,
”
Ne
u
ro
-
c
o
mp
u
ti
n
g
,
v
o
l
.
5
5
,
p
p
.
307
-
3
1
9
,
2
0
0
3
.
[5
3
]
W
.
Hu
a
n
g
a
,
e
t
a
l
.
,
“
F
o
re
c
a
stin
g
S
to
c
k
M
a
rk
e
t
M
o
v
e
m
e
n
t
Dire
c
ti
o
n
w
it
h
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
i
n
e
s
,
”
Co
mp
u
ter
s
&
Op
e
ra
ti
o
n
s R
e
se
a
rc
h
,
v
o
l
.
3
2
,
p
p
.
2
5
1
3
-
2
5
2
2
,
2
0
0
5
.
[5
4
]
R.
Ch
o
u
d
h
a
ry
,
e
t
a
l
.
,
“
A
Hy
b
rid
M
a
c
h
in
e
L
e
a
rn
in
g
S
y
ste
m
f
o
r
S
to
c
k
M
a
rk
e
t
F
o
re
c
a
stin
g
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
mp
u
ter
,
El
e
c
trica
l,
A
u
t
o
ma
ti
o
n
,
Co
n
tro
l
a
n
d
I
n
fo
rm
a
ti
o
n
E
n
g
i
n
e
e
rin
g
,
v
ol
/
issu
e
:
2
(
3
),
p
p
.
6
8
9
-
6
9
2
,
2
0
0
8
.
[5
5
]
V
.
Kh
a
ti
b
i
,
e
t
a
l
.
,
“
A
Ne
w
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
i
n
e
–
G
e
n
e
ti
c
A
lg
o
rit
h
m
(S
V
M
GA
)
b
a
se
d
M
e
t
ho
d
f
o
r
S
to
c
k
M
a
rk
e
t
F
o
re
c
a
stin
g
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
th
e
Ph
y
sic
a
l
S
c
ien
c
e
s,
v
ol
/i
s
su
e
:
6
(2
5
),
p
p
.
6
0
9
1
-
6
0
9
7
,
2
0
1
1
.
[5
6
]
L.
G
.
Ca
o
,
e
t
a
l
.
,
“
F
i
n
a
n
c
ial
F
o
re
c
a
stin
g
Us
in
g
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
s
,
”
Ne
u
ra
l
Co
m
p
u
t
&
Ap
p
li
c
,
S
p
rin
g
e
r,
v
o
l.
1
0
,
p
p
.
1
8
4
-
1
9
2
,
2
0
0
1
.
[5
7
]
L.
G
.
Ca
o
,
e
t
a
l
.
,
“
Im
p
ro
v
e
d
F
in
a
n
c
ial
T
i
m
e
S
e
ries
F
o
re
c
a
stin
g
b
y
Co
m
b
in
in
g
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
s
w
it
h
S
e
lf
-
Org
a
n
izin
g
F
e
a
tu
re
M
a
p
,
”
In
telli
g
e
n
t
Da
ta
An
a
lys
is,
v
ol
/i
ss
u
e
:
5
(4
),
p
p
.
3
3
9
-
3
5
4
,
2
0
0
1
.
[5
8
]
N.
I.
S
a
p
a
n
k
e
v
y
c
h
,
e
t
a
l.
,
“
Ti
m
e
S
e
ries
P
re
d
ictio
n
U
sin
g
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
s:
A
S
u
rv
e
y
,
”
IEE
E
Co
mp
u
t
a
ti
o
n
a
l
I
n
telli
g
e
n
c
e
M
a
g
a
zin
e
,
v
ol
/i
ss
u
e
:
4
(2
)
,
p
p
.
2
4
-
3
8
,
2
0
0
9
.
[5
9
]
M.
T
im
o
r
,
et
al
.,
“
P
e
rf
o
r
m
a
n
c
e
Co
m
p
a
riso
n
of
A
rti
f
ici
a
l
Ne
u
ra
l
Ne
tw
o
rk
(
A
N
N)
a
n
d
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
i
n
e
s
(S
V
M
)
M
o
d
e
ls
f
o
r
th
e
S
to
c
k
S
e
le
c
ti
o
n
P
ro
b
lem
:
An
A
p
p
li
c
a
ti
o
n
on
th
e
Ista
n
b
u
l
S
t
o
c
k
Ex
c
h
a
n
g
e
(I
S
E)
-
30
In
d
e
x
in
T
u
rk
e
y
,
”
Af
ric
a
n
J
o
u
rn
a
l
of
Bu
si
n
e
ss
M
a
n
a
g
e
me
n
t,
v
ol
/i
s
s
u
e
:
6
(
3
)
,
p
p
.
1
1
9
1
-
1
1
9
8
,
2
0
1
2
.
[6
0
]
S
.
S
a
m
a
n
t,
“
P
re
d
icti
o
n
o
f
F
in
a
n
c
ial
P
e
rf
o
r
m
a
n
c
e
Us
in
g
Ge
n
e
ti
c
A
l
g
o
rit
h
m
a
n
d
A
s
so
c
iativ
e
Ru
le
M
in
i
n
g
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
E
n
g
in
e
e
rin
g
Res
e
a
rc
h
a
n
d
Ge
n
e
ra
l
S
c
ien
c
e
,
v
ol
/i
ss
u
e
:
3
(
1
),
p
p
.
1
0
3
5
-
1
0
4
5
,
2
0
1
5
.
[6
1
]
L
.
Yu
,
e
t
a
l
.,
“
M
i
n
in
g
S
to
c
k
M
a
r
k
e
t
T
e
n
d
e
n
c
y
Us
in
g
GA
-
Ba
s
e
d
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
i
n
e
s
,
”
L
NC
S
(
S
p
rin
g
e
r),
v
o
l.
3
8
2
8
,
p
p
.
3
3
6
-
3
4
5
,
2
0
0
5
.
[6
2
]
A.
F
.
S
h
e
ta
,
e
t
a
l
.
,
“
A
Ge
n
e
ti
c
P
r
o
g
ra
m
m
in
g
M
o
d
e
l
f
o
r
S
&
P
5
0
0
S
to
c
k
M
a
rk
e
t
P
re
d
icti
o
n
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
n
tro
l
a
n
d
Au
t
o
ma
ti
o
n
,
v
ol
/i
s
su
e
:
6
(5
)
,
p
p
.
3
0
3
-
3
1
4
,
2
0
1
3
.
[6
3
]
B.
M
a
jh
i
,
e
t
a
l
.
,
“
On
th
e
De
v
e
lo
p
m
e
n
t
a
n
d
P
e
rf
o
r
m
a
n
c
e
Ev
a
lu
a
ti
o
n
o
f
a
M
u
lt
i
Ob
jec
ti
v
e
GA
-
b
a
se
d
RBF
A
d
a
p
ti
v
e
M
o
d
e
l
f
o
r
th
e
P
re
d
ictio
n
o
f
S
to
c
k
In
d
ice
s
,
”
J
o
u
rn
a
l
o
f
Ki
n
g
S
a
u
d
Un
ive
rs
it
y
–
Co
m
p
u
ter
a
n
d
I
n
fo
r
ma
ti
o
n
S
c
ien
c
e
s,
v
o
l.
2
6
,
p
p
.
3
1
9
–
3
3
1
,
2
0
1
4
.
[6
4
]
L.
Y.
Wei,
“
A
H
y
b
rid
M
o
d
e
l
b
a
s
e
d
o
n
A
NFIS
a
n
d
A
d
a
p
ti
v
e
Ex
p
e
c
tatio
n
G
e
n
e
ti
c
A
lg
o
rit
h
m
to
F
o
r
e
c
a
st
TA
IEX
,
”
Eco
n
o
mic
M
o
d
e
ll
i
n
g
,
v
o
l.
3
3
,
p
p
.
8
9
3
–
8
9
9
,
2
0
1
3
.
[6
5
]
R.
S
.
S
e
x
to
n
,
e
t
a
l
.
,
“
Co
m
p
a
ra
ti
v
e
E
v
a
lu
a
ti
o
n
o
f
G
e
n
e
ti
c
A
l
g
o
rit
h
m
a
n
d
Ba
c
k
p
ro
p
a
g
a
ti
o
n
f
o
r
Train
in
g
Ne
u
ra
l
Ne
tw
o
rk
s
,
”
In
fo
rm
a
ti
o
n
S
c
ien
c
e
s,
v
ol
/i
ss
u
e
:
1
2
9
(
1
),
p
p
.
4
5
-
5
9
,
2
0
0
0
.
[6
6
]
S
.
F
a
ll
a
h
i
,
e
t
a
l
.
,
“
A
p
p
ly
in
g
G
M
DH
-
Ty
p
e
N
e
u
ra
l
Ne
t
w
o
rk
a
n
d
G
e
n
e
ti
c
A
l
g
o
rit
h
m
f
o
r
S
to
c
k
P
ri
c
e
P
re
d
icti
o
n
o
f
Ira
n
ian
Ce
m
e
n
t
S
e
c
to
r
,
”
Ap
p
li
c
a
t
io
n
s
a
n
d
A
p
p
li
e
d
M
a
th
e
ma
ti
c
s:
An
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
(
AA
M
),
v
ol
/i
ss
u
e
:
6
(2
),
p
p
.
5
7
2
–
5
9
1
,
2
0
1
1
.
[6
7
]
M.
R.
Ha
ss
a
n
,
e
t
a
l
.
,
“
A F
u
sio
n
M
o
d
e
l
o
f
HMM
,
A
NN
a
n
d
G
A
f
o
r
S
to
c
k
M
a
rk
e
t
F
o
re
c
a
stin
g
,
”
E
x
p
e
rt S
y
ste
ms
wit
h
Ap
p
li
c
a
ti
o
n
s,
v
ol
/i
ss
u
e
:
3
3
(
1
),
p
p
.
1
7
1
–
1
8
0
,
2
0
0
7
.
[6
8
]
Y
.
Zu
o
,
e
t
a
l
.
,
“
Up
/Do
w
n
A
n
a
ly
sis
o
f
S
to
c
k
I
n
d
e
x
b
y
Us
in
g
Ba
y
e
sia
n
N
e
t
w
o
rk
,
”
En
g
in
e
e
rin
g
M
a
n
a
g
e
me
n
t
Res
e
a
rc
h
,
v
ol
/i
ss
u
e
:
1
(2
),
p
p
.
4
6
-
5
2
,
2
0
1
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
6
,
No
.
6
,
Dec
em
b
er
2
0
1
6
:
3
196
–
3
204
3204
[6
9
]
S
.
Na
slm
o
sa
v
i
,
e
t
a
l
.
,
“
Co
m
p
a
rin
g
th
e
A
b
il
it
y
o
f
Ba
y
e
si
a
n
Ne
tw
o
r
k
s an
d
A
d
a
b
o
o
st
f
o
r
P
re
d
ictin
g
F
i
n
a
n
c
ial
Distre
ss
o
f
F
irm
s
L
isted
o
n
T
e
h
ra
n
S
to
c
k
Ex
c
h
a
n
g
e
(T
S
E)
,
”
Au
stra
li
a
n
J
o
u
rn
a
l
o
f
Ba
sic
a
n
d
Ap
p
li
e
d
S
c
ien
c
e
s,
v
ol
/i
ss
u
e
:
5
(1
0
),
p
p
.
6
2
9
-
6
3
4
,
2
0
1
1
.
[7
0
]
S
.
A
.
Bo
g
le
,
e
t
a
l
.
,
“
A
M
a
c
h
in
e
L
e
a
rn
in
g
P
re
d
ictiv
e
M
o
d
e
l
f
o
r
th
e
Ja
m
a
ica
F
ro
n
ti
e
r
M
a
rk
e
t
,
”
Pro
c
e
e
d
in
g
s
o
f
t
h
e
W
o
rl
d
Co
n
g
re
ss
o
n
E
n
g
i
n
e
e
rin
g
,
W
CE
,
L
o
n
d
o
n
(U.K.
)
,
2
0
1
5
.
[7
1
]
J.
P
a
tel
,
e
t
a
l
.
,
“
P
re
d
icti
n
g
S
t
o
c
k
a
n
d
S
to
c
k
In
d
e
x
P
r
ice
M
o
v
e
m
e
n
t
Us
in
g
T
re
n
d
De
term
in
isti
c
Da
ta
P
re
p
a
ra
ti
o
n
a
n
d
M
a
c
h
in
e
L
e
a
rn
in
g
T
e
c
h
n
iq
u
e
s
,
”
Exp
e
rt S
y
ste
ms
wit
h
A
p
p
l
ica
ti
o
n
s,
v
ol
/i
ss
u
e
:
42
(1
)
,
p
p
.
2
5
9
-
2
6
8
,
2
0
1
5
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
S
a
c
h
i
n
K
a
m
ley
d
id
h
is
M
a
ste
rs
f
ro
m
S
.
A
.
T
.
I.
,
Co
m
p
u
ter
A
p
p
li
c
a
ti
o
n
s
De
p
a
rtm
e
n
t,
Ra
ji
v
G
a
n
d
h
i
T
e
c
h
n
o
lo
g
ica
l
Un
iv
e
rsity
,
Bh
o
p
a
l
(M
.
P
.
)
in
2
0
0
6
.
He
is
w
o
rk
in
g
a
t
S
a
m
ra
t
As
h
o
k
T
e
c
h
n
o
lo
g
ica
l
In
stit
u
te
(S
.
A
.
T
.
I),
Vid
is
h
a
a
s
a
L
e
c
tu
re
r
f
ro
m
M
a
y
2
0
0
7
t
o
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
A
p
p
li
c
a
ti
o
n
s
a
n
d
c
o
m
p
lete
d
P
h
.
D.
f
ro
m
Ba
r
k
a
tu
ll
a
h
Un
iv
e
rsity
,
Bh
o
p
a
l
in
th
e
y
e
a
r
2
0
1
5
.
He
h
a
s atte
n
d
e
d
m
a
n
y
w
o
rk
sh
o
p
s an
d
c
o
n
f
e
re
n
c
e
s o
f
Na
ti
o
n
a
l
re
p
u
te
.
S
h
a
il
e
s
h
J
a
lo
r
e
e
is
a
n
A
s
so
c
iate
P
ro
f
e
ss
o
r
in
t
h
e
De
p
a
rtm
e
n
t
o
f
A
p
p
li
e
d
M
a
th
’s
a
n
d
C
o
m
p
u
ter
S
c
ien
c
e
a
t
S
a
m
ra
t
A
sh
o
k
Tec
h
n
o
l
o
g
ica
l
In
stit
u
te
(S
.
A
.
T
.
I.
),
Vi
d
ish
a
,
I
n
d
ia.
He
e
a
rn
e
d
h
is
M
a
ste
r
De
g
r
e
e
f
ro
m
De
v
i
A
h
il
i
y
a
Un
iv
e
rsit
y
In
d
o
re
(M
.
P
.
)
i
n
1
9
9
1
a
n
d
P
h
.
D
.
De
g
re
e
(
A
p
p
li
e
d
M
a
th
s)
F
ro
m
Ba
rk
a
tu
ll
a
h
Un
iv
e
rsity
,
Bh
o
p
a
l
(M
.
P
.
)
in
2
0
0
2
.
A
t
P
re
se
n
t
h
e
is
g
u
id
i
n
g
se
v
e
ra
l
P
h
.
D.
Re
se
a
rc
h
S
c
h
o
lars
in
M
a
th
e
m
a
ti
c
s
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
f
ield
.
He
h
a
s
p
u
b
li
sh
e
d
m
o
re
th
a
n
3
5
Re
se
a
rc
h
P
a
p
e
r
in
Na
ti
o
n
a
l,
In
tern
a
ti
o
n
a
l,
Jo
u
r
n
a
ls
a
n
d
Co
n
f
e
re
n
c
e
s.
His
a
re
a
s
o
f
in
tere
st i
n
c
l
u
d
e
S
p
e
c
ial
F
u
n
c
ti
o
n
,
Da
ta M
in
in
g
,
Da
ta W
a
re
h
o
u
si
n
g
a
n
d
W
e
b
M
i
n
in
g
.
Ra
m
je
e
v
a
n
S
in
g
h
T
h
a
k
u
r
is
a
n
A
ss
o
c
iate
P
r
o
f
e
ss
o
r
in
t
h
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
A
p
p
li
c
a
ti
o
n
s
a
t
M
a
u
lan
a
A
z
a
d
N
a
ti
o
n
a
l
I
n
stit
u
te
o
f
T
e
c
h
n
o
lo
g
y
,
Bh
o
p
a
l
,
In
d
ia.
He
h
a
d
a
lo
n
g
c
a
rrier
in
tea
c
h
in
g
a
n
d
re
se
a
rc
h
,
in
c
lu
d
in
g
T
h
re
e
Ye
a
r
T
e
a
c
h
in
g
in
th
e
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
A
p
p
li
c
a
ti
o
n
s
a
t
Na
ti
o
n
a
l
In
stit
u
te
o
f
Tec
h
n
o
lo
g
y
,
T
iru
c
h
irap
a
ll
i,
a
n
d
T
a
m
il
n
a
d
u
,
I
n
d
ia.
A
t
P
re
se
n
t
h
e
is
g
u
i
d
in
g
se
v
e
ra
l
P
h
.
D.
Re
se
a
rc
h
S
c
h
o
lars
a
n
d
h
a
n
d
li
n
g
G
o
v
e
rn
m
e
n
t
Re
se
a
r
c
h
P
r
o
jec
ts
o
f
a
b
o
u
t
Rs.
O
n
e
Cro
re
.
He
h
a
s
p
u
b
li
s
h
e
d
m
o
re
th
a
n
7
5
Re
se
a
rc
h
P
a
p
e
r
in
Na
ti
o
n
a
l,
In
tern
a
ti
o
n
a
l,
J
o
u
r
n
a
ls
a
n
d
C
o
n
f
e
re
n
c
e
s.
He
h
a
s v
isit
e
d
se
v
e
r
a
l
Un
i
v
e
rsiti
e
s in
USA
,
Ho
n
g
Ko
n
g
,
Ira
n
,
T
h
il
a
n
d
,
M
a
lay
sia
,
a
n
d
S
in
g
a
p
o
re
.
Evaluation Warning : The document was created with Spire.PDF for Python.