I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
1
6
,
No
.
3
,
J
u
n
e
20
2
6
,
p
p
.
1298
~
1
3
0
6
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
1
6
i
3
.
pp
1
2
9
8
-
1
3
0
6
1298
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
An enhance
ment
o
f
sto
ck pri
ce
foreca
sting
bas
ed on
hybrid
BiL
STM
-
Tra
nsfo
rmer mo
del
P
ha
m
H
o
a
ng
Vuo
ng
1,
2
,
L
a
m
H
un
g
P
hu
2
,
L
e
Nha
t
Duy
1
,
P
ha
m
T
he
B
a
o
2
,
T
a
n Da
t
T
rin
h
2
1
F
a
c
u
l
t
y
o
f
I
n
f
o
r
m
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
I
n
d
u
s
t
r
i
a
l
U
n
i
v
e
r
si
t
y
o
f
H
o
C
h
i
M
i
n
h
C
i
t
y
,
H
o
C
h
i
M
i
n
h
C
i
t
y
,
V
i
e
t
n
a
m
2
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
I
n
f
o
r
mat
i
o
n
S
c
i
e
n
c
e
F
a
c
u
l
t
y
,
S
a
i
g
o
n
U
n
i
v
e
r
si
t
y
,
H
o
C
h
i
M
i
n
h
C
i
t
y
,
V
i
e
t
n
a
m
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
No
v
6
,
2
0
2
4
R
ev
is
ed
J
an
2
4
,
2
0
2
6
Acc
ep
ted
Ma
r
1
6
,
2
0
2
6
S
to
c
k
p
rice
fo
re
c
a
stin
g
p
re
se
n
ts
a
c
h
a
ll
e
n
g
in
g
p
r
o
b
lem
d
u
e
to
fa
c
to
rs
li
k
e
n
o
n
li
n
e
a
rit
y
,
se
a
so
n
a
li
ty
,
a
n
d
e
c
o
n
o
m
ic
v
o
latil
it
y
in
fi
n
a
n
c
ial
d
a
ta.
De
e
p
lea
rn
in
g
a
p
p
ro
a
c
h
e
s
c
a
n
h
a
n
d
le
n
o
n
li
n
e
a
rit
y
a
n
d
c
o
m
p
lex
it
y
o
f
fin
a
n
c
ial
d
a
ta,
b
u
t
t
h
e
y
o
fte
n
fa
c
e
li
m
it
a
ti
o
n
s
i
n
c
a
p
tu
ri
n
g
b
o
t
h
lo
c
a
l
a
n
d
g
l
o
b
a
l
d
e
p
e
n
d
e
n
c
ies
.
Th
is st
u
d
y
i
n
tro
d
u
c
e
s a
h
y
b
ri
d
Tran
sf
o
rm
e
r
–
b
i
d
irec
ti
o
n
a
l
l
o
n
g
sh
o
rt
-
term
m
e
m
o
ry
(Bi
LS
TM
)
m
o
d
e
l
t
o
imp
r
o
v
e
st
o
c
k
p
rice
f
o
re
c
a
stin
g
.
Ou
r
m
e
th
o
d
c
o
m
b
i
n
e
s
th
e
stre
n
g
th
o
f
Bi
LS
TM
with
th
e
g
lo
b
a
l
c
o
n
tex
t
u
n
d
e
r
sta
n
d
i
n
g
o
f
th
e
Tra
n
sfo
rm
e
r
b
y
e
m
b
e
d
d
in
g
a
1
D
c
o
n
v
o
lu
t
io
n
a
l
lay
e
r
.
Th
e
m
o
d
e
l
c
a
n
e
fficie
n
tl
y
c
a
p
tu
r
e
sh
o
rt
-
term
a
n
d
l
o
n
g
-
term
d
e
p
e
n
d
e
n
c
ies
in
sto
c
k
d
a
ta.
E
x
p
e
rime
n
tal
re
su
lt
s
o
n
v
a
rio
u
s
d
a
tas
e
ts
sh
o
w
t
h
a
t
o
u
r
h
y
b
ri
d
m
o
d
e
l
o
u
tp
e
rf
o
rm
s o
t
h
e
r
we
ll
-
k
n
o
wn
m
o
d
e
ls.
K
ey
w
o
r
d
s
:
B
iLST
M
Dee
p
lear
n
in
g
Hy
b
r
id
m
o
d
el
Sto
ck
p
r
ice
f
o
r
ec
asti
n
g
T
r
an
s
f
o
r
m
e
r
m
o
d
el
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
:
Ph
am
T
h
e
B
ao
I
n
f
o
r
m
atio
n
Scien
ce
Facu
lty
,
Saig
o
n
Un
iv
er
s
ity
2
7
3
An
D
u
o
n
g
Vu
o
n
g
Stre
et,
C
h
o
Qu
an
W
ar
d
,
Ho
C
h
i M
in
h
C
ity
,
Vietn
am
E
m
ail:
p
tb
ao
@
s
g
u
.
ed
u
.
v
n
1.
I
NT
RO
D
UCT
I
O
N
Sto
ck
p
r
ice
f
o
r
ec
asti
n
g
(
SP
F)
h
as
b
ee
n
a
to
p
ic
o
f
f
in
an
cial
r
esear
ch
,
ess
en
tial
f
o
r
v
ar
io
u
s
tr
ad
in
g
an
d
in
v
estme
n
t
s
tr
ateg
ies.
Fin
an
ci
al
m
ar
k
ets,
with
th
eir
v
o
latilit
y
an
d
co
m
p
lex
ity
,
ar
e
af
f
ec
te
d
b
y
m
a
n
y
f
ac
to
r
s
s
u
ch
as
p
o
liti
ca
l
ev
en
ts
o
r
m
ar
k
et
tr
e
n
d
s
[
1
]
,
[
2
]
.
T
h
is
m
ak
es
p
r
ed
ictin
g
s
to
ck
p
r
i
ce
s
a
d
if
f
ic
u
lt
task
.
Pre
d
ictin
g
a
s
to
ck
's
f
u
tu
r
e
p
r
ice
in
v
o
lv
es
f
in
d
in
g
p
atter
n
s
with
in
u
n
p
r
ed
ictab
le,
n
o
n
-
lin
ea
r
,
an
d
m
u
lti
-
d
im
en
s
io
n
al
tim
e
-
s
er
ies
d
ata.
Ma
n
y
ap
p
r
o
ac
h
es
o
f
th
e
SP
F
h
as
d
ev
elo
p
ed
o
v
er
th
e
y
ea
r
s
[
1
]
,
[
3
]
.
Statis
tical
ap
p
r
o
ac
h
es
f
o
r
th
e
SP
F
ar
e
m
ath
em
atica
l
f
r
am
ewo
r
k
s
th
at
a
im
to
f
o
r
ec
ast
f
u
tu
r
e
p
r
ices
u
s
in
g
h
is
to
r
ical
d
ata.
Au
to
r
eg
r
ess
iv
e
in
teg
r
ated
m
o
v
in
g
a
v
er
ag
e
(
AR
I
MA
)
[
4
]
,
[
5
]
ar
e
well
-
k
n
o
wn
m
eth
o
d
s
f
o
r
th
e
SP
F.
Su
b
ak
k
ar
et
a
l.
[
4
]
ap
p
lied
AR
I
MA
to
f
o
r
ec
ast
T
esla
'
s
s
to
ck
d
ata.
T
h
e
r
esu
lts
o
b
tain
ed
f
r
o
m
th
e
AR
I
MA
d
em
o
n
s
tr
ate
r
o
b
u
s
t
ac
c
u
r
ac
y
f
o
r
s
h
o
r
t
-
ter
m
s
to
ck
p
r
ice
p
r
ed
ictio
n
s
.
Su
r
ip
to
[
5
]
d
em
o
n
s
tr
ated
t
h
at
th
e
AR
I
MA
(
1
,
1
,
1
)
m
o
d
el
h
a
d
an
a
p
p
licab
ilit
y
r
a
te
o
f
9
8
%
f
o
r
p
r
ed
ictin
g
s
to
c
k
p
r
ices.
Alth
o
u
g
h
AR
I
MA
c
an
b
e
s
u
f
f
icien
t
f
o
r
s
h
o
r
t
-
ter
m
f
o
r
ec
asts
,
its
ab
ilit
y
to
p
r
ed
ict
o
v
er
l
o
n
g
er
ter
m
s
is
u
n
ce
r
tain
.
Ma
ch
in
e
lear
n
in
g
(
ML
)
m
o
d
els
h
av
e
i
n
cr
ea
s
in
g
ly
b
ee
n
u
s
ed
f
o
r
t
h
e
SP
F.
ML
alg
o
r
ith
m
s
s
u
ch
as
n
eu
r
al
n
etwo
r
k
(
ANN)
[
6
]
,
s
u
p
p
o
r
t
v
ec
to
r
r
eg
r
ess
io
n
(
SVR
)
[
7
]
,
[
8
]
,
en
s
em
b
le
m
o
d
els
(
r
a
n
d
o
m
f
o
r
est
(
R
F),
X
G
B
o
o
s
t)
[
6
]
,
[
9
]
,
p
r
o
v
id
es
s
ig
n
if
ican
t
ad
v
a
n
tag
es
o
v
er
tr
ad
itio
n
al
s
tatis
tical
m
o
d
els.
Vijh
et
a
l.
[
6
]
ex
p
lo
r
e
d
ANN
an
d
R
F
f
o
r
p
r
e
d
ictin
g
s
t
o
ck
m
a
r
k
et
clo
s
in
g
p
r
ices.
Z
h
an
g
et
a
l.
[
7
]
in
tr
o
d
u
ce
d
an
e
n
s
em
b
le
m
o
d
el
th
at
co
m
b
in
es
f
ea
tu
r
es
o
f
b
o
t
h
SVR
an
d
th
e
en
s
em
b
le
ad
ap
ti
v
e
n
eu
r
o
f
u
zz
y
in
f
er
e
n
ce
s
y
s
tem
.
B
az
r
k
ar
an
d
Ho
s
s
ein
i
[
8
]
a
p
p
lied
a
m
eth
o
d
f
o
r
th
e
SP
F
u
s
in
g
SVM
a
n
d
p
ar
ticle
s
war
m
o
p
tim
izatio
n
(
PS
O)
alg
o
r
ith
m
s
.
T
h
e
r
esu
lts
in
d
icate
d
th
at
th
e
ir
m
eth
o
d
c
o
n
s
is
ten
tly
o
u
tp
er
f
o
r
m
ed
o
th
er
tec
h
n
iq
u
es,
ac
h
iev
in
g
a
p
r
ed
ictio
n
ac
cu
r
ac
y
co
n
s
is
ten
tly
ab
o
v
e
9
0
%.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
n
en
h
a
n
ce
men
t o
f sto
ck
p
r
ic
e
fo
r
ec
a
s
tin
g
b
a
s
ed
o
n
h
y
b
r
id
…
(
P
h
a
m
Ho
a
n
g
V
u
o
n
g
)
1299
R
e
c
e
n
tl
y
,
d
e
e
p
l
e
a
r
n
i
n
g
(
D
L
)
,
w
i
t
h
i
ts
a
u
t
o
m
a
ti
c
f
e
a
t
u
r
e
l
e
a
r
n
i
n
g
,
a
b
i
l
i
t
y
t
o
p
r
o
c
e
s
s
c
o
m
p
l
ex
p
a
t
t
e
r
n
s
,
a
n
d
b
e
t
t
e
r
a
d
a
p
t
a
t
i
o
n
t
o
l
a
r
g
e
d
a
t
a
s
et
s
,
o
f
f
e
r
s
a
s
i
g
n
i
f
i
ca
n
t
ad
v
a
n
t
a
g
e
.
T
h
e
D
L
m
o
d
e
l
s
s
u
ch
a
s
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
(
C
NN
)
[
1
0
]
,
[
1
1
]
a
n
d
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
(
R
N
N
)
[
1
2
]
–
[
1
5
]
h
a
v
e
b
e
e
n
s
u
c
c
es
s
f
u
l
l
y
a
p
p
li
e
d
t
o
s
t
o
c
k
p
r
i
c
e
f
o
r
e
c
as
t
i
n
g
.
F
ath
a
l
i
e
t
a
l
.
[
1
6
]
a
p
p
l
i
e
d
C
N
N
a
n
d
R
N
N
t
o
p
r
e
d
i
ct
t
h
e
s
t
o
c
k
t
r
e
n
d
s
.
S
a
t
r
i
a
[
1
7
]
i
n
v
e
s
t
i
g
at
e
d
R
N
N
,
l
o
n
g
s
h
o
r
t
-
t
e
r
m
m
e
m
o
r
y
(
L
S
T
M
)
,
a
n
d
g
a
t
e
d
r
e
c
u
r
r
e
n
t
u
n
i
t
(
G
R
U
)
m
o
d
e
l
s
f
o
r
p
r
e
d
i
c
t
i
n
g
b
a
n
k
i
n
g
s
t
o
c
k
p
r
i
c
e
s
.
M
o
o
t
h
a
e
t
a
l
.
[
1
8
]
f
o
c
u
s
e
d
o
n
p
r
e
d
i
c
t
i
n
g
f
u
t
u
r
e
v
a
l
u
e
s
o
f
a
s
t
o
c
k
u
s
i
n
g
B
i
d
i
r
ec
t
i
o
n
a
l
L
S
T
M
(
B
i
L
S
T
M
)
b
a
s
e
d
S
e
q
2
Se
q
m
o
d
e
l
i
n
g
.
T
h
e
m
o
d
e
l
s
i
g
n
i
f
ic
a
n
t
l
y
o
u
t
p
e
r
f
o
r
m
e
d
e
x
i
s
ti
n
g
a
lg
o
r
i
t
h
m
s
.
R
ec
en
tly
,
n
ew
h
y
b
r
id
DL
ap
p
r
o
ac
h
es
[
1
9
]
–
[
2
1
]
h
av
e
s
h
o
wn
p
r
o
m
is
e
in
f
o
r
ec
asti
n
g
s
t
o
ck
d
ata.
Ald
h
y
an
i
a
n
d
Alza
h
r
an
i
[
2
2
]
i
n
tr
o
d
u
ce
d
C
NN
-
L
STM
ap
p
r
o
ac
h
to
f
o
r
ec
ast
t
h
e
clo
s
in
g
p
r
ice
u
s
in
g
two
y
ea
r
s
'
wo
r
th
o
f
d
ata.
C
h
en
et
a
l.
[
2
3
]
in
tr
o
d
u
ce
d
a
m
o
d
el
wh
ich
c
o
m
b
in
in
g
C
NN
-
B
iLST
M
-
E
C
A
(
ef
f
icien
t
ch
an
n
el
atten
tio
n
)
f
o
r
f
o
r
ec
asti
n
g
s
to
c
k
d
ata.
E
x
p
e
r
im
en
ts
r
ev
ea
l
th
at
th
eir
m
o
d
el
o
v
e
r
ca
m
e
ex
is
tin
g
m
eth
o
d
s
.
W
an
g
[
2
4
]
p
r
o
p
o
s
ed
B
iLST
M
-
MT
R
AN
-
T
C
N
m
o
d
el
f
o
r
s
to
ck
p
r
ic
e
f
o
r
ec
asti
n
g
.
I
t
d
e
m
o
n
s
tr
ates
b
etter
p
er
f
o
r
m
an
c
e
o
n
ea
ch
in
d
ex
s
to
ck
c
o
m
p
ar
e
d
to
o
th
er
ex
is
tin
g
m
eth
o
d
s
,
ac
h
iev
in
g
th
e
h
ig
h
est
R
2
s
co
r
e
in
8
5
.
7
%
o
f
th
e
s
to
ck
d
ataset.
I
n
th
is
r
esear
ch
,
we
in
tr
o
d
u
c
e
a
n
ew
m
o
d
el
th
at
ap
p
lies
T
r
an
s
f
o
r
m
e
r
an
d
B
iLST
M
ar
ch
itectu
r
es.
B
iLST
M
is
well
-
k
n
o
wn
to
c
ap
tu
r
e
b
id
ir
ec
tio
n
al
d
ep
en
d
en
cies
in
s
to
ck
d
ata,
p
r
o
ce
s
s
in
g
in
f
o
r
m
atio
n
f
r
o
m
b
o
th
th
e
p
ast
an
d
f
u
tu
r
e
to
u
n
d
er
s
tan
d
th
e
lo
ca
l
tem
p
o
r
al
s
t
r
u
ctu
r
e
m
o
r
e
ef
f
ec
tiv
ely
.
B
y
i
n
teg
r
atin
g
B
iLST
M
with
a
T
r
an
s
f
o
r
m
er
,
o
u
r
m
o
d
e
l
ca
p
italizes
o
n
b
o
th
s
h
o
r
t
-
ter
m
s
eq
u
en
tial
p
r
o
ce
s
s
in
g
an
d
l
o
n
g
-
ter
m
co
n
tex
t
u
al
u
n
d
er
s
tan
d
i
n
g
.
T
h
r
o
u
g
h
ex
p
er
im
en
tal
an
aly
s
is
,
we
aim
to
u
n
d
er
s
tan
d
th
ese
m
o
d
els'
ef
f
icac
y
in
p
r
o
ce
s
s
in
g
th
e
co
m
p
lex
tim
e
s
eq
u
en
ce
s
in
s
to
ck
p
r
ice
ch
an
g
es
an
d
th
eir
c
ap
ab
ilit
y
to
f
o
r
ec
ast
f
u
tu
r
e
p
r
ices
with
in
cr
ea
s
ed
p
r
ec
is
io
n
an
d
r
eliab
ilit
y
.
2.
P
RO
P
O
SE
D
M
E
T
H
O
D
2
.
1
.
L
S
T
M
a
nd
B
i
L
ST
M
m
o
dels
f
o
r
s
t
o
c
k
price
f
o
re
ca
s
t
ing
R
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
tw
o
r
k
(
R
NN
)
i
s
e
f
f
e
ct
i
v
e
f
o
r
s
e
q
u
e
n
c
e
d
at
a
b
u
t
h
a
v
e
d
i
f
f
i
c
u
l
t
y
l
e
a
r
n
i
n
g
l
o
n
g
-
r
a
n
g
e
d
e
p
e
n
d
e
n
c
i
e
s
.
L
S
T
M
m
o
d
e
ls
w
e
r
e
d
e
v
e
l
o
p
e
d
t
o
o
v
e
r
c
o
m
e
t
h
e
s
e
l
i
m
it
a
t
i
o
n
s
b
y
r
e
d
u
c
i
n
g
t
h
e
v
a
n
i
s
h
i
n
g
g
r
a
d
i
e
n
t
p
r
o
b
l
e
m
[
9
]
.
F
i
g
u
r
e
1
s
h
o
ws
th
e
s
t
r
u
c
t
u
r
e
o
f
a
L
S
T
M
u
n
i
t
,
w
h
i
c
h
is
u
s
e
d
f
o
r
p
r
o
c
es
s
i
n
g
in
f
o
r
m
a
t
i
o
n
.
A
t
y
p
i
c
al
L
S
T
M
c
o
n
s
i
s
t
s
o
f
f
o
u
r
m
a
i
n
c
o
m
p
o
n
e
n
t
s
:
a
m
e
m
o
r
y
c
e
ll
,
a
n
in
p
u
t
g
a
t
e
,
a
n
o
u
t
p
u
t
g
a
t
e
,
a
n
d
a
f
o
r
g
e
t
g
a
t
e
.
T
h
e
m
em
o
r
y
ce
ll
eq
u
ally
v
alu
es
p
ast
an
d
f
u
t
u
r
e
i
n
f
o
r
m
atio
n
,
e
n
s
u
r
in
g
th
at
b
o
th
ar
e
s
to
r
ed
ef
f
ec
tiv
ely
.
T
h
e
in
p
u
t
a
n
d
o
u
t
p
u
t
g
ates
f
ac
ilit
ate
th
e
u
n
it'
s
ab
ilit
y
to
m
ain
tain
in
f
o
r
m
atio
n
o
v
er
lo
n
g
p
e
r
io
d
s
.
Sp
ec
if
ically
,
th
e
in
p
u
t
g
ate
d
eter
m
in
es
wh
eth
er
n
ew
in
f
o
r
m
atio
n
s
h
o
u
l
d
b
e
a
d
d
ed
in
to
th
e
m
em
o
r
y
ce
ll.
C
o
n
v
er
s
ely
,
th
e
o
u
tp
u
t
g
ate
d
ec
id
es
wh
ich
p
o
r
tio
n
s
o
f
th
e
m
em
o
r
y
co
n
tr
ib
u
te
to
th
e
o
u
t
p
u
t.
Me
an
w
h
ile,
th
e
f
o
r
g
et
g
ate
is
r
esp
o
n
s
ib
le
f
o
r
d
ec
id
in
g
wh
ich
p
iece
s
o
f
in
f
o
r
m
atio
n
ar
e
to
b
e
r
etain
ed
a
n
d
wh
ic
h
ar
e
to
b
e
d
is
ca
r
d
ed
.
T
h
e
L
STM
m
o
d
el
b
en
ef
its
f
r
o
m
ag
g
r
e
g
atin
g
c
o
n
tex
ts
f
r
o
m
b
o
th
p
ast
an
d
f
u
tu
r
e
t
o
p
r
o
d
u
ce
o
u
tp
u
ts
,
th
er
eb
y
p
r
o
v
id
in
g
m
o
r
e
co
m
p
r
eh
e
n
s
iv
e
in
f
o
r
m
atio
n
to
ad
jace
n
t e
lem
en
ts
.
T
h
e
f
o
r
war
d
an
d
b
ac
k
war
d
L
STM
s
ca
n
b
e
co
m
b
in
ed
in
to
a
s
in
g
le
n
etwo
r
k
,
ter
m
ed
a
B
iLST
M
[
2
5
]
.
T
h
is
n
etwo
r
k
is
d
esig
n
ed
to
ex
p
l
o
it
in
f
o
r
m
atio
n
in
b
o
th
d
ir
ec
ti
o
n
s
[
2
3
]
,
[
2
6
]
.
Fig
u
r
e
1
.
I
ll
u
s
tr
atio
n
o
f
a
b
asic L
STM
u
n
it
[
9
]
2
.
2
.
O
v
er
v
iew
o
f
T
ra
ns
f
o
rmer
m
o
del
T
h
e
T
r
a
n
s
f
o
r
m
er
m
o
d
el
was
d
ev
elo
p
ed
f
o
r
s
eq
u
en
ce
-
to
-
s
eq
u
en
ce
task
s
[
2
7
]
,
[
2
8
]
.
I
t
s
tan
d
s
o
u
t
f
r
o
m
tr
ad
itio
n
al
R
NN
m
o
d
els
b
y
in
co
r
p
o
r
atin
g
a
s
elf
-
atten
tio
n
m
ec
h
an
is
m
.
T
h
is
f
ea
tu
r
e
en
a
b
les
th
e
m
o
d
el
to
f
o
cu
s
o
n
d
is
tin
ct
p
a
r
ts
o
f
th
e
in
p
u
t
wh
ile
g
en
er
atin
g
o
u
tp
u
ts
.
T
r
a
n
s
f
o
r
m
er
s
ca
n
lear
n
r
elatio
n
s
h
ip
s
ac
r
o
s
s
v
ar
io
u
s
p
ar
ts
in
th
e
in
p
u
t,
s
ig
n
if
ican
tly
en
h
a
n
cin
g
th
eir
a
b
ilit
y
to
m
an
ag
e
lo
n
g
-
r
an
g
e
d
ep
en
d
e
n
cies.
T
h
e
o
v
er
all
ar
ch
itectu
r
e
o
f
a
T
r
a
n
s
f
o
r
m
er
i
s
s
h
o
wn
in
Fig
u
r
e
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
3
,
J
u
n
e
20
2
6
:
1
2
9
8
-
1
3
0
6
1300
T
h
e
en
c
o
d
er
,
d
escr
ib
e
d
o
n
lef
t
s
id
e
o
f
th
e
T
r
an
s
f
o
r
m
er
a
r
ch
itectu
r
e
in
Fig
u
r
e
2
,
ess
en
tially
m
ap
s
a
n
in
p
u
t
s
eq
u
en
ce
in
to
a
s
er
ies
o
f
co
n
tin
u
o
u
s
r
ep
r
esen
tatio
n
s
.
T
h
ese
r
ep
r
esen
tatio
n
s
ar
e
p
ass
ed
o
n
to
th
e
d
ec
o
d
er
.
T
h
e
d
ec
o
d
er
,
d
escr
ib
ed
o
n
r
ig
h
t
s
id
e
o
f
th
e
ar
ch
ite
ctu
r
e,
tak
es
in
th
e
en
co
d
e
r
'
s
o
u
tp
u
t
alo
n
g
with
its
o
wn
o
u
tp
u
t
f
r
o
m
th
e
p
r
ev
i
o
u
s
tim
estep
,
to
g
en
er
ate
an
o
u
t
p
u
t
s
eq
u
en
ce
.
T
r
an
s
f
o
r
m
er
s
u
s
e
m
u
lti
-
h
ea
d
s
elf
-
atten
tio
n
to
o
v
e
r
co
m
e
C
NN
a
n
d
L
STM
lim
itatio
n
s
b
y
ev
al
u
atin
g
in
p
u
t
r
elatio
n
s
h
ip
s
an
d
c
ap
tu
r
in
g
l
o
n
g
-
te
r
m
d
ep
en
d
e
n
cies.
2
.
3
.
H
y
brid m
o
del f
o
r
s
t
o
ck
price
f
o
re
ca
s
t
ing
T
h
e
atten
tio
n
m
ec
h
an
is
m
h
as
b
ee
n
in
teg
r
ated
with
C
NN
–
L
STM
ar
ch
itectu
r
es
[
2
1
]
,
[
2
3
]
,
[
2
9
]
,
[
3
0
]
to
im
p
r
o
v
e
s
to
ck
p
r
ice
p
r
ed
ict
io
n
ac
cu
r
ac
y
,
b
u
t
s
eq
u
en
tial
p
r
o
ce
s
s
in
g
in
L
STM
s
r
estrict
s
p
ar
alleliza
tio
n
an
d
b
ec
o
m
es
in
ef
f
icien
t
f
o
r
lo
n
g
s
eq
u
en
ce
s
.
T
r
a
n
s
f
o
r
m
er
s
o
v
e
r
co
m
e
t
h
ese
d
r
awb
a
ck
s
b
y
e
f
f
icien
tly
m
o
d
elin
g
co
m
p
lex
p
atter
n
s
an
d
lo
n
g
-
ter
m
d
ep
en
d
en
cies.
T
o
lev
er
a
g
e
th
e
s
tr
en
g
th
s
o
f
b
o
t
h
ar
ch
itect
u
r
es,
o
u
r
p
r
o
p
o
s
ed
h
y
b
r
id
m
o
d
el
in
te
g
r
ates
m
u
lti
-
h
ea
d
atte
n
tio
n
,
C
o
n
v
1
D,
an
d
B
id
ir
ec
tio
n
al
L
STM
lay
e
r
s
,
c
o
m
b
in
in
g
th
e
lo
ca
l
f
ea
tu
r
e
e
x
tr
ac
tio
n
with
th
e
te
m
p
o
r
al
m
o
d
elin
g
a
n
d
th
e
g
lo
b
al
d
ep
e
n
d
en
c
y
m
o
d
elin
g
.
T
a
b
le
1
s
h
o
ws
p
r
o
p
o
s
e
d
h
y
b
r
id
m
o
d
el
a
r
ch
itectu
r
e
f
o
r
s
to
ck
p
r
ice
f
o
r
ec
asti
n
g
u
s
in
g
Ker
as f
r
am
ewo
r
k
.
Fig
u
r
e
2
.
T
h
e
T
r
a
n
s
f
o
r
m
er
ar
c
h
itectu
r
e
[
3
1
]
T
ab
le
1
.
Ou
r
m
o
d
el
ar
ch
itectu
r
e
f
o
r
s
to
ck
p
r
ice
f
o
r
ec
asti
n
g
u
s
in
g
th
e
Ker
as f
r
am
ewo
r
k
La
y
e
r
(
t
y
p
e
)
O
u
t
p
u
t
s
h
a
p
e
i
n
p
u
t
_
l
a
y
e
r
(
I
n
p
u
t
La
y
e
r
)
(
N
o
n
e
,
1
0
,
1
)
l
a
y
e
r
_
n
o
r
ma
l
i
z
a
t
i
o
n
(
La
y
e
r
N
o
r
m
a
l
i
z
a
t
i
o
n
)
(
N
o
n
e
,
1
0
,
1
)
mu
l
t
i
_
h
e
a
d
_
a
t
t
e
n
t
i
o
n
(
M
u
l
t
i
H
e
a
d
A
t
t
e
n
t
i
o
n
)
(
N
o
n
e
,
1
0
,
1
)
d
r
o
p
o
u
t
_
1
(
D
r
o
p
o
u
t
)
(
N
o
n
e
,
1
0
,
1
)
a
d
d
(
A
d
d
)
(
N
o
n
e
,
1
0
,
1
)
l
a
y
e
r
_
n
o
r
ma
l
i
z
a
t
i
o
n
_
1
(
La
y
e
r
N
o
r
mal
i
z
a
t
i
o
n
)
(
N
o
n
e
,
1
0
,
1
)
c
o
n
v
1
d
(
C
o
n
v
1
D
)
(
N
o
n
e
,
1
0
,
5
5
)
b
i
d
i
r
e
c
t
i
o
n
a
l
(
B
i
d
i
r
e
c
t
i
o
n
a
l
)
(
N
o
n
e
,
1
0
,
1
1
0
)
d
r
o
p
o
u
t
_
2
(
D
r
o
p
o
u
t
)
(
N
o
n
e
,
1
0
,
1
1
0
)
a
d
d
_
1
(
A
d
d
)
(
N
o
n
e
,
1
0
,
1
1
0
)
g
l
o
b
a
l
_
a
v
e
r
a
g
e
_
p
o
o
l
i
n
g
1
d
(
G
l
o
b
a
l
A
v
e
r
a
g
e
P
o
o
l
i
n
g
1
D
)
(
N
o
n
e
,
1
0
)
d
e
n
se
(
D
e
n
s
e
)
(
N
o
n
e
,
2
5
6
)
d
r
o
p
o
u
t
_
3
(
D
r
o
p
o
u
t
)
(
N
o
n
e
,
2
5
6
)
d
e
n
se
_
1
(
D
e
n
se)
(
N
o
n
e
,
1
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
n
en
h
a
n
ce
men
t o
f sto
ck
p
r
ic
e
fo
r
ec
a
s
tin
g
b
a
s
ed
o
n
h
y
b
r
id
…
(
P
h
a
m
Ho
a
n
g
V
u
o
n
g
)
1301
I
n
o
u
r
m
o
d
el,
m
u
lti
-
h
ea
d
atte
n
tio
n
an
d
la
y
er
n
o
r
m
aliza
tio
n
ar
e
ap
p
lied
at
th
e
in
p
u
t
s
tag
e
to
id
en
tify
g
lo
b
al
d
ep
en
d
en
cies
in
s
to
ck
d
ata
s
eq
u
en
ce
s
.
T
h
e
C
o
n
v
1
D
lay
er
th
en
ca
p
tu
r
es
lo
ca
l
tem
p
o
r
al
p
atter
n
s
an
d
s
h
o
r
t
-
ter
m
f
lu
ct
u
atio
n
s
in
p
r
ice
m
o
v
em
e
n
ts
.
Fo
llo
win
g
th
is
,
a
B
iLST
M
lay
er
p
r
o
ce
s
s
es
th
e
s
eq
u
en
tial
d
ata
in
b
o
th
f
o
r
war
d
an
d
b
ac
k
war
d
d
ir
ec
tio
n
s
,
en
ab
lin
g
th
e
m
o
d
e
l
to
lear
n
f
r
o
m
b
o
th
p
ast
an
d
f
u
tu
r
e
tim
e
s
tep
s
.
Dr
o
p
o
u
t
lay
er
s
a
r
e
a
d
d
ed
to
p
r
ev
en
t
o
v
er
f
itti
n
g
,
w
h
ile
Ad
d
l
ay
er
s
estab
lis
h
r
esid
u
al
co
n
n
e
ctio
n
s
th
at
s
tab
ilize
tr
ain
in
g
a
n
d
p
r
eser
v
e
im
p
o
r
ta
n
t
lear
n
e
d
f
ea
t
u
r
es.
T
h
e
o
u
tp
u
t
f
r
o
m
th
e
B
iLST
M
is
p
ass
ed
th
r
o
u
g
h
a
g
lo
b
al
av
er
ag
e
p
o
o
lin
g
lay
er
t
o
r
ed
u
ce
d
im
en
s
io
n
ality
.
Fin
ally
,
two
Den
s
e
lay
er
s
p
er
f
o
r
m
t
h
e
r
eg
r
ess
io
n
task
.
Ov
er
all,
o
u
r
h
y
b
r
id
co
n
f
i
g
u
r
a
tio
n
allo
ws
th
e
m
o
d
el
to
ef
f
e
ctiv
ely
ca
p
tu
r
e
s
h
o
r
t
-
ter
m
d
e
p
en
d
en
cies
t
h
r
o
u
g
h
co
n
v
o
l
u
tio
n
al
an
d
r
ec
u
r
r
en
t
lay
er
s
an
d
lo
n
g
-
ter
m
r
elatio
n
s
h
ip
s
th
r
o
u
g
h
s
elf
-
atten
tio
n
m
ec
h
an
is
m
s
.
T
h
e
in
teg
r
atio
n
o
f
T
r
an
s
f
o
r
m
er
wi
th
B
iLST
M
an
d
C
NN
co
m
p
o
n
en
ts
lead
s
to
im
p
r
o
v
e
d
p
r
ed
i
ctio
n
p
e
r
f
o
r
m
an
ce
an
d
r
o
b
u
s
tn
ess
in
s
to
ck
p
r
ice
f
o
r
ec
asti
n
g
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
Da
t
a
co
llect
io
n
a
nd
pre
-
pro
ce
s
s
ing
W
e
in
v
esti
g
ate
p
er
f
o
r
m
an
ce
o
f
o
u
r
m
eth
o
d
f
o
r
p
r
e
d
ictin
g
s
t
o
ck
p
r
ices
b
y
u
s
in
g
a
d
ataset
at
Yah
o
o
web
s
ite
(
h
ttp
s
:
//fi
n
a
n
ce
.
ya
h
o
o
.
co
m/
)
[
2
5
]
.
T
h
e
d
ataset
in
clu
d
es
ten
lead
i
n
g
c
o
m
p
an
ie
s
⎯
Alp
h
ab
et
I
n
c.
,
Am
az
o
n
,
Ap
p
le,
B
aid
u
,
I
n
tel,
Mic
r
o
s
o
f
t,
Netf
lix
,
NVI
DI
A
,
T
en
ce
n
t
an
d
T
esla
⎯
ch
o
s
en
f
o
r
th
ei
r
s
tr
o
n
g
m
ar
k
et
im
p
ac
t
an
d
v
o
latilit
y
.
E
ac
h
d
ataset
s
p
an
s
f
r
o
m
J
an
u
ar
y
3
,
2
0
1
2
,
to
Dec
em
b
er
2
4
,
2
0
2
0
,
with
2
,
2
6
1
s
am
p
les.
T
ab
le
2
p
r
esen
ts
th
e
s
tatis
t
ical
an
aly
s
i
s
o
f
clo
s
in
g
p
r
ices
o
f
v
ar
io
u
s
s
to
ck
in
d
ices.
Fro
m
T
ab
le
2
,
we
r
ea
lized
th
at
Am
az
o
n
h
as
th
e
h
ig
h
est
a
v
er
ag
e
p
r
ice
an
d
v
o
latilit
y
,
wh
ile
I
n
tel
is
th
e
m
o
s
t
s
tab
le
with
th
e
lo
west
av
er
ag
e
p
r
ice
an
d
s
tan
d
ar
d
d
ev
iatio
n
.
T
esla
an
d
NVI
DI
A
also
s
h
o
w
r
elativ
ely
h
ig
h
s
tan
d
ar
d
d
ev
iatio
n
s
(
3
1
.
5
5
a
n
d
3
2
.
7
8
,
r
esp
ec
tiv
ely
)
co
m
p
a
r
ed
to
th
ei
r
m
ea
n
s
,
in
d
icatin
g
h
ig
h
v
o
latilit
y
an
d
s
ig
n
if
ican
t
p
r
ice
f
lu
ctu
atio
n
s
.
C
o
m
p
an
ie
s
lik
e
B
aid
u
an
d
Mic
r
o
s
o
f
t
s
h
o
w
m
ed
ian
s
clo
s
e
to
th
eir
r
esp
ec
tiv
e
m
ea
n
s
,
in
d
icatin
g
a
m
o
r
e
s
y
m
m
etr
i
c
d
is
tr
ib
u
tio
n
o
f
d
aily
p
r
ice
s
.
Mo
r
e
estab
lis
h
ed
co
m
p
an
ies
lik
e
I
n
tel
an
d
Mic
r
o
s
o
f
t,
wh
ile
s
till
s
h
o
win
g
g
r
o
wth
,
d
em
o
n
s
tr
ate
g
r
ea
ter
s
tab
ilit
y
.
T
h
e
d
iv
er
s
e
b
eh
av
i
o
r
s
o
f
th
ese
s
to
ck
s
,
f
r
o
m
h
ig
h
v
o
latilit
y
to
s
tab
ilit
y
,
m
ak
e
th
em
s
u
itab
le
f
o
r
m
o
d
elin
g
s
to
ck
p
r
ice
p
r
e
d
ictio
n
s
.
T
h
is
v
alu
e
is
co
m
m
o
n
l
y
u
tili
ze
d
to
d
ete
r
m
in
e
wh
eth
er
a
tr
a
n
s
ac
tio
n
r
es
u
lted
in
a
p
r
o
f
it
o
r
lo
s
s
.
Mo
r
eo
v
er
,
it
p
r
o
v
id
es
cr
itical
in
f
o
r
m
atio
n
f
o
r
in
v
esto
r
s
.
T
h
er
ef
o
r
e,
we
u
s
e
clo
s
in
g
p
r
ice
as f
o
r
ec
asti
n
g
ta
r
g
et.
I
n
o
u
r
ex
p
er
im
en
ts
,
t
h
e
d
atas
et
was
s
p
lit
in
to
8
0
%
f
o
r
tr
ai
n
in
g
a
n
d
2
0
%
f
o
r
test
in
g
,
wh
ile
2
0
%
o
f
tr
ain
in
g
d
ata
was
f
u
r
t
h
er
u
s
ed
f
o
r
v
alid
atio
n
.
B
ef
o
r
e
im
p
l
em
en
tin
g
th
e
p
r
e
d
ictio
n
m
eth
o
d
,
p
r
ep
r
o
ce
s
s
in
g
is
ess
en
tial.
T
o
d
ec
r
ea
s
e
d
is
p
ar
ities
an
d
in
co
n
s
is
ten
cies
in
th
e
d
ata
an
d
en
h
an
ce
th
e
ac
cu
r
ac
y
o
f
o
u
r
f
o
r
ec
asti
n
g
s
y
s
tem
,
d
ata
n
o
r
m
aliza
tio
n
is
em
p
lo
y
ed
.
W
e
u
tili
ze
th
e
Min
Ma
x
Scaler
m
eth
o
d
t
o
s
ca
le
d
ata
v
alu
es
in
t
o
th
e
[
0
,
1
]
in
ter
v
al.
T
ab
le
2
.
Statis
tical
d
escr
ip
tio
n
o
f
clo
s
in
g
p
r
ice
o
f
v
ar
io
u
s
s
to
ck
in
d
ices o
v
e
r
th
e
s
tu
d
y
p
er
io
d
S
t
o
c
k
i
n
d
e
x
D
a
i
l
y
M
e
a
n
SD
M
e
d
i
a
n
M
i
n
M
a
x
A
p
p
l
e
3
8
.
6
4
2
4
.
1
3
2
9
.
7
7
1
3
.
9
4
1
3
4
.
1
7
A
maz
o
n
1
0
0
9
.
2
0
8
2
2
.
8
6
7
2
6
.
7
2
1
7
5
.
9
2
3
5
3
1
.
4
4
N
V
I
D
I
A
2
9
.
7
5
3
2
.
7
8
1
1
.
8
8
2
.
8
4
1
4
5
.
6
1
Te
sl
a
2
3
.
0
5
3
1
.
5
5
1
5
.
8
1
1
.
5
1
2
3
1
.
6
6
N
e
t
f
l
i
x
1
7
2
.
7
8
1
4
8
.
4
9
1
0
9
.
9
5
7
.
6
8
5
5
6
.
5
4
Te
n
c
e
n
t
2
9
.
0
4
1
9
.
0
1
2
2
.
6
9
3
.
9
9
8
0
.
8
3
M
i
c
r
o
s
o
f
t
7
7
.
9
5
5
2
.
0
6
5
5
.
6
6
2
6
.
3
7
2
3
1
.
6
4
I
n
t
e
l
3
7
.
4
3
1
1
.
6
3
3
4
.
8
6
1
9
.
3
6
6
8
.
4
7
A
l
p
h
a
b
e
t
I
n
c
.
4
0
.
8
9
1
8
.
5
1
3
7
.
5
8
1
3
.
9
2
9
1
.
3
9
B
a
i
d
u
1
6
5
.
4
3
4
6
.
9
7
1
6
6
.
2
2
8
3
.
5
8
2
8
4
.
0
7
S
D
:
st
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
3
.
2
.
E
x
perim
ent
s
et
up
C
h
o
o
s
in
g
an
ap
p
r
o
p
r
iate
tim
e
s
tep
p
r
esen
ts
s
ig
n
i
f
ican
t
c
h
allen
g
es
in
tim
e
s
er
ies
f
o
r
ec
asti
n
g
.
A
to
o
s
m
all
tim
estep
ca
n
ca
u
s
e
lar
g
e
d
ev
iatio
n
s
an
d
ex
ce
s
s
iv
ely
h
ig
h
c
o
m
p
u
tatio
n
co
s
t,
o
v
er
lo
o
k
in
g
im
p
ac
t
o
f
g
lo
b
al
m
ar
k
et
f
ac
to
r
s
.
C
o
n
v
er
s
ely
,
a
lar
g
e
tim
e
s
tep
m
a
y
in
tr
o
d
u
ce
h
ig
h
v
o
latilit
y
,
r
ed
u
ci
n
g
th
e
ac
c
u
r
ac
y
o
f
p
r
ed
ictio
n
s
.
B
ased
o
n
ex
p
e
r
im
en
ts
,
we
u
tili
ze
a
tim
e
s
tep
o
f
1
0
.
I
t in
co
r
p
o
r
ates a
6
0
-
h
ea
d
m
u
lti
-
h
ea
d
atten
tio
n
m
ec
h
an
is
m
,
a
5
5
-
u
n
it
B
i
-
L
STM
lay
er
,
an
d
o
n
e
T
r
a
n
s
f
o
r
m
e
r
b
lo
ck
s
.
A
d
en
s
e
lay
e
r
with
2
5
6
r
ec
tifie
d
lin
ea
r
u
n
it
(
R
eL
U)
u
n
its
an
d
a
d
r
o
p
o
u
t
r
ate
o
f
0
.
3
is
ap
p
lied
b
ef
o
r
e
th
e
f
in
al
lin
ea
r
o
u
tp
u
t
lay
er
.
Du
r
in
g
th
e
tr
ain
in
g
p
r
o
ce
s
s
,
lear
n
in
g
r
ate
was
s
et
to
0
.
0
0
0
1
.
T
h
e
n
etwo
r
k
is
tr
ain
ed
u
s
in
g
th
e
b
ac
k
p
r
o
p
ag
atio
n
alg
o
r
ith
m
with
th
e
Ad
am
o
p
tim
izer
,
a
b
atch
s
ize
o
f
2
0
,
an
d
1
0
0
e
p
o
ch
s
.
L
o
s
s
f
u
n
ctio
n
is
ca
lcu
lated
b
y
MSE
lo
s
s
.
Mo
d
el
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
3
,
J
u
n
e
20
2
6
:
1
2
9
8
-
1
3
0
6
1302
ac
cu
r
ac
y
was a
s
s
ess
ed
u
s
in
g
r
o
o
t m
ea
n
s
q
u
ar
e
e
r
r
o
r
(
R
MSE
)
,
m
ea
n
ab
s
o
lu
te
er
r
o
r
(
MA
E
)
,
an
d
m
ea
n
ab
s
o
lu
te
p
er
ce
n
tag
e
e
r
r
o
r
(
MA
PE
)
as p
er
f
o
r
m
a
n
ce
m
etr
ics.
3
.
3
.
Resul
t
s
a
na
ly
s
is
I
n
th
is
s
ec
tio
n
,
th
e
well
-
k
n
o
wn
f
o
r
ec
asti
n
g
m
o
d
els,
an
d
o
u
r
h
y
b
r
id
m
o
d
el
in
s
to
ck
p
r
ice
f
o
r
ec
asti
n
g
ar
e
ev
alu
ated
.
W
e
ex
p
lo
r
e
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
ese
m
o
d
els
o
n
ten
s
to
ck
p
r
ice
in
d
ices.
T
ab
le
3
co
m
p
ar
es
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
m
o
d
els
o
n
th
e
s
to
ck
d
atasets
.
Ou
r
m
o
d
el’
s
ac
cu
r
ac
y
v
ar
ies
ac
r
o
s
s
d
if
f
er
en
t
s
to
ck
s
,
r
ef
lectin
g
ea
ch
s
to
ck
’
s
u
n
iq
u
e
v
o
latilit
y
an
d
m
a
r
k
et
b
e
h
av
io
r
.
T
ab
le
3
.
Per
f
o
r
m
an
ce
o
f
d
if
f
er
en
t a
p
p
r
o
ac
h
es a
cr
o
s
s
ten
s
to
c
k
in
d
ices
M
e
a
su
r
e
s
M
o
d
e
l
A
R
I
M
A
LSTM
C
N
N
+
LST
M
C
R
N
N
+
A
t
t
e
n
t
i
o
n
Tr
a
n
sf
o
r
mer
O
u
r
mo
d
e
l
A
p
p
l
e
(
A
A
P
L)
R
M
S
E
0
.
0
6
4
0
.
0
3
1
0
.
0
3
3
0
.
0
2
4
0
.
0
2
1
0
.
0
2
2
M
A
E
0
.
0
4
4
0
.
0
2
4
0
.
0
2
3
0
.
0
1
7
0
.
0
1
4
0
.
0
1
4
M
A
P
E
4
.
4
8
8
2
.
4
7
1
2
.
3
2
7
1
.
7
0
5
1
.
4
8
2
1
.
4
2
2
A
maz
o
n
(
A
M
ZN
)
R
M
S
E
0
.
0
3
7
0
.
0
2
4
0
.
0
3
7
0
.
0
2
4
0
.
0
1
7
0
.
0
2
6
M
A
E
0
.
0
2
6
0
.
0
1
8
0
.
0
2
7
0
.
0
1
7
0
.
0
1
2
0
.
0
1
8
M
A
P
E
2
.
6
3
5
1
.
8
7
3
2
.
7
0
4
1
.
7
0
2
1
.
2
9
3
1
.
8
1
4
N
V
I
D
I
A
(
N
V
D
A
)
R
M
S
E
0
.
0
4
5
0
.
0
3
3
0
.
0
5
2
0
.
0
6
8
0
.
0
1
9
0
.
0
2
1
M
A
E
0
.
0
3
2
0
.
0
2
2
0
.
0
3
6
0
.
0
4
4
0
.
0
1
3
0
.
0
1
4
M
A
P
E
3
.
2
2
4
2
.
2
7
5
3
.
6
9
3
4
.
4
6
9
1
.
3
5
4
1
.
4
4
5
Te
sl
a
(
TSLA
)
R
M
S
E
0
.
2
3
4
0
.
0
2
3
0
.
0
3
2
0
.
0
2
1
0
.
0
1
8
0
.
0
1
8
M
A
E
0
.
1
3
1
0
.
0
1
3
0
.
0
2
3
0
.
0
1
4
0
.
0
1
0
0
.
0
1
0
M
A
P
E
1
.
3
1
9
1
.
3
3
8
2
.
3
9
5
1
.
4
1
2
1
.
0
9
7
0
.
9
9
9
N
e
t
f
l
i
x
(
N
F
LX
)
R
M
S
E
0
.
0
3
4
0
.
0
4
1
0
.
0
3
8
0
.
0
3
7
0
.
0
3
5
0
.
0
3
5
M
A
E
0
.
0
2
5
0
.
0
2
9
0
.
0
2
8
0
.
0
2
7
0
.
0
2
4
0
.
0
2
4
M
A
P
E
2
.
5
1
7
2
.
9
1
3
2
.
8
2
7
2
.
7
6
1
2
.
4
2
9
2
.
4
3
4
Te
n
c
e
n
t
(
TC
EH
Y
)
R
M
S
E
0
.
0
3
5
0
.
0
3
4
0
.
0
3
5
0
.
0
3
3
0
.
0
3
9
0
.
0
3
0
M
A
E
0
.
0
2
7
0
.
0
2
5
0
.
0
2
6
0
.
0
2
4
0
.
0
2
3
0
.
0
2
1
M
A
P
E
2
.
7
7
4
2
.
5
0
3
2
.
6
3
4
2
.
4
8
4
2
.
3
9
6
2
.
1
8
9
M
i
c
r
o
s
o
f
t
(
M
S
F
T)
R
M
S
E
0
.
0
5
4
0
.
0
3
8
0
.
0
3
3
0
.
0
3
2
0
.
0
3
1
0
.
0
3
1
M
A
E
0
.
0
3
7
0
.
0
2
6
0
.
0
2
3
0
.
0
2
2
0
.
0
2
1
0
.
0
2
0
M
A
P
E
3
.
7
3
3
2
.
6
8
9
2
.
3
3
1
2
.
2
1
6
2
.
1
0
9
2
.
0
5
8
I
n
t
e
l
(
I
N
TC
)
R
M
S
E
0
.
0
6
8
0
.
0
6
2
0
.
0
6
8
0
.
0
7
0
0
.
0
5
9
0
.
0
5
9
M
A
E
0
.
0
4
6
0
.
0
3
9
0
.
0
4
4
0
.
0
4
2
0
.
0
3
7
0
.
0
3
6
M
A
P
E
4
.
6
9
3
3
.
9
1
2
4
.
4
4
4
4
.
2
2
4
3
.
7
5
0
3
.
6
0
1
A
l
p
h
a
b
e
t
I
n
c
.
(
G
O
O
G
)
R
M
S
E
0
.
0
3
9
0
.
0
3
9
0
.
0
3
7
0
.
0
3
6
0
.
0
3
4
0
.
0
3
4
M
A
E
0
.
0
2
8
0
.
0
2
7
0
.
0
2
7
0
.
0
2
6
0
.
0
2
2
0
.
0
2
2
M
A
P
E
2
.
8
3
4
2
.
7
7
8
2
.
7
2
1
2
.
6
0
9
2
.
2
7
9
2
.
2
6
8
B
a
i
d
u
(
B
I
D
U
)
R
M
S
E
0
.
0
2
6
0
.
0
3
4
0
.
0
3
8
0
.
0
3
4
0
.
0
3
0
0
.
0
3
1
M
A
E
0
.
0
1
8
0
.
0
2
2
0
.
0
2
5
0
.
0
2
3
0
.
0
2
0
0
.
0
2
1
M
A
P
E
1
.
8
1
5
2
.
2
5
3
2
.
5
4
2
2
.
3
5
9
2
.
0
4
8
2
.
0
6
8
As
s
h
o
wn
in
T
ab
le
3
,
AAPL
a
n
d
AM
Z
N
ac
h
iev
e
th
e
h
ig
h
est
ac
cu
r
ac
y
with
th
e
lo
west
R
MSE
,
MA
E
,
an
d
MA
PE
v
alu
es.
T
SLA
als
o
p
er
f
o
r
m
s
well
with
lo
w
e
r
r
o
r
r
ates,
wh
ile
NVDA
,
MSFT,
an
d
B
I
DU
s
h
o
w
m
o
d
er
ate
e
r
r
o
r
s
.
I
n
c
o
n
tr
ast,
NFLX
,
T
C
E
HY,
GOOG
,
an
d
esp
ec
ially
I
NT
C
o
b
tain
h
ig
h
er
er
r
o
r
s
ac
r
o
s
s
all
m
etr
ics,
in
d
icatin
g
g
r
ea
ter
p
r
e
d
ictio
n
d
if
f
icu
lty
.
Fig
u
r
e
3
co
m
p
ar
es
ac
tu
al
a
n
d
p
r
ed
icted
s
to
ck
p
r
ices
ac
r
o
s
s
m
u
ltip
le
co
m
p
an
ies,
r
ev
ea
lin
g
o
u
r
m
o
d
el’
s
f
o
r
ec
asti
n
g
p
e
r
f
o
r
m
a
n
ce
.
Fo
r
AAPL
an
d
MSFT
as
s
h
o
wn
in
Fig
u
r
e
s
3
(
a)
an
d
3
(
g
)
,
p
r
ed
ic
tio
n
s
clo
s
ely
f
o
llo
w
ac
tu
al
tr
en
d
s
,
r
ef
lectin
g
s
tr
o
n
g
p
er
f
o
r
m
an
ce
with
s
tab
le
s
to
ck
s
.
AM
Z
N
an
d
GOOG
,
a
s
s
h
o
wn
in
Fig
u
r
e
s
3
(
b
)
an
d
3
(
i)
,
also
s
h
o
w
ac
cu
r
ate
tr
en
d
ca
p
tu
r
e,
with
s
lig
h
t
lag
d
u
r
in
g
r
ap
id
p
r
ice
in
cr
ea
s
e.
T
h
e
m
o
d
el
ca
p
tu
r
es
lo
n
g
-
te
r
m
p
atter
n
s
b
u
t
s
tr
u
g
g
les
in
h
ig
h
ly
v
o
latile
ca
s
es
s
u
ch
as
NVDA
an
d
T
SLA
as
s
h
o
wn
in
Fig
u
r
e
s
3
(
c)
an
d
3
(
d
)
.
NFLX
,
I
NT
C
an
d
B
I
DU,
as
s
h
o
wn
in
Fig
u
r
e
s
3
(
e)
,
3
(
h
)
an
d
3
(
j)
,
a
ch
iev
e
m
o
d
er
ate
ac
cu
r
ac
y
,
w
h
ile
T
C
E
HY
as
s
h
o
wn
in
Fig
u
r
e
3
(
f
)
p
r
ed
ictio
n
s
o
cc
asio
n
ally
d
iv
er
g
e
y
et
s
till
ca
p
tu
r
e
o
v
er
all
tr
en
d
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
n
en
h
a
n
ce
men
t o
f sto
ck
p
r
ic
e
fo
r
ec
a
s
tin
g
b
a
s
ed
o
n
h
y
b
r
id
…
(
P
h
a
m
Ho
a
n
g
V
u
o
n
g
)
1303
Fu
r
th
er
m
o
r
e
,
we
ev
alu
ate
th
e
p
er
f
o
r
m
an
ce
o
f
o
u
r
m
eth
o
d
in
co
m
p
ar
is
o
n
to
o
th
er
well
-
k
n
o
wn
m
o
d
els
in
p
r
ed
ictin
g
m
ar
k
et
p
r
ices
as
s
h
o
wn
in
T
ab
le
3
.
Dif
f
er
en
t
m
o
d
els,
in
clu
d
in
g
AR
I
MA
[
4
]
,
[
9
]
,
L
STM
[
1
3
]
,
[
3
2
]
,
C
NN+
L
STM
[
1
9
]
,
[
2
9
]
,
C
R
NN+
Atten
tio
n
[
2
3
]
,
[
2
9
]
,
[
3
0
]
,
T
r
a
n
s
f
o
r
m
er
[
3
3
]
,
[
3
4
]
,
an
d
p
r
o
p
o
s
ed
h
y
b
r
id
m
o
d
el,
h
av
e
b
ee
n
ev
a
lu
ated
o
n
ten
s
to
ck
p
r
ice
d
at
asets
.
First,
we
co
n
s
id
er
t
h
at
class
ical
AR
I
MA
m
o
d
el
g
en
er
ally
o
b
tain
s
h
ig
h
er
er
r
o
r
r
ates
ac
r
o
s
s
all
d
atasets
.
T
h
e
AR
I
MA
r
esu
lts
r
ef
le
ct
its
lim
itatio
n
s
in
ca
p
tu
r
in
g
n
o
n
lin
ea
r
d
y
n
am
ics
o
f
s
to
ck
d
ata.
I
ts
ef
f
ec
tiv
e
n
e
s
s
is
lim
ited
,
p
ar
ticu
lar
ly
in
f
i
n
an
cial
tim
e
s
er
ies,
wh
ich
o
f
ten
p
r
esen
t n
o
n
lin
ea
r
an
d
n
o
n
-
s
tatio
n
ar
y
ch
ar
ac
ter
is
tics
[
3
2
]
,
[
3
5
]
.
(
a)
(
b
)
(
c)
(
d
)
(
e)
(f)
(
g
)
(
h
)
(
i)
(
j)
Fig
u
r
e
3
.
R
esu
lts
o
f
s
to
ck
p
r
ice
f
o
r
ec
asti
n
g
o
f
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
o
n
ten
s
to
ck
d
ata
(
a)
AA
PL,
(
b
)
AM
Z
N,
(
c)
NVDA
,
(
d
)
T
SLA,
(
e
)
NFLX
,
(
f
)
T
C
E
HY,
(
g
)
MSFT,
(
h
)
I
NT
C
,
(
i)
GOOG
,
an
d
(
j
)
B
I
DU
T
h
e
r
esu
lts
in
T
ab
le
3
in
d
icate
th
at
d
ee
p
lear
n
in
g
m
o
d
e
ls
o
u
tp
er
f
o
r
m
th
e
AR
I
MA
o
n
s
ev
er
al
d
atasets
.
Sp
ec
if
ically
,
L
STM
m
o
d
el
d
em
o
n
s
tr
ates
b
etter
p
er
f
o
r
m
a
n
ce
co
m
p
ar
ed
to
AR
I
MA
,
in
d
icatin
g
th
eir
ca
p
ab
ilit
y
to
m
o
d
el
s
to
ck
d
a
ta
with
lo
n
g
-
ter
m
d
ep
e
n
d
en
c
ies.
W
h
ile
co
m
b
in
in
g
co
n
v
o
l
u
tio
n
al
lay
er
s
with
r
ec
u
r
r
en
t
la
y
er
s
,
C
NN+
L
STM
m
o
d
el
ca
n
ca
p
tu
r
e
tem
p
o
r
al
an
d
s
eq
u
en
tial
d
ep
en
d
en
ci
es
in
tim
e
Ser
ie
d
ata
[
1
9
]
,
[
2
0
]
.
T
h
e
y
ca
n
o
u
tp
e
r
f
o
r
m
L
STM
m
o
d
els
alo
n
e.
T
h
e
C
R
NN+
Atten
tio
n
h
as
led
to
en
h
a
n
ce
d
p
er
f
o
r
m
an
ce
o
f
th
e
p
r
ed
ictio
n
m
o
d
el.
Ad
d
itio
n
ally
,
T
r
an
s
f
o
r
m
er
m
o
d
els
o
f
ten
o
u
tp
e
r
f
o
r
m
o
th
er
ap
p
r
o
ac
h
es,
d
em
o
n
s
tr
atin
g
th
eir
ab
ilit
y
to
ca
p
tu
r
e
co
m
p
le
x
d
ep
en
d
en
cie
s
u
s
in
g
m
u
lti
-
h
ea
d
atten
tio
n
.
Ou
r
p
r
o
p
o
s
ed
h
y
b
r
id
m
o
d
el
c
o
n
s
is
ten
tly
y
ield
s
th
e
b
est
p
er
f
o
r
m
a
n
ce
ac
r
o
s
s
m
o
s
t
d
atasets
.
T
h
e
s
ig
n
if
ican
t
p
er
f
o
r
m
a
n
ce
o
f
o
u
r
h
y
b
r
id
m
o
d
el
i
n
d
icate
s
a
p
r
o
m
is
in
g
ar
ea
f
o
r
f
u
tu
r
e
r
esear
ch
.
3
.
4
.
Resea
rc
h lim
it
a
t
io
ns
T
h
e
m
o
s
t
s
ig
n
if
ican
t
d
r
awb
ac
k
o
f
o
u
r
wo
r
k
is
th
e
h
i
g
h
co
m
p
u
tatio
n
al
tim
e.
T
h
e
AR
I
M
A
m
o
d
el
is
th
e
f
astes
t
m
eth
o
d
an
d
d
o
es
n
o
t
r
eq
u
ir
e
GPU
co
m
p
u
tin
g
.
Dee
p
lear
n
in
g
ap
p
r
o
ac
h
es
u
s
e
GPU
co
m
p
u
tin
g
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
3
,
J
u
n
e
20
2
6
:
1
2
9
8
-
1
3
0
6
1304
r
esu
ltin
g
in
i
n
cr
ea
s
ed
c
o
m
p
u
t
atio
n
co
s
t
[
3
6
]
.
T
h
e
in
co
r
p
o
r
a
tio
n
o
f
th
e
B
iLST
M
lay
er
ad
d
s
to
th
e
c
o
m
p
lex
it
y
an
d
co
m
p
u
tatio
n
al
e
x
p
en
s
e
o
f
th
e
m
o
d
el,
m
ak
i
n
g
r
ea
l
-
tim
e
f
o
r
ec
asti
n
g
c
h
allen
g
in
g
.
Ad
d
itio
n
ally
,
f
in
d
in
g
o
p
tim
al
p
a
r
am
eter
s
f
o
r
ea
ch
s
to
ck
d
ataset
p
r
o
v
ed
d
if
f
ic
u
lt,
as
v
ar
iatio
n
s
in
m
ar
k
et
b
eh
av
i
o
r
d
em
an
d
d
is
tin
ct
co
n
f
ig
u
r
atio
n
s
.
Fu
r
th
e
r
m
o
r
e,
r
ely
in
g
o
n
l
y
o
n
h
is
to
r
ical
d
ata
f
o
r
p
r
ed
ictin
g
f
u
tu
r
e
v
alu
es
m
ak
es
it
ch
allen
g
in
g
to
ad
d
r
ess
s
u
d
d
en
ch
an
g
es,
wh
ich
v
ar
y
d
if
f
e
r
en
t sto
ck
s
d
u
r
in
g
p
er
i
o
d
s
o
f
h
ig
h
v
o
latilit
y
o
r
u
n
ex
p
ec
te
d
m
ar
k
et
ev
en
ts
.
T
h
e
r
ef
o
r
e
,
in
te
g
r
atin
g
ex
ter
n
al
d
ata
s
o
u
r
ce
s
lik
e
n
ews
s
en
tim
en
t
o
r
o
th
e
r
m
a
r
k
et
in
d
icato
r
s
,
co
u
ld
en
h
an
ce
a
d
ap
tab
ilit
y
to
r
ea
l
-
wo
r
ld
v
o
latilit
y
.
4.
CO
NCLU
SI
O
N
I
n
th
is
s
tu
d
y
,
we
in
tr
o
d
u
ce
d
a
h
y
b
r
id
m
o
d
el
f
o
r
s
to
c
k
p
r
ice
f
o
r
ec
asti
n
g
th
at
in
teg
r
ates
B
iLST
M
in
to
th
e
f
ee
d
-
f
o
r
war
d
lay
er
o
f
T
r
a
n
s
f
o
r
m
er
m
o
d
el,
we
ad
d
r
ess
ed
lim
itatio
n
s
in
ca
p
tu
r
in
g
l
o
c
al
an
d
lo
n
g
-
r
a
n
g
e
tem
p
o
r
al
d
ep
en
d
en
cies
in
s
to
c
k
p
r
ices.
T
h
e
m
o
d
el
tak
es
ad
v
an
tag
e
o
f
B
iLST
M’
s
s
tr
en
g
th
in
s
eq
u
en
tial
d
ata
p
r
o
ce
s
s
in
g
an
d
t
h
e
T
r
an
s
f
o
r
m
er
’
s
s
elf
-
atten
tio
n
m
ec
h
an
is
m
,
wh
ich
allo
ws
f
o
r
g
lo
b
al
c
o
n
t
ex
t
u
n
d
er
s
tan
d
in
g
.
Ou
r
ex
p
er
im
e
n
ts
s
h
o
w
th
at
th
e
m
o
d
el
co
n
s
is
ten
tly
o
v
e
r
c
a
m
e
b
aselin
e
ap
p
r
o
ac
h
es,
d
eliv
er
in
g
b
etter
ac
cu
r
ac
y
in
f
o
r
ec
asti
n
g
s
to
ck
p
r
ices
ac
r
o
s
s
m
o
s
t
d
ataset
s
.
Fu
tu
r
e
wo
r
k
will
aim
to
o
p
tim
ize
th
e
m
o
d
el
f
o
r
r
ea
l
-
tim
e
u
s
e
an
d
en
h
an
ce
its
p
r
e
d
ictiv
e
a
cc
u
r
ac
y
b
y
in
te
g
r
atin
g
m
u
lti
v
ar
iate
f
o
r
ec
asti
n
g
m
eth
o
d
s
an
d
in
co
r
p
o
r
atin
g
ad
d
itio
n
al
d
ata
s
o
u
r
ce
s
,
in
clu
d
in
g
m
ar
k
et
s
en
tim
e
n
t a
n
d
ec
o
n
o
m
ic
in
d
icato
r
s
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Ph
am
Ho
an
g
Vu
o
n
g
✓
✓
✓
✓
✓
✓
✓
✓
✓
L
am
Hu
n
g
Ph
u
✓
✓
✓
✓
L
e
Nh
at
Du
y
✓
✓
Ph
am
T
h
e
B
ao
✓
✓
✓
T
an
Dat
T
r
in
h
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
Data
av
ailab
ilit
y
is
n
o
t
ap
p
li
ca
b
le
to
th
is
p
ap
er
as
n
o
n
e
w
d
ata
wer
e
cr
ea
ted
o
r
an
aly
ze
d
in
th
is
s
tu
d
y
.
RE
F
E
R
E
NC
E
S
[
1
]
P
.
H
.
V
u
o
n
g
,
L.
H
.
P
h
u
,
T.
H
.
V
a
n
N
g
u
y
e
n
,
L.
N
.
D
u
y
,
P
.
T
.
B
a
o
,
a
n
d
T.
D
.
Tr
i
n
h
,
“
A
b
i
b
l
i
o
me
t
r
i
c
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
o
f
s
t
o
c
k
p
r
i
c
e
f
o
r
e
c
a
st
i
n
g
:
F
r
o
m
s
t
a
t
i
s
t
i
c
a
l
m
o
d
e
l
t
o
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
S
c
i
e
n
c
e
Pr
o
g
r
e
ss
,
v
o
l
.
1
0
7
,
n
o
.
1
,
p
.
0
0
3
6
8
5
0
4
2
4
1
2
3
6
5
5
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
7
7
/
0
0
3
6
8
5
0
4
2
4
1
2
3
6
5
5
7
.
[
2
]
I
.
K
.
N
t
i
,
A
.
F
.
A
d
e
k
o
y
a
,
a
n
d
B
.
A
.
W
e
y
o
r
i
,
“
A
sy
s
t
e
m
a
t
i
c
r
e
v
i
e
w
o
f
f
u
n
d
a
me
n
t
a
l
a
n
d
t
e
c
h
n
i
c
a
l
a
n
a
l
y
si
s
o
f
st
o
c
k
mar
k
e
t
p
r
e
d
i
c
t
i
o
n
s,”
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
R
e
v
i
e
w
,
v
o
l
.
5
3
,
n
o
.
4
,
p
p
.
3
0
0
7
–
3
0
5
7
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
4
6
2
-
0
1
9
-
0
9
7
5
4
-
z.
[
3
]
M
.
M
.
K
u
m
b
u
r
e
,
C
.
L
o
h
r
ma
n
n
,
P
.
L
u
u
k
k
a
,
a
n
d
J.
P
o
r
r
a
s
,
“
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
a
n
d
d
a
t
a
f
o
r
st
o
c
k
mark
e
t
f
o
r
e
c
a
s
t
i
n
g
:
A
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
,
”
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
.
1
9
7
,
p
.
1
1
6
6
5
9
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
2
.
1
1
6
6
5
9
.
[
4
]
A
.
S
u
b
a
k
k
a
r
,
S
.
G
r
a
c
e
l
i
n
e
Jasm
i
n
e
,
L.
Ja
n
i
A
n
b
a
r
a
si
,
J.
G
a
n
e
s
h
,
a
n
d
C
.
M
.
Y
u
k
t
h
a
S
r
i
,
“
A
n
a
n
a
l
y
s
i
s
o
n
T
e
sl
a
’
s
st
o
c
k
p
r
i
c
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
n
en
h
a
n
ce
men
t o
f sto
ck
p
r
ic
e
fo
r
ec
a
s
tin
g
b
a
s
ed
o
n
h
y
b
r
id
…
(
P
h
a
m
Ho
a
n
g
V
u
o
n
g
)
1305
f
o
r
e
c
a
st
i
n
g
u
si
n
g
A
R
I
M
A
m
o
d
e
l
,
”
i
n
C
o
g
n
i
t
i
v
e
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
2
0
2
3
,
p
p
.
8
3
–
8
9
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
981
-
19
-
2
3
5
8
-
6
_
8
.
[
5
]
S
u
r
i
p
t
o
,
“
D
e
c
i
s
i
o
n
-
m
a
k
i
n
g
m
o
d
e
l
t
o
p
r
e
d
i
c
t
a
u
t
o
-
r
e
j
e
c
t
i
o
n
:
A
n
i
m
p
l
e
me
n
t
a
t
i
o
n
o
f
A
R
I
M
A
f
o
r
a
c
c
u
r
a
t
e
f
o
r
e
c
a
st
i
n
g
o
f
s
t
o
c
k
p
r
i
c
e
v
o
l
a
t
i
l
i
t
y
d
u
r
i
n
g
t
h
e
C
o
v
i
d
-
1
9
,
”
D
e
c
i
s
i
o
n
S
c
i
e
n
c
e
L
e
t
t
e
rs
,
v
o
l
.
1
2
,
n
o
.
1
,
p
p
.
1
0
7
–
1
1
6
,
2
0
2
3
,
d
o
i
:
1
0
.
5
2
6
7
/
j
.
d
sl
.
2
0
2
2
.
1
0
.
0
0
2
.
[
6
]
M
.
V
i
j
h
,
D
.
C
h
a
n
d
o
l
a
,
V
.
A
.
Ti
k
k
i
w
a
l
,
a
n
d
A
.
K
u
m
a
r
,
“
S
t
o
c
k
c
l
o
si
n
g
p
r
i
c
e
p
r
e
d
i
c
t
i
o
n
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
”
Pro
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
6
7
,
p
p
.
5
9
9
–
6
0
6
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
2
0
.
0
3
.
3
2
6
.
[
7
]
J.
Zh
a
n
g
,
L
.
Li
,
a
n
d
W
.
C
h
e
n
,
“
P
r
e
d
i
c
t
i
n
g
st
o
c
k
p
r
i
c
e
u
s
i
n
g
t
w
o
-
st
a
g
e
mac
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
,
”
C
o
m
p
u
t
a
t
i
o
n
a
l
Ec
o
n
o
m
i
c
s
,
v
o
l
.
5
7
,
n
o
.
4
,
p
p
.
1
2
3
7
–
1
2
6
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
0
6
1
4
-
0
2
0
-
1
0
0
1
3
-
5.
[
8
]
M
.
J
.
B
a
z
r
k
a
r
a
n
d
S
.
H
o
ss
e
i
n
i
,
“
P
r
e
d
i
c
t
st
o
c
k
p
r
i
c
e
s
u
si
n
g
s
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
a
n
d
p
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
mi
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m,
”
C
o
m
p
u
t
a
t
i
o
n
a
l
E
c
o
n
o
m
i
c
s
,
v
o
l
.
6
2
,
n
o
.
1
,
p
p
.
1
6
5
–
1
8
6
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
0
6
1
4
-
0
2
2
-
1
0
2
7
3
-
3.
[
9
]
P
.
H
.
V
u
o
n
g
,
T
.
T.
D
a
t
,
T.
K
.
M
a
i
,
P
.
H
.
U
y
e
n
,
a
n
d
P
.
T
.
B
a
o
,
“
S
t
o
c
k
-
p
r
i
c
e
f
o
r
e
c
a
st
i
n
g
b
a
se
d
o
n
X
G
B
o
o
st
a
n
d
L
S
TM
,
”
C
o
m
p
u
t
e
r
S
y
s
t
e
m
s
S
c
i
e
n
c
e
a
n
d
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
4
0
,
n
o
.
1
,
p
p
.
2
3
7
–
2
4
6
,
2
0
2
2
,
d
o
i
:
1
0
.
3
2
6
0
4
/
C
S
S
E.
2
0
2
2
.
0
1
7
6
8
5
.
[
1
0
]
H
.
R
e
z
a
e
i
,
H
.
F
a
a
l
j
o
u
,
a
n
d
G
.
M
a
n
s
o
u
r
f
a
r
,
“
S
t
o
c
k
p
r
i
c
e
p
r
e
d
i
c
t
i
o
n
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
a
n
d
f
r
e
q
u
e
n
c
y
d
e
c
o
m
p
o
s
i
t
i
o
n
,
”
E
x
p
e
rt
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
.
1
6
9
,
p
.
1
1
4
3
3
2
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
0
.
1
1
4
3
3
2
.
[
1
1
]
H
.
C
h
u
n
g
a
n
d
K
.
sh
i
k
S
h
i
n
,
“
G
e
n
e
t
i
c
a
l
g
o
r
i
t
h
m
-
o
p
t
i
mi
z
e
d
mu
l
t
i
-
c
h
a
n
n
e
l
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
st
o
c
k
mark
e
t
p
r
e
d
i
c
t
i
o
n
,
”
N
e
u
r
a
l
C
o
m
p
u
t
i
n
g
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
2
,
n
o
.
1
2
,
p
p
.
7
8
9
7
–
7
9
1
4
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
2
1
-
0
1
9
-
0
4
2
3
6
-
3.
[
1
2
]
S
.
H
a
n
su
n
a
n
d
J.
C
.
Y
o
u
n
g
,
“
P
r
e
d
i
c
t
i
n
g
LQ
4
5
f
i
n
a
n
c
i
a
l
sec
t
o
r
i
n
d
i
c
e
s
u
s
i
n
g
R
N
N
-
LST
M
,
”
J
o
u
r
n
a
l
o
f
B
i
g
D
a
t
a
,
v
o
l
.
8
,
n
o
.
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
8
6
/
s4
0
5
3
7
-
0
2
1
-
0
0
4
9
5
-
x.
[
1
3
]
S
.
S
i
a
mi
-
N
a
m
i
n
i
,
N
.
Ta
v
a
k
o
l
i
,
a
n
d
A
.
S
.
N
a
mi
n
,
“
Th
e
p
e
r
f
o
r
ma
n
c
e
o
f
LST
M
a
n
d
B
i
LST
M
i
n
f
o
r
e
c
a
st
i
n
g
t
i
me
seri
e
s,
”
i
n
Pro
c
e
e
d
i
n
g
s
-
2
0
1
9
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Bi
g
D
a
t
a
,
Bi
g
D
a
t
a
2
0
1
9
,
D
e
c
.
2
0
1
9
,
p
p
.
3
2
8
5
–
3
2
9
2
,
d
o
i
:
1
0
.
1
1
0
9
/
B
i
g
D
a
t
a
4
7
0
9
0
.
2
0
1
9
.
9
0
0
5
9
9
7
.
[
1
4
]
X
.
Zh
a
o
,
Y
.
Li
u
,
a
n
d
Q
.
Z
h
a
o
,
“
G
e
n
e
r
a
l
i
z
e
d
l
o
ss
-
b
a
se
d
C
N
N
-
B
i
LST
M
f
o
r
st
o
c
k
mar
k
e
t
p
r
e
d
i
c
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
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
.
6
1
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
i
j
f
s
1
2
0
3
0
0
6
1
.
[
1
5
]
K
.
S
r
i
j
i
r
a
n
o
n
,
Y
.
L
e
r
t
r
a
t
a
n
a
k
h
a
m,
a
n
d
T.
T
a
n
a
n
t
o
n
g
,
“
A
h
y
b
r
i
d
f
r
a
mew
o
r
k
u
si
n
g
P
C
A
,
EM
D
a
n
d
LST
M
m
e
t
h
o
d
s
f
o
r
s
t
o
c
k
mark
e
t
p
r
i
c
e
p
r
e
d
i
c
t
i
o
n
w
i
t
h
se
n
t
i
men
t
a
n
a
l
y
si
s,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
(
S
w
i
t
z
e
rl
a
n
d
)
,
v
o
l
.
1
2
,
n
o
.
2
1
,
p
.
1
0
8
2
3
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
2
2
1
1
0
8
2
3
.
[
1
6
]
Z.
F
a
t
h
a
l
i
,
Z.
K
o
d
i
a
,
a
n
d
L.
B
e
n
S
a
i
d
,
“
S
t
o
c
k
mar
k
e
t
p
r
e
d
i
c
t
i
o
n
o
f
N
I
F
TY
5
0
i
n
d
e
x
a
p
p
l
y
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,”
Ap
p
l
i
e
d
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
3
6
,
n
o
.
1
,
p
.
2
1
1
1
1
3
4
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
8
0
/
0
8
8
3
9
5
1
4
.
2
0
2
2
.
2
1
1
1
1
3
4
.
[
1
7
]
D
.
S
a
t
r
i
a
,
“
P
r
e
d
i
c
t
i
n
g
b
a
n
k
i
n
g
s
t
o
c
k
p
r
i
c
e
s
u
si
n
g
R
N
N
,
LST
M
,
a
n
d
G
R
U
a
p
p
r
o
a
c
h
,
”
A
p
p
l
i
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
9
,
n
o
.
1
,
p
p
.
8
2
–
9
4
,
2
0
2
3
,
d
o
i
:
1
0
.
3
5
7
8
4
/
a
c
s
-
2
0
2
3
-
0
6
.
[
1
8
]
S
.
M
o
o
t
h
a
,
S
.
S
r
i
d
h
a
r
,
R
.
S
e
e
t
h
a
r
a
ma
n
,
a
n
d
S
.
C
h
i
t
r
a
k
a
l
a
,
“
S
t
o
c
k
p
r
i
c
e
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
B
i
-
d
i
r
e
c
t
i
o
n
a
l
LST
M
b
a
sed
se
q
u
e
n
c
e
t
o
seq
u
e
n
c
e
m
o
d
e
l
i
n
g
a
n
d
mu
l
t
i
t
a
sk
l
e
a
r
n
i
n
g
,
”
i
n
2
0
2
0
1
1
t
h
I
EEE
A
n
n
u
a
l
U
b
i
q
u
i
t
o
u
s
C
o
m
p
u
t
i
n
g
,
El
e
c
t
ro
n
i
c
s
a
n
d
M
o
b
i
l
e
C
o
m
m
u
n
i
c
a
t
i
o
n
C
o
n
f
e
r
e
n
c
e
,
U
EM
C
O
N
2
0
2
0
,
2
0
2
0
,
p
p
.
0
0
7
8
–
0
0
8
6
,
d
o
i
:
1
0
.
1
1
0
9
/
U
EM
C
O
N
5
1
2
8
5
.
2
0
2
0
.
9
2
9
8
0
6
6
.
[
1
9
]
A
.
K
a
n
w
a
l
,
M
.
F
.
L
a
u
,
S
.
P
.
H
.
N
g
,
K
.
Y
.
S
i
m,
a
n
d
S
.
C
h
a
n
d
r
a
se
k
a
r
a
n
,
“
B
i
C
u
D
N
N
LST
M
-
1
d
C
N
N
—
A
h
y
b
r
i
d
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
p
r
e
d
i
c
t
i
v
e
m
o
d
e
l
f
o
r
st
o
c
k
p
r
i
c
e
p
r
e
d
i
c
t
i
o
n
,
”
E
x
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
.
2
0
2
,
p
.
1
1
7
1
2
3
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
2
.
1
1
7
1
2
3
.
[
2
0
]
J.
S
h
a
h
,
D
.
V
a
i
d
y
a
,
a
n
d
M
.
S
h
a
h
,
“
A
c
o
mp
r
e
h
e
n
s
i
v
e
r
e
v
i
e
w
o
n
mu
l
t
i
p
l
e
h
y
b
r
i
d
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
f
o
r
st
o
c
k
p
r
e
d
i
c
t
i
o
n
,
”
I
n
t
e
l
l
i
g
e
n
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
.
1
6
,
p
.
2
0
0
1
1
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
sw
a
.
2
0
2
2
.
2
0
0
1
1
1
.
[
2
1
]
Q
.
C
h
e
n
,
W
.
Z
h
a
n
g
,
a
n
d
Y
.
Lo
u
,
“
F
o
r
e
c
a
s
t
i
n
g
st
o
c
k
p
r
i
c
e
s
u
si
n
g
a
h
y
b
r
i
d
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
i
n
t
e
g
r
a
t
i
n
g
a
t
t
e
n
t
i
o
n
me
c
h
a
n
i
sm
,
mu
l
t
i
-
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
,
a
n
d
b
i
d
i
r
e
c
t
i
o
n
a
l
l
o
n
g
-
sh
o
r
t
t
e
r
m
mem
o
r
y
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
8
,
p
p
.
1
1
7
3
6
5
–
1
1
7
3
7
6
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
3
0
0
4
2
8
4
.
[
2
2
]
T.
H
.
H
.
A
l
d
h
y
a
n
i
a
n
d
A
.
A
l
z
a
h
r
a
n
i
,
“
F
r
a
m
e
w
o
r
k
f
o
r
p
r
e
d
i
c
t
i
n
g
a
n
d
m
o
d
e
l
i
n
g
st
o
c
k
mar
k
e
t
p
r
i
c
e
s
b
a
se
d
o
n
d
e
e
p
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms,
”
E
l
e
c
t
r
o
n
i
c
s
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
1
,
n
o
.
1
9
,
p
.
3
1
4
9
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
1
1
9
3
1
4
9
.
[
2
3
]
Y
.
C
h
e
n
e
t
a
l
.
,
“
S
t
o
c
k
p
r
i
c
e
f
o
r
e
c
a
s
t
b
a
se
d
o
n
C
N
N
-
B
i
LST
M
-
E
C
A
mo
d
e
l
,
”
S
c
i
e
n
t
i
f
i
c
Pr
o
g
ra
m
m
i
n
g
,
v
o
l
.
2
0
2
1
,
p
.
2
4
4
6
5
4
3
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
1
/
2
4
4
6
5
4
3
.
[
2
4
]
S
.
W
a
n
g
,
“
A
st
o
c
k
p
r
i
c
e
p
r
e
d
i
c
t
i
o
n
me
t
h
o
d
b
a
s
e
d
o
n
B
i
LS
TM
a
n
d
i
mp
r
o
v
e
d
Tr
a
n
sf
o
r
m
e
r
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
1
0
4
2
1
1
–
1
0
4
2
2
3
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
9
6
3
0
8
.
[
2
5
]
H
.
V
P
h
a
m,
H
.
P
.
La
m
,
L
.
N
.
D
u
y
,
T
.
B
.
P
h
a
m,
a
n
d
T
.
D
.
Tr
i
n
h
,
“
A
n
i
m
p
r
o
v
e
d
c
o
n
v
o
l
u
t
i
o
n
a
l
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
st
o
c
k
p
r
i
c
e
f
o
r
e
c
a
st
i
n
g
,
”
I
AE
S
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
3
,
n
o
.
3
,
p
p
.
3
3
8
1
–
3
3
9
4
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
a
i
.
v
1
3
.
i
3
.
p
p
3
3
8
1
-
3
3
9
4
.
[
2
6
]
T.
T.
D
a
t
e
t
a
l
.
,
“
A
n
i
m
p
r
o
v
e
d
C
R
N
N
f
o
r
V
i
e
t
n
a
mes
e
i
d
e
n
t
i
t
y
c
a
r
d
i
n
f
o
r
mat
i
o
n
r
e
c
o
g
n
i
t
i
o
n
,
”
C
o
m
p
u
t
e
r
S
y
s
t
e
m
s
S
c
i
e
n
c
e
a
n
d
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
4
0
,
n
o
.
2
,
p
p
.
5
3
9
–
5
5
5
,
2
0
2
1
,
d
o
i
:
1
0
.
3
2
6
0
4
/
C
S
S
E.
2
0
2
2
.
0
1
9
0
6
4
.
[
2
7
]
T.
Li
n
,
Y
.
W
a
n
g
,
X
.
Li
u
,
a
n
d
X
.
Q
i
u
,
“
A
s
u
r
v
e
y
o
f
Tr
a
n
sf
o
r
m
e
r
s,”
AI
O
p
e
n
,
v
o
l
.
3
,
p
p
.
1
1
1
–
1
3
2
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
i
o
p
e
n
.
2
0
2
2
.
1
0
.
0
0
1
.
[
2
8
]
N
.
P
a
t
w
a
r
d
h
a
n
,
S
.
M
a
r
r
o
n
e
,
a
n
d
C
.
S
a
n
s
o
n
e
,
“
Tr
a
n
sf
o
r
m
e
r
s
i
n
t
h
e
r
e
a
l
w
o
r
l
d
:
A
s
u
r
v
e
y
o
n
N
LP
a
p
p
l
i
c
a
t
i
o
n
s
,
”
I
n
f
o
rm
a
t
i
o
n
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
4
,
n
o
.
4
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
i
n
f
o
1
4
0
4
0
2
4
2
.
[
2
9
]
W
.
Lu
,
J.
Li
,
J.
W
a
n
g
,
a
n
d
L.
Q
i
n
,
“
A
C
N
N
-
B
i
LST
M
-
A
M
m
e
t
h
o
d
f
o
r
st
o
c
k
p
r
i
c
e
p
r
e
d
i
c
t
i
o
n
,
”
N
e
u
r
a
l
C
o
m
p
u
t
i
n
g
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
3
,
n
o
.
1
0
,
p
p
.
4
7
4
1
–
4
7
5
3
,
M
a
y
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
2
1
-
0
2
0
-
0
5
5
3
2
-
z.
[
3
0
]
J.
Z
h
a
n
g
,
L
.
Y
e
,
a
n
d
Y
.
La
i
,
“
S
t
o
c
k
p
r
i
c
e
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
C
N
N
-
B
i
LSTM
-
a
t
t
e
n
t
i
o
n
m
o
d
e
l
,
”
M
a
t
h
e
m
a
t
i
c
s
,
v
o
l
.
1
1
,
n
o
.
9
,
p
.
1
9
8
5
,
2
0
2
3
.
[
3
1
]
A
.
V
a
sw
a
n
i
e
t
a
l
.
,
“
A
t
t
e
n
t
i
o
n
i
s
a
l
l
y
o
u
n
e
e
d
,
”
A
d
v
a
n
c
e
s
i
n
N
e
u
r
a
l
I
n
f
o
rm
a
t
i
o
n
Pro
c
e
ss
i
n
g
S
y
st
e
m
s
,
v
o
l
.
2
0
1
7
-
D
e
c
e
mb
e
r
,
p
p
.
5
9
9
9
–
6
0
0
9
,
2
0
1
7
,
d
o
i
:
1
0
.
1
2
0
1
/
9
7
8
1
0
0
3
5
6
1
4
6
0
-
1
9
.
[
3
2
]
D
.
K
o
b
i
e
l
a
,
D
.
K
r
e
f
t
a
,
W
.
K
r
ó
l
,
a
n
d
P
.
W
e
i
c
h
b
r
o
t
h
,
“
A
R
I
M
A
v
s
LST
M
o
n
N
A
S
D
A
Q
s
t
o
c
k
e
x
c
h
a
n
g
e
d
a
t
a
,
”
P
ro
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
0
7
,
p
p
.
3
8
3
6
–
3
8
4
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
2
2
.
0
9
.
4
4
5
.
[
3
3
]
C
.
W
a
n
g
,
Y
.
C
h
e
n
,
S
.
Z
h
a
n
g
,
a
n
d
Q
.
Zh
a
n
g
,
“
S
t
o
c
k
mar
k
e
t
i
n
d
e
x
p
r
e
d
i
c
t
i
o
n
u
si
n
g
d
e
e
p
Tr
a
n
sf
o
r
mer
mo
d
e
l
,
”
E
x
p
e
r
t
S
y
s
t
e
m
s
w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
0
8
,
p
.
1
1
8
1
2
8
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
2
.
1
1
8
1
2
8
.
[
3
4
]
C
.
L
i
a
n
d
G
.
Q
i
a
n
,
“
S
t
o
c
k
p
r
i
c
e
p
r
e
d
i
c
t
i
o
n
u
si
n
g
a
f
r
e
q
u
e
n
c
y
d
e
c
o
mp
o
s
i
t
i
o
n
b
a
s
e
d
G
R
U
Tr
a
n
sf
o
r
m
e
r
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
3
,
n
o
.
1
,
p
.
2
2
2
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
3
0
1
0
2
2
2
.
[
3
5
]
F
.
H
.
M
u
st
a
p
a
a
n
d
M
.
T
.
I
smai
l
,
“
M
o
d
e
l
l
i
n
g
a
n
d
f
o
r
e
c
a
s
t
i
n
g
S
&P
5
0
0
st
o
c
k
p
r
i
c
e
s
u
s
i
n
g
h
y
b
r
i
d
A
r
i
m
a
-
G
a
r
c
h
m
o
d
e
l
,
”
J
o
u
r
n
a
l
o
f
Ph
y
s
i
c
s:
C
o
n
f
e
r
e
n
c
e
S
e
ri
e
s
,
v
o
l
.
1
3
6
6
,
n
o
.
1
,
p
.
1
2
1
3
0
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/
1
3
6
6
/
1
/
0
1
2
1
3
0
.
[
3
6
]
T.
S
i
n
g
h
,
R
.
K
a
l
r
a
,
S
.
M
i
sh
r
a
,
S
a
t
a
k
s
h
i
,
a
n
d
M
.
K
u
mar,
“
A
n
e
f
f
i
c
i
e
n
t
r
e
a
l
-
t
i
me
st
o
c
k
p
r
e
d
i
c
t
i
o
n
e
x
p
l
o
i
t
i
n
g
i
n
c
r
e
me
n
t
a
l
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
,
”
E
v
o
l
v
i
n
g
S
y
st
e
m
s
,
v
o
l
.
1
4
,
n
o
.
6
,
p
p
.
9
1
9
–
9
3
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
2
5
3
0
-
022
-
0
9
4
8
1
-
x.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
3
,
J
u
n
e
20
2
6
:
1
2
9
8
-
1
3
0
6
1306
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
P
h
a
m
H
o
a
n
g
V
u
o
n
g
r
e
c
e
i
v
e
d
h
i
s
B
.
S
c
.
d
e
g
r
e
e
i
n
m
a
t
h
e
m
a
ti
c
s
a
n
d
c
o
m
p
u
t
e
r
s
c
i
e
n
c
e
f
r
o
m
t
h
e
U
n
i
v
e
r
s
i
t
y
o
f
E
d
u
c
a
t
i
o
n
–
V
i
e
t
n
a
m
N
a
t
i
o
n
a
l
U
n
i
v
e
r
s
i
t
y
,
H
o
C
h
i
M
i
n
h
C
i
t
y
,
i
n
1
9
9
2
.
H
e
e
a
r
n
e
d
h
i
s
E
n
g
i
n
e
e
r
i
n
g
d
e
g
r
e
e
f
r
o
m
H
a
n
o
i
U
n
i
v
e
r
s
i
t
y
o
f
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
i
n
2
0
0
0
a
n
d
h
i
s
M
.
S
c
.
d
e
g
r
e
e
f
r
o
m
H
o
C
h
i
M
i
n
h
C
i
t
y
U
n
i
v
e
r
s
i
t
y
o
f
S
c
i
e
n
c
e
i
n
2
0
0
1
.
H
e
h
a
s
b
e
e
n
a
L
e
c
t
u
r
e
r
i
n
t
h
e
D
e
p
a
r
t
m
e
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
t
S
a
i
g
o
n
U
n
i
v
e
r
si
t
y
,
V
i
e
t
n
a
m
,
s
i
n
c
e
2
0
0
8
.
H
i
s
r
e
s
e
a
r
c
h
i
n
te
r
e
s
ts
i
n
c
l
u
d
e
s
t
o
c
k
p
r
ic
e
f
o
re
c
a
s
t
i
n
g
a
n
d
c
o
m
p
u
t
e
r
v
i
s
i
o
n
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
.
H
e
c
a
n
b
e
c
o
n
t
a
c
t
e
d
a
t
e
m
a
il:
p
h
v
u
o
n
g
@
s
g
u
.
e
d
u
.
v
n
.
L
a
m
H
u
n
g
P
h
u
r
e
c
e
i
v
e
d
h
i
s
b
a
c
h
e
l
o
r
’
s
d
e
g
r
e
e
i
n
i
n
f
o
r
m
a
t
i
o
n
t
e
c
h
n
o
l
o
g
y
f
r
o
m
S
a
i
g
o
n
U
n
i
v
e
r
s
i
t
y
,
H
o
C
h
i
M
i
n
h
C
i
t
y
,
V
i
e
t
n
a
m
,
i
n
2
0
2
3
.
H
e
i
s
a
r
e
c
e
n
t
g
r
a
d
u
a
t
e
,
a
n
d
h
i
s
r
e
s
e
a
rc
h
i
n
t
e
r
e
s
t
s
i
n
c
l
u
d
e
p
r
e
d
ic
t
i
v
e
m
o
d
e
l
i
n
g
,
c
o
m
p
u
t
e
r
v
i
s
i
o
n
,
a
n
d
d
a
t
a
a
n
a
ly
s
i
s
.
H
e
c
a
n
b
e
c
o
n
t
a
c
te
d
a
t
e
m
a
i
l
:
p
t
h
.
a
3
.
3
0
.
h
u
n
g
p
h
u
@
g
m
a
i
l
.
c
o
m
.
L
e
N
h
a
t
D
u
y
r
e
c
e
i
v
e
d
h
i
s
P
h
.
D
.
d
e
g
r
e
e
i
n
c
o
m
p
u
t
e
r
s
c
i
e
n
c
e
f
ro
m
M
o
s
c
o
w
S
t
a
te
P
e
d
a
g
o
g
i
c
a
l
U
n
i
v
e
r
s
i
t
y
,
R
u
s
s
i
a
,
i
n
2
0
1
3
.
S
i
n
c
e
2
0
1
3
,
h
e
h
a
s
b
e
e
n
a
L
e
c
t
u
r
e
r
i
n
t
h
e
D
e
p
a
r
t
m
e
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
t
t
h
e
I
n
d
u
s
t
r
i
a
l
U
n
i
v
e
r
s
i
t
y
o
f
H
o
C
h
i
M
i
n
h
C
i
t
y
,
V
i
e
t
n
a
m
.
H
i
s
re
se
a
rc
h
i
n
t
e
r
e
s
t
s
i
n
c
l
u
d
e
c
o
m
p
u
t
a
t
i
o
n
a
l
in
t
e
l
l
i
g
e
n
c
e
a
n
d
c
r
y
p
t
o
g
r
a
p
h
y
.
H
e
c
a
n
b
e
c
o
n
t
a
c
te
d
a
t
e
m
a
i
l
:
l
e
n
h
a
t
d
u
y
@
i
u
h
.
e
d
u
.
v
n
.
P
h
a
m
T
h
e
B
a
o
r
e
c
e
i
v
e
d
h
i
s
B
.
S
c
.
d
e
g
r
e
e
i
n
A
l
g
e
b
r
a
f
r
o
m
t
h
e
U
n
i
v
e
r
s
i
t
y
o
f
N
a
t
u
r
a
l
S
c
i
e
n
c
e
–
V
ie
t
n
a
m
N
a
t
i
o
n
a
l
U
n
i
v
e
r
s
i
t
y
,
H
o
C
h
i
M
i
n
h
C
i
t
y
,
i
n
1
9
9
5
.
H
e
e
a
r
n
e
d
h
i
s
M
.
S
c
.
d
e
g
r
e
e
i
n
t
h
e
m
a
t
h
e
m
a
t
ic
a
l
f
o
u
n
d
a
t
i
o
n
s
o
f
c
o
m
p
u
t
e
r
sc
i
e
n
c
e
i
n
2
0
0
0
a
n
d
h
i
s
P
h
.
D
.
d
e
g
r
e
e
i
n
c
o
m
p
u
t
e
r
s
c
i
e
n
c
e
i
n
2
0
0
9
,
b
o
t
h
f
r
o
m
t
h
e
s
a
m
e
u
n
i
v
e
r
s
i
t
y
.
F
r
o
m
1
9
9
5
t
o
2
0
1
8
,
h
e
s
e
r
v
e
d
a
s
a
L
e
c
t
u
re
r
a
n
d
P
r
o
f
e
s
s
o
r
i
n
t
h
e
D
e
p
a
r
t
m
e
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
F
a
c
u
l
t
y
o
f
M
a
t
h
e
m
a
t
ic
s
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
a
t
t
h
e
U
n
i
v
e
rs
i
t
y
o
f
N
a
t
u
r
a
l
S
c
i
e
n
c
e
.
S
i
n
c
e
2
0
1
9
,
h
e
h
a
s
b
e
e
n
t
h
e
D
e
a
n
a
n
d
a
P
r
o
f
e
ss
o
r
i
n
t
h
e
D
e
p
a
r
tm
e
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
t
S
a
i
g
o
n
U
n
i
v
e
r
s
i
t
y
,
V
i
e
t
n
a
m
.
H
e
h
a
s
p
u
b
l
i
s
h
e
d
o
v
e
r
5
0
p
a
p
e
r
s
i
n
i
n
t
e
r
n
a
t
i
o
n
a
l
j
o
u
r
n
a
l
s
a
n
d
c
o
n
f
e
r
e
n
c
e
s
.
H
is
r
e
s
e
a
r
c
h
i
n
t
e
r
e
s
t
s
i
n
c
l
u
d
e
i
m
a
g
e
p
r
o
c
e
s
s
i
n
g
,
p
a
t
t
e
r
n
r
e
c
o
g
n
i
t
i
o
n
,
a
n
d
i
n
t
e
l
l
i
g
e
n
t
c
o
m
p
u
t
i
n
g
.
H
e
c
a
n
b
e
c
o
n
t
a
c
t
e
d
a
t
e
m
a
i
l
:
p
t
b
a
o
@
s
g
u
.
e
d
u
.
v
n
.
T
a
n
D
a
t
T
r
i
n
h
r
e
c
e
i
v
e
d
h
i
s
B
.
S
c
.
d
e
g
r
e
e
i
n
m
a
t
h
e
m
a
t
i
c
s
a
n
d
c
o
m
p
u
t
e
r
s
c
i
e
n
c
e
f
r
o
m
t
h
e
U
n
i
v
e
rs
i
t
y
o
f
N
a
t
u
r
a
l
S
c
i
e
n
c
e
–
V
i
e
t
n
a
m
Na
t
i
o
n
a
l
U
n
i
v
e
r
s
i
t
y
,
H
o
C
h
i
M
i
n
h
C
i
t
y
,
i
n
2
0
1
0
.
H
e
e
a
r
n
e
d
h
i
s
M
a
s
te
r
o
f
E
n
g
i
n
e
e
r
i
n
g
(
M
.
E
n
g
.
)
a
n
d
P
h
.
D
.
d
e
g
r
e
e
s
i
n
e
l
e
c
t
r
o
n
i
c
s
a
n
d
c
o
m
p
u
t
e
r
e
n
g
i
n
e
e
r
i
n
g
f
r
o
m
C
h
o
n
n
a
m
N
a
t
i
o
n
a
l
U
n
i
v
e
r
s
i
t
y
,
K
o
r
e
a
,
i
n
2
0
1
3
a
n
d
2
0
1
7
,
r
e
s
p
e
c
t
i
v
e
l
y
.
S
i
n
c
e
2
0
1
9
,
h
e
h
a
s
b
e
e
n
a
l
e
c
t
u
r
e
r
i
n
t
h
e
D
e
p
a
r
t
m
e
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
t
S
a
i
g
o
n
U
n
i
v
e
r
s
i
t
y
,
V
i
e
t
n
a
m
.
H
is
r
e
s
e
a
r
c
h
i
n
t
e
r
e
s
t
s
i
n
c
l
u
d
e
s
p
e
a
k
e
r
r
e
c
o
g
n
i
t
i
o
n
,
s
p
e
e
c
h
s
i
g
n
a
l
p
r
o
c
e
s
s
i
n
g
,
c
o
m
p
u
t
e
r
v
i
s
i
o
n
,
a
n
d
p
a
t
t
e
r
n
r
e
c
o
g
n
i
t
i
o
n
.
H
e
c
a
n
b
e
c
o
n
t
a
c
t
e
d
a
t
e
m
a
i
l
:
t
r
i
n
h
t
a
n
d
a
t
@
s
g
u
.
e
d
u
.
v
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.