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.
15
,
No
.
2
,
A
p
r
il
20
25
,
p
p
.
1
7
8
3
~
1
7
9
2
I
SS
N:
2
0
8
8
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
2
.
p
p
1
7
8
3
-
1
7
9
2
1783
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Predic
ting
sto
ck
prices using
e
nse
mble lea
rning
tec
hniques
Sa
lm
a
E
ls
a
y
ed
1
,
Ahm
a
d Sa
la
h
1
,2
,
I
bra
him
E
lhena
wy
1
,
M
a
rwa
Abdella
h
1
1
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
,
F
a
c
u
l
t
y
o
f
C
o
m
p
u
t
e
r
s
a
n
d
I
n
f
o
r
mat
i
c
s
,
Za
g
a
z
i
g
U
n
i
v
e
r
si
t
y
,
Z
a
g
a
z
i
g
,
E
g
y
p
t
2
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
Te
c
h
n
o
l
o
g
y
,
C
o
l
l
e
g
e
o
f
C
o
m
p
u
t
i
n
g
a
n
d
I
n
f
o
r
m
a
t
i
o
n
S
c
i
e
n
c
e
s,
U
n
i
v
e
r
s
i
t
y
o
f
T
e
c
h
n
o
l
o
g
y
a
n
d
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s,
I
b
r
i
,
S
u
l
t
a
n
a
t
e
o
f
O
ma
n
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
2
8
,
2
0
2
3
R
ev
is
ed
Au
g
1
3
,
2
0
2
4
Acc
ep
ted
Oct
2
3
,
2
0
2
4
S
to
c
k
p
rice
p
re
d
ictio
n
h
a
s g
r
o
wn
in
imp
o
r
tan
c
e
d
u
e
to
it
s r
o
le i
n
d
e
term
in
in
g
th
e
fu
t
u
re
wo
rth
o
f
b
u
sin
e
ss
sh
a
re
s.
Th
e
re
a
re
se
v
e
ra
l
a
p
p
ro
a
c
h
e
s
fo
r
sto
c
k
p
rice
p
re
d
ictio
n
th
a
t
c
a
n
b
e
c
las
s
ifi
e
d
in
t
o
m
a
c
h
in
e
lea
rn
in
g
,
d
e
e
p
lea
rn
in
g
,
a
n
d
e
n
se
m
b
le
lea
rn
in
g
m
e
th
o
d
s.
To
p
re
d
ict
sto
c
k
p
r
ice
s,
we
p
ro
p
o
se
d
c
o
ll
e
c
ti
n
g
a
d
a
tas
e
t
f
o
r
d
iffere
n
t
we
ll
-
k
n
o
wn
sto
c
k
s,
e
.
g
.
,
M
icro
so
ft.
T
h
e
u
ti
li
z
e
d
d
a
tas
e
ts co
n
sist o
f
two
p
a
rts;
th
e
first
p
a
rt
c
o
n
tain
s a
se
t
o
f
twe
e
ts f
o
r
th
e
sto
c
k
s
u
n
d
e
r
in
v
e
stig
a
ti
o
n
i
n
th
is
st
u
d
y
wh
ic
h
we
re
c
o
ll
e
c
ted
f
ro
m
th
e
X
so
c
ial
m
e
d
ia
p
latfo
rm
a
n
d
th
e
o
th
e
r
p
a
rt
c
o
n
tai
n
s
th
e
sto
c
k
p
rice
s.
S
e
n
ti
m
e
n
tal
fe
a
tu
re
s
o
f
t
h
e
twe
e
ts
we
re
e
x
trac
ted
a
n
d
m
e
rg
e
d
wit
h
th
e
sto
c
k
p
rice
c
h
a
n
g
e
s.
T
h
e
n
,
we
fra
m
e
d
t
h
e
p
r
o
b
lem
a
s
a
re
g
re
ss
io
n
tas
k
.
we
a
im
to
a
n
a
ly
z
e
th
e
p
e
rf
o
rm
a
n
c
e
g
a
p
b
e
t
we
e
n
e
n
se
m
b
le
lea
rn
in
g
a
n
d
o
t
h
e
r
m
a
c
h
in
e
lea
rn
in
g
(M
L)
a
n
d
d
e
e
p
lea
rn
i
n
g
(DL)
m
o
d
e
ls
fo
r
p
re
d
icti
n
g
st
o
c
k
p
r
ice
s
b
a
se
d
o
n
twe
e
ts.
In
t
h
is
c
o
n
te
x
t,
d
iffere
n
t
e
n
se
m
b
le
lea
rn
in
g
m
o
d
e
ls
we
re
p
ro
p
o
se
d
to
p
re
d
ict
th
e
p
rice
c
h
a
n
g
e
o
f
e
a
c
h
st
o
c
k
.
Be
sid
e
s,
se
v
e
r
a
l
m
a
c
h
in
e
lea
rn
in
g
a
n
d
d
e
e
p
lea
rn
i
n
g
m
o
d
e
ls
we
re
u
se
d
fo
r
c
o
m
p
a
riso
n
p
u
rp
o
se
s.
S
e
v
e
ra
l
e
v
a
lu
a
ti
o
n
m
e
tri
c
s
we
re
u
ti
li
z
e
d
to
e
v
a
lu
a
te
t
h
e
p
e
rfo
rm
a
n
c
e
o
f
th
e
p
ro
p
o
se
d
m
o
d
e
ls.
Th
e
e
x
p
e
ri
m
e
n
tal
re
su
lt
s
p
ro
v
e
d
th
a
t
t
h
e
sta
c
k
in
g
re
g
re
ss
o
r
m
o
d
e
l
o
u
t
p
e
rfo
rm
e
d
t
h
e
o
th
e
r
m
o
d
e
ls.
K
ey
w
o
r
d
s
:
Dee
p
lear
n
in
g
E
n
s
em
b
le
lear
n
in
g
Ma
ch
in
e
lear
n
in
g
Pre
d
ictio
n
r
eg
r
ess
io
n
Sto
ck
p
r
ice
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
:
Ah
m
ad
Salah
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
,
Facu
lty
o
f
C
o
m
p
u
ter
s
an
d
I
n
f
o
r
m
atics,
Z
ag
az
ig
U
n
iv
er
s
ity
Alze
r
aa
S
q
u
ar
e,
Z
ag
az
i
g
,
Sh
ar
k
ia,
4
4
5
1
9
,
E
g
y
p
t
E
m
ail: a
h
m
ad
@
zu
.
ed
u
.
e
g
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
in
ter
n
et
s
er
v
es
as
an
o
n
lin
e
lear
n
in
g
p
latf
o
r
m
f
o
r
co
m
m
u
n
icatio
n
an
d
ex
c
h
an
g
in
g
id
ea
s
.
T
h
r
o
u
g
h
co
m
m
o
n
s
o
cial
m
ed
i
a
p
latf
o
r
m
s
,
p
eo
p
le
ca
n
co
n
tr
i
b
u
te
f
ee
d
b
ac
k
an
d
s
u
g
g
esti
o
n
s
f
o
r
a
wid
e
r
an
g
e
o
f
s
er
v
ices
a
n
d
o
f
f
er
in
g
s
.
T
witter
,
Face
b
o
o
k
,
a
n
d
Go
o
g
l
e+
ar
e
well
-
k
n
o
wn
ex
a
m
p
le
s
o
f
s
o
cial
m
ed
ia
p
latf
o
r
m
s
th
at
ar
e
u
tili
ze
d
f
o
r
id
ea
p
o
s
tin
g
.
T
witter
is
an
o
n
lin
e
s
o
cial
n
etwo
r
k
wh
er
e
m
illi
o
n
s
o
f
twee
ts
ar
e
p
o
s
ted
ev
er
y
d
a
y
.
T
h
e
p
r
e
d
ictio
n
m
eth
o
d
m
a
y
b
e
ca
r
r
ied
o
u
t
u
s
in
g
T
witter
d
ata.
L
iv
e
T
witter
d
ata
m
ay
b
e
co
llected
v
ia
th
e
T
witter
API
an
d
an
al
y
ze
d
u
s
in
g
th
e
class
if
ier
.
T
h
e
s
to
c
k
m
ar
k
et
is
an
im
p
o
r
tan
t
p
ar
t
o
f
th
e
ec
o
n
o
m
y
an
d
af
f
ec
ts
co
m
m
er
c
e
ch
an
g
es a
n
d
in
d
u
s
tr
ial
g
r
o
wt
h
.
Sev
er
al
d
ata
m
in
in
g
ap
p
r
o
a
ch
es a
r
e
em
p
lo
y
ed
to
h
an
d
le
v
ar
iatio
n
s
in
th
e
s
to
ck
m
ar
k
et,
a
n
d
f
in
an
cial
n
ews a
r
ticles
ar
e
ass
u
m
ed
to
in
f
lu
en
ce
s
to
ck
p
r
ices
[
1
]
,
[
2
]
,
[
3
]
.
I
n
[
4
]
,
a
u
n
iq
u
e
s
en
tim
en
t
in
d
icato
r
b
ased
o
n
weig
h
ted
tex
t
u
al
co
n
ten
ts
an
d
f
in
a
n
cial
ab
e
r
r
atio
n
s
to
f
o
r
ec
ast
s
to
ck
c
h
an
g
es
is
p
er
f
o
r
m
ed
.
First,
th
e
a
u
th
o
r
s
s
u
g
g
ested
a
u
n
i
q
u
e
weig
h
tin
g
ap
p
r
o
ac
h
f
o
r
ea
ch
s
to
ck
m
o
v
em
en
t.
T
h
en
,
th
ey
p
r
o
d
u
c
ed
an
ac
tu
al
ad
j
u
s
ted
s
en
tim
en
t
m
ea
s
u
r
e
th
at
was
m
o
r
e
ac
c
u
r
ate
b
y
ac
c
o
u
n
tin
g
f
o
r
th
e
d
a
y
o
f
th
e
wee
k
a
n
d
v
ac
atio
n
.
Usi
n
g
s
u
p
p
o
r
t
v
ec
t
o
r
m
ac
h
in
e
(
SVM)
[
5
]
,
[
6
]
,
d
ec
is
io
n
tr
ee
(
DT
)
,
g
r
ad
ien
t
b
o
o
s
tin
g
d
ec
is
io
n
tr
ee
(
GB
DT
)
,
r
an
d
o
m
f
o
r
est
(
R
F)
[
7
]
n
aï
v
e
B
ay
es
(
NB
)
,
K
-
n
ea
r
est
n
eig
h
b
o
r
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.
15
,
No
.
2
,
Ap
r
il
20
25
:
1
7
8
3
-
1
7
9
2
1784
(
KNN)
[
8
]
,
an
d
lo
g
is
tic
r
eg
r
es
s
io
n
(
L
R
)
alg
o
r
ith
m
s
.
T
h
ey
o
b
s
er
v
ed
th
at
th
e
m
o
d
if
ie
d
s
en
t
im
en
t
m
ea
s
u
r
e
ca
n
ef
f
ec
tiv
ely
im
p
r
o
v
e
s
to
ck
m
ar
k
et
m
o
v
em
e
n
t p
r
e
d
ictio
n
.
In
s
tu
d
y
[
9
]
,
a
u
n
iq
u
e
teac
h
in
g
a
n
d
lear
n
in
g
b
ased
o
p
tim
i
za
tio
n
(
T
L
B
O)
m
o
d
el
u
s
in
g
l
o
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
[
1
0
]
,
b
ased
o
n
s
en
tim
e
n
t
an
aly
s
is
(
S
A)
f
o
r
s
to
ck
p
r
ice
p
r
ed
ictio
n
u
s
in
g
d
ata
c
o
llected
f
r
o
m
T
witter
is
co
n
d
u
cted
.
T
h
e
au
th
o
r
s
p
r
ed
icte
d
s
to
ck
p
r
ices
u
s
in
g
f
o
u
r
m
ain
s
tep
s
:
p
r
e
-
p
r
o
ce
s
s
in
g
,
class
if
icatio
n
,
lear
n
in
g
r
ate
s
ch
ed
u
le,
an
d
o
u
tp
u
t u
n
it o
p
tim
i
za
tio
n
.
Fu
r
th
er
m
o
r
e,
a
n
L
ST
M
m
o
d
el
was u
s
ed
to
ca
teg
o
r
ize
twee
ts
in
to
p
o
s
itiv
e
an
d
n
eg
ativ
e
s
en
tim
en
ts
o
n
s
to
ck
v
alu
es.
Usi
n
g
s
ev
er
al
m
eth
o
d
s
,
ex
p
e
r
im
en
tal
r
esu
lts
o
f
th
e
T
L
B
O
-
L
STM
m
o
d
el
o
u
tp
er
f
o
r
m
t
h
e
latest
tech
n
iq
u
es
with
a
m
ax
im
u
m
a
cc
u
r
ac
y
o
f
9
5
.
3
3
%,
a
r
ec
all
o
f
8
5
.
2
8
%,
a
n
d
an
F1
-
s
co
r
e
o
f
9
0
%.
Fo
r
ec
asti
n
g
th
e
tr
e
n
d
o
f
s
to
c
k
p
r
ices
is
a
cr
itical
m
is
s
io
n
th
at
ass
is
ts
in
v
esto
r
s
in
m
ak
in
g
s
o
u
n
d
f
in
an
cial
d
ec
is
io
n
s
in
th
e
s
to
c
k
m
ar
k
et.
T
h
u
s
,
th
e
g
o
al
o
f
t
h
e
cu
r
r
e
n
t
wo
r
k
is
to
co
n
s
id
e
r
ab
ly
m
in
im
ize
th
e
r
is
k
o
f
tr
en
d
p
r
e
d
ictio
n
u
s
in
g
th
e
en
s
em
b
le
lear
n
in
g
tech
n
iq
u
e.
T
h
e
ef
f
icien
cy
o
f
th
e
s
u
g
g
ested
ap
p
r
o
ac
h
f
o
r
p
r
ed
ictin
g
s
to
ck
p
r
ice
is
p
r
o
v
e
d
b
y
test
in
g
o
n
2
2
c
o
r
p
o
r
atio
n
s
s
u
ch
as
T
SLA,
Am
az
o
n
,
ME
T
A,
an
d
Mic
r
o
s
o
f
t
u
s
in
g
T
witter
d
ata.
E
ac
h
d
ataset
is
d
iv
id
ed
in
to
tr
ain
in
g
an
d
test
in
g
s
ets
f
o
r
th
e
ex
p
er
im
en
t.
I
n
th
e
p
r
o
p
o
s
e
d
wo
r
k
,
a
p
r
e
-
p
r
o
ce
s
s
in
g
o
f
th
e
T
wee
ts
d
ata
i
s
co
n
d
u
cted
to
co
n
v
er
t
u
n
s
tr
u
ctu
r
ed
d
ata
in
t
o
m
ea
n
in
g
f
u
l
tex
t.
T
h
en
,
t
h
e
p
o
lar
ity
o
f
t
h
e
twe
ets
was
ex
tr
ac
ted
u
s
in
g
two
d
if
f
er
en
t
ap
p
r
o
ac
h
es.
I
n
th
e
f
ir
s
t
ap
p
r
o
ac
h
,
th
e
VADE
R
m
o
d
el,
im
p
lem
en
ted
in
s
tu
d
y
[
1
1
]
,
was
u
s
ed
to
e
x
tr
ac
t
th
e
p
o
lar
ity
o
f
ea
c
h
tw
ee
t
an
d
o
b
tain
t
h
e
s
en
tim
en
tal
s
co
r
e
(
in
th
e
r
an
g
e
o
f
-
1
to
1
)
.
I
n
th
e
s
ec
o
n
d
ap
p
r
o
ac
h
,
we
ch
o
s
e
th
e
m
ax
im
u
m
v
alu
e
o
f
p
o
s
itiv
e,
n
eg
ativ
e,
an
d
n
e
u
tr
al
p
er
c
en
t
ag
es
as
th
e
p
o
lar
ity
s
co
r
e.
T
h
e
d
aily
clo
s
in
g
p
r
ice’
s
p
e
r
ce
n
tag
e
ch
a
n
g
e
is
co
m
p
u
ted
b
ased
o
n
th
e
p
er
ce
n
tag
e
b
etwe
en
two
co
n
s
ec
u
tiv
e
d
ay
s
’
clo
s
in
g
p
r
ices
an
d
b
ased
o
n
th
is
p
er
ce
n
tag
e
we
co
u
ld
co
m
p
u
te
th
e
p
o
lar
ity
o
f
th
e
twee
ts
.
T
h
e
n
,
we
m
atch
e
d
th
e
d
aily
clo
s
in
g
p
r
ice
c
h
an
g
es
t
o
th
e
two
ex
t
r
ac
ted
p
o
lar
ities
to
f
in
d
o
u
t
wh
ich
a
p
p
r
o
ac
h
was
m
o
r
e
ef
f
ec
tiv
e.
T
h
e
h
ig
h
est
n
u
m
b
er
o
f
m
atch
es
with
th
e
f
in
an
cial
clo
s
in
g
p
r
ic
e
ch
an
g
es wa
s
th
e
s
en
tim
en
tal
s
co
r
e
to
ex
tr
ac
t
p
o
lar
ity
,
t
h
e
f
ir
s
t a
p
p
r
o
ac
h
.
T
h
e
tr
ain
in
g
s
et
co
n
tain
s
8
0
%
o
f
th
e
d
ataset,
an
d
th
e
test
s
et
is
m
ad
e
u
p
o
f
th
e
r
em
ain
in
g
2
0
%
o
f
th
e
d
ataset.
T
h
e
en
s
em
b
le
m
o
d
el
s
ar
e
m
ain
ly
class
if
ied
in
to
s
tack
in
g
,
b
len
d
in
g
,
b
a
g
g
in
g
,
a
n
d
b
o
o
s
tin
g
.
T
h
is
s
tu
d
y
co
m
p
ar
es
f
iv
e
en
s
em
b
le
lear
n
in
g
m
o
d
els
wh
ich
ar
e
,
,
,
,
an
d
.
E
ac
h
p
r
ed
ictiv
e
m
o
d
el
is
ev
alu
ated
b
y
f
iv
e
m
etr
ics
wh
i
ch
ar
e
m
ea
n
-
ab
s
o
lu
te
-
er
r
o
r
(
MA
E
)
,
m
ea
n
ab
s
o
lu
te
p
er
ce
n
tag
e
er
r
o
r
(
MA
PE)
,
m
ea
n
s
q
u
a
r
ed
er
r
o
r
(
MSE
)
,
r
o
o
t
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
R
MSE
)
,
an
d
R
s
q
u
ar
e
d
(
R
2
)
.
Mo
r
eo
v
er
,
s
ev
er
al
m
ac
h
in
e
lear
n
in
g
m
o
d
els
s
u
c
h
as
KNN,
s
u
p
p
o
r
t
v
ec
to
r
m
a
ch
in
e
(
SVM)
,
an
d
lin
ea
r
r
eg
r
e
s
s
io
n
(
L
R
)
ar
e
u
s
ed
f
o
r
co
m
p
ar
is
o
n
p
u
r
p
o
s
es
to
f
i
n
d
o
u
t
th
e
b
est
ac
cu
r
ac
y
.
T
h
e
MA
PE
m
etr
ic
o
f
t
h
e
Stack
in
g
R
eg
r
ess
o
r
m
o
d
el
was
th
e
lo
west
o
f
th
e
test
ed
m
o
d
els,
in
d
icatin
g
th
at
th
e
St
ac
k
in
g
R
eg
r
ess
o
r
m
o
d
el
o
u
tp
er
f
o
r
m
e
d
th
e
o
th
er
m
o
d
els.
T
h
e
en
s
em
b
le
m
o
d
el
s
ef
f
ec
tiv
ely
f
o
r
ec
ast
s
to
ck
cl
o
s
in
g
p
r
ices,
as
th
e
y
ac
h
ie
v
ed
lo
w
v
alu
es
in
m
o
s
t
m
etr
ics.
T
h
e
m
ain
co
n
tr
ib
u
tio
n
s
o
f
th
is
wo
r
k
a
r
e
as f
o
llo
ws:
−
E
x
tr
ac
tin
g
twee
ts
’
s
en
tim
en
tal
f
ea
tu
r
es
in
two
d
if
f
er
e
n
t
m
e
th
o
d
s
.
T
h
en
,
th
e
ex
tr
ac
ted
f
ea
tu
r
es
ar
e
to
b
e
u
s
ed
f
o
r
g
en
er
atin
g
an
e
f
f
icien
t d
ataset
f
r
o
m
th
e
o
r
ig
in
al
o
n
e.
−
Usi
n
g
en
s
em
b
le
lear
n
in
g
m
o
d
els
to
p
r
ed
ict
th
e
s
to
ck
p
r
ice
an
d
co
m
p
ar
in
g
th
eir
r
esu
lts
with
d
if
f
er
en
t
m
ac
h
in
e
lear
n
in
g
(
ML
)
an
d
d
e
ep
lear
n
in
g
(
DL
)
m
o
d
els.
−
2
2
d
i
f
f
er
en
t
s
to
ck
s
with
s
ev
er
al
ev
alu
atio
n
m
etr
ics
wer
e
u
tili
ze
d
to
th
o
r
o
u
g
h
ly
ev
alu
ate
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
p
r
o
p
o
s
ed
p
r
e
d
ictiv
e
m
o
d
els ag
ain
s
t o
n
e
o
f
th
e
ex
is
tin
g
r
esear
ch
wo
r
k
s
.
T
h
e
r
em
ai
n
in
g
p
ar
ts
o
f
th
e
p
a
p
er
ar
e
as
f
o
llo
ws.
Sectio
n
2
d
is
cu
s
s
es
s
o
m
e
p
ap
er
s
th
at
u
s
ed
ML
a
n
d
DL
in
p
r
e
d
ictin
g
s
to
ck
p
r
ice
b
ased
o
n
s
en
tim
en
t
a
n
aly
s
is
.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
o
l
o
g
y
is
ex
p
lain
e
d
in
s
ec
tio
n
3
.
Sectio
n
4
s
u
m
m
a
r
izes
th
e
r
esu
lts
o
f
o
u
r
s
tu
d
y
a
n
d
co
n
s
tr
u
cts
it
in
tab
les
an
d
b
a
r
ch
ar
ts
.
Fin
ally
,
th
e
p
ap
er
is
co
n
cl
u
d
ed
i
n
s
ec
tio
n
5
.
2.
RE
L
AT
E
D
W
O
R
K
2
.
1
.
ML
-
ba
s
e
d sto
ck
price
predic
t
io
n m
o
dels
Vijh
et
a
l.
[
1
2
]
p
r
o
p
o
s
ed
a
m
o
d
el
to
p
r
e
d
ict
th
e
n
ex
t
clo
s
in
g
p
r
ice
f
o
r
f
iv
e
d
if
f
e
r
en
t
f
ir
m
s
f
r
o
m
v
ar
io
u
s
f
ield
s
u
s
in
g
an
ar
tific
i
al
n
eu
r
al
n
etwo
r
k
(
ANN)
m
o
d
el
[
1
3
]
an
d
R
F
m
o
d
el.
T
h
ey
c
o
llected
th
e
d
ataset
o
v
er
1
0
y
ea
r
s
f
r
o
m
4
/
5
/2
0
0
9
t
o
4
/5
/
2
0
1
9
f
o
r
Nik
e,
Go
l
d
m
an
Sach
s
,
J
o
h
n
s
o
n
,
J
o
h
n
s
o
n
,
Pfi
ze
r
,
an
d
J
P
Mo
r
g
an
C
h
ase
an
d
C
o
.
B
ased
o
n
th
e
R
MSE
,
MA
PE,
an
d
MA
E
m
e
tr
ics,
th
e
co
m
p
ar
is
o
n
s
tu
d
y
s
h
o
wed
th
at
th
e
ANN
m
o
d
el
o
u
tp
er
f
o
r
m
s
R
F
in
s
to
ck
p
r
ice
p
r
e
d
ictio
n
.
Ho
we
v
er
,
th
e
y
s
h
o
u
ld
u
s
e
m
o
r
e
tech
n
iq
u
es
in
th
e
co
m
p
ar
is
o
n
t
o
en
s
u
r
e
t
h
e
ac
cu
r
ac
y
o
f
ANN
in
th
e
p
r
e
d
ictio
n
p
r
o
ce
s
s
.
C
h
r
is
tan
to
et
a
l.
[
1
4
]
s
u
g
g
es
ted
em
p
lo
y
in
g
f
in
a
n
cial
s
to
ck
d
ata
as
in
p
u
t
p
ar
am
eter
s
t
o
s
ev
er
al
m
ac
h
in
e
lear
n
i
n
g
m
o
d
els
s
u
ch
as
SVM
[
1
5
]
.
T
h
ey
o
b
tain
e
d
a
d
ataset
o
f
1
6
f
i
r
s
t
s
u
ch
as
NASDAQ,
Nik
k
ei
2
2
5
,
Han
g
Sen
g
in
d
ex
,
FTSE
1
0
0
,
DAX,
an
d
ASX.
T
h
e
p
r
ices
d
ataset
is
co
llected
f
o
r
th
e
p
er
io
d
f
r
o
m
th
e
4
th
o
f
J
an
u
ar
y
2
0
0
0
to
th
e
2
5
th
o
f
Octo
b
er
2
0
1
2
.
T
h
e
y
u
s
ed
th
e
m
u
ltip
le
ad
d
itiv
e
r
eg
r
es
s
io
n
tr
ee
s
(
MA
R
T
)
m
o
d
el
(
a
d
ec
is
io
n
tr
ee
-
b
ased
b
o
o
s
tin
g
alg
o
r
ith
m
)
an
d
c
o
m
p
ar
ed
it
ag
ain
s
t
an
SVM
m
o
d
el.
T
h
ey
f
o
u
n
d
o
u
t
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
P
r
ed
ictin
g
s
to
ck
p
r
ices u
s
in
g
en
s
emb
le
lea
r
n
in
g
tech
n
i
q
u
es
(
S
a
lma
E
ls
a
ye
d
)
1785
th
at
th
e
v
o
lu
m
e
o
f
th
e
tr
ain
in
g
d
ata
is
im
p
o
r
tan
t
f
o
r
t
h
e
SVM
m
o
d
el
b
ec
au
s
e
if
its
s
ize
is
in
s
u
f
f
icien
t,
th
e
h
y
p
er
p
lan
e
m
ig
h
t
b
e
u
n
ab
le
t
o
ef
f
ec
tiv
ely
d
iv
id
e
th
e
d
ata.
T
h
ey
u
s
ed
th
e
R
MSE
m
etr
ic
[
1
6
]
to
ev
alu
ate
th
e
p
er
f
o
r
m
an
ce
o
f
th
eir
m
o
d
el.
T
h
ey
ap
p
lied
lin
ea
r
r
eg
r
ess
io
n
,
g
en
er
alize
d
lin
ea
r
m
o
d
el
(
GL
M)
,
an
d
SVM
to
f
o
r
ec
ast
th
e
d
aily
NASDAQ
p
r
ice
m
o
v
em
en
t.
T
h
e
r
esu
lts
s
h
o
wed
th
at
th
e
p
r
o
p
o
s
ed
SVM
m
o
d
el
o
u
tp
er
f
o
r
m
s
th
e
o
th
er
m
o
d
els,
as it a
ch
iev
e
d
th
e
lo
west R
MSE
.
Sad
o
r
s
k
y
[
1
7
]
u
tili
ze
d
a
r
an
d
o
m
f
o
r
ests
m
o
d
el
to
f
o
r
ec
ast
t
h
e
s
to
ck
p
r
ice
d
ir
ec
tio
n
o
f
cle
an
en
er
g
y
ex
ch
an
g
e
-
tr
ad
ed
f
u
n
d
s
(
E
FTs).
T
h
e
au
th
o
r
s
u
s
ed
r
an
d
o
m
f
o
r
ests
an
d
d
ec
is
io
n
tr
ee
b
ag
g
in
g
m
o
d
els
in
th
e
p
r
ed
ictio
n
task
an
d
co
m
p
a
r
ed
th
eir
r
esu
lts
with
an
ANN
m
o
d
el
[
1
8
]
an
d
SVMs.
T
h
ey
u
s
ed
d
ata
o
n
th
e
s
to
ck
v
alu
e
o
f
f
iv
e
well
-
k
n
o
wn
f
ir
m
s
,
in
th
e
US
-
lis
ted
,
an
d
e
x
te
n
s
iv
ely
tr
ad
e
d
clea
n
en
e
r
g
y
E
T
Fs
.
T
h
e
d
aily
d
ata
s
et
b
eg
in
s
o
n
1
J
an
u
ar
y
2
0
0
9
an
d
f
in
is
h
es
o
n
3
0
Sep
tem
b
er
2
0
2
0
.
T
h
e
i
n
f
o
r
m
atio
n
was
o
b
tain
ed
f
r
o
m
Yah
o
o
Fin
an
ce
.
T
h
e
f
o
r
ec
ast
ac
cu
r
a
cy
o
f
ea
ch
E
T
F
is
ev
alu
ate
d
ac
r
o
s
s
a
p
er
io
d
r
an
g
in
g
f
r
o
m
o
n
e
d
ay
to
twen
t
y
d
ay
s
.
Fo
r
p
r
ed
ictin
g
r
a
n
g
es
o
f
1
0
d
ay
s
o
r
lo
n
g
e
r
,
th
e
f
o
r
ec
asti
n
g
ac
cu
r
ac
y
o
f
R
F
an
d
tr
ee
b
ag
g
in
g
m
o
d
els
ex
ce
ed
s
8
0
%.
T
h
ey
f
o
u
n
d
th
at
R
F
m
o
d
el
[
1
9
]
an
d
d
ec
is
io
n
tr
ee
b
ag
g
in
g
ar
e
s
im
p
ler
to
p
r
e
d
ict
th
an
o
th
er
ML
m
o
d
els
s
u
ch
as
ANNs
an
d
S
VM
s
.
Ho
wev
er
,
th
e
y
s
h
o
u
ld
h
av
e
u
s
ed
m
o
r
e
m
etr
ics
to
en
s
u
r
e
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
eir
tech
n
iq
u
es.
2
.
2
.
DL
-
ba
s
ed
s
t
o
ck
price
predict
io
n m
o
dels
Me
h
ta
et
a
l.
[
2
0
]
p
r
o
p
o
s
ed
t
o
p
r
ed
ict
th
e
I
n
d
ian
s
to
ck
m
ar
k
et
d
u
r
in
g
th
e
p
er
io
d
f
r
o
m
th
e
1
st
o
f
Octo
b
er
2
0
1
4
to
th
e
31
st
of
De
ce
m
b
er
2
0
1
8
u
s
in
g
s
en
tim
en
t
an
aly
s
is
.
T
h
ey
ap
p
lied
m
ac
h
in
e
lear
n
in
g
an
d
d
ee
p
lear
n
in
g
tech
n
iq
u
es
n
a
m
ely
,
SVM,
lin
ea
r
r
eg
r
ess
io
n
,
n
aïv
e
B
ay
es
,
an
d
L
STM
.
T
h
ey
an
al
y
ze
d
t
h
e
r
elatio
n
s
h
ip
b
etwe
en
m
ed
ia
d
ata
an
d
m
ar
k
e
t
p
r
ice
r
ates
o
v
er
a
co
n
s
tr
ain
ed
tim
e
an
d
ap
p
lied
a
r
an
g
e
of
f
ac
to
r
s
f
r
o
m
f
in
alize
d
d
ata
s
ets
to
en
h
an
ce
p
r
ed
ictio
n
ac
cu
r
ac
y
.
T
h
e
f
in
d
in
g
s
p
r
o
v
e
d
th
at
by
em
p
lo
y
in
g
o
n
lin
e
p
la
tf
o
r
m
s
an
d
f
in
an
cial
n
ews
d
ata,
L
STM
[
2
1
]
was
ab
le
to
ac
h
iev
e
th
e
h
ig
h
est
ac
cu
r
ac
y
o
f
a
b
o
u
t
9
2
.
4
5
%.
L
i
n
ea
r
SVC
clas
s
if
ier
ac
h
iev
ed
th
e
s
ec
o
n
d
-
h
ig
h
est
p
r
ec
is
io
n
class
if
ier
.
T
h
e
n
aïv
e
B
ay
es,
lin
ea
r
r
eg
r
ess
io
n
,
an
d
m
ax
im
u
m
en
tr
o
p
y
m
eth
o
d
o
l
o
g
y
r
em
ain
ed
a
r
o
u
n
d
8
6
.
7
2
%,
8
6
.
7
5
%,
an
d
8
8
.
9
3
%
,
r
esp
ec
tiv
ely
.
In
s
tu
d
y
[
2
2
]
,
th
e
p
r
o
p
o
s
ed
m
o
d
el
in
clu
d
e
d
a
r
eliab
le
f
o
r
ec
asti
n
g
tech
n
iq
u
e
f
o
r
th
e
p
r
o
b
ab
ilit
y
o
f
s
to
ck
m
ar
k
et
ch
an
g
es.
Firstl
y
,
t
h
e
m
o
s
t
im
p
o
r
tan
t
f
in
an
cial
m
ar
k
et
in
d
icato
r
s
ar
e
b
ee
n
ch
o
s
en
th
at
m
ig
h
t
b
e
u
tili
ze
d
to
f
o
r
ec
ast
th
e
s
to
ck
m
ar
k
et.
So
m
e
s
tatis
tical
m
ac
h
in
e
lear
n
in
g
ap
p
r
o
ac
h
es
h
av
e
b
ee
n
ap
p
lied
as
well
as
two
n
ew
alg
o
r
ith
m
s
th
at
p
r
o
d
u
ce
b
etter
r
esu
lts
in
o
th
er
s
cien
tific
d
o
m
ain
s
wh
ich
ar
e
d
ee
p
n
eu
r
al
n
etwo
r
k
s
an
d
ex
tr
em
e
g
r
ad
ien
t
b
o
o
s
tin
g
(
XGBo
o
s
t)
[
2
3
]
.
T
h
e
p
er
f
o
r
m
an
ce
m
etr
ics
s
u
ited
f
o
r
u
n
b
alan
ce
d
d
atasets
ar
e
b
ee
n
ap
p
lied
f
o
r
test
in
g
th
e
m
o
d
els.
T
h
eir
em
p
ir
ical
f
i
n
d
in
g
s
s
h
o
wed
th
at
d
ee
p
lear
n
in
g
[
2
4
]
p
r
o
d
u
ce
d
b
ette
r
p
r
ed
ictio
n
ac
c
u
r
ac
y
.
Ab
d
u
llah
an
d
Salah
[
2
5
]
im
p
lem
en
ted
th
e
C
NN
-
L
STM
m
o
d
el,
a
h
y
b
r
id
m
o
d
el
th
at
m
er
g
es
an
L
STM
m
o
d
el
[
2
6
]
an
d
co
n
v
o
lu
tio
n
n
eu
r
al
n
etwo
r
k
(
C
N
N)
ar
ch
itectu
r
e
[
2
7
]
,
[
2
8
]
.
T
h
e
p
r
o
p
o
s
ed
h
y
b
r
id
m
o
d
el
m
ak
es
u
s
e
o
f
th
e
co
n
v
o
lu
tio
n
lay
er
attr
i
b
u
tes
f
o
r
r
etr
iev
in
g
r
elev
a
n
t
f
ea
tu
r
es
co
n
t
ain
ed
in
tim
e
s
er
ies
d
ata,
in
ad
d
itio
n
to
th
e
L
STM
d
esig
n
’
s
ab
ilit
y
to
lear
n
l
o
n
g
-
ter
m
ass
o
ciatio
n
s
.
T
h
e
d
atasets
u
s
ed
in
th
e
test
s
wer
e
g
ath
er
e
d
f
r
o
m
Yah
o
o
F
in
an
ce
f
o
r
t
h
r
ee
y
ea
r
s
f
r
o
m
t
h
e
1
st
o
f
Dec
em
b
er
2
0
1
6
t
o
t
h
e
1
st
o
f
Dec
em
b
er
2
0
2
0
v
ia
a
d
aily
tim
e
in
ter
v
a
l.
T
h
e
an
al
y
s
es
wer
e
p
er
f
o
r
m
ed
o
n
th
r
ee
u
n
iq
u
e
d
ataset
f
o
r
m
s
:
s
to
ck
m
ar
k
et,
f
o
r
eig
n
e
x
ch
an
g
e
to
o
ls
,
an
d
cr
y
p
to
cu
r
r
en
c
y
.
Usi
n
g
two
e
v
alu
atio
n
m
etr
ics
n
am
ely
,
M
SE
an
d
MA
E
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
els
o
u
tp
er
f
o
r
m
e
d
th
e
s
tate
-
of
-
th
e
-
ar
t
ap
p
r
o
ac
h
es,
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es,
an
d
s
tatis
tical
tech
n
iq
u
es.
T
h
e
f
in
d
i
n
g
s
s
h
o
w
th
at
th
e
s
u
g
g
ested
C
NN
-
L
S
T
M
m
o
d
el
o
u
tp
er
f
o
r
m
s
th
e
L
STM
m
o
d
el
an
d
th
e
o
th
er
m
o
d
els o
n
th
e
m
ajo
r
ity
o
f
th
e
d
atasets
test
ed
.
3.
T
H
E
P
RO
P
O
SE
D
M
E
T
H
O
D
I
n
Fig
u
r
e
1,
we
u
tili
ze
d
a
d
a
taset
f
r
o
m
t
h
e
Kag
g
le
web
s
it
e
ab
o
u
t
s
to
ck
twee
ts
,
as
ca
n
b
e
f
o
u
n
d
in
ℎ
:
/
/
.
.
/
/
/
−
−
−
−
−
−
?
=
_
.
.
Nex
t,
we
co
n
d
u
cte
d
a
p
r
e
p
r
o
ce
s
s
in
g
s
tep
to
elim
i
n
ate
n
o
n
-
ess
en
tial
co
n
ten
t.
T
o
en
s
u
r
e
p
o
lar
ity
,
we
ex
tr
ac
ted
f
ea
tu
r
es
f
r
o
m
th
e
twee
ts
u
s
in
g
tw
o
d
is
tin
ct
m
eth
o
d
s
.
Su
b
s
eq
u
en
tly
,
we
u
tili
ze
d
v
ar
io
u
s
en
s
em
b
le,
m
ac
h
i
n
e
lear
n
in
g
,
a
n
d
d
ee
p
lear
n
in
g
m
o
d
els
to
b
u
ild
th
e
p
r
ed
ictiv
e
m
o
d
els.
Fin
ally
,
we
ap
p
lied
ev
alu
atio
n
m
etr
ic
s
to
ass
es
s
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
ese
p
r
e
d
ictio
n
m
o
d
els.
I
n
th
e
o
v
er
v
iew
s
u
b
s
ec
tio
n
,
we
clea
r
ly
d
is
cu
s
s
ed
th
e
s
tep
s
o
f
o
u
r
m
o
d
el.
I
n
th
e
d
ataset
s
u
b
s
ec
tio
n
,
we
d
etailed
th
e
p
r
o
ce
s
s
o
f
g
en
er
atin
g
th
e
f
in
al
d
ataset.
T
h
e
f
ea
tu
r
e
ex
tr
ac
tio
n
s
u
b
s
ec
tio
n
ex
p
lain
ed
th
e
two
d
if
f
er
en
t
m
eth
o
d
s
u
s
ed
f
o
r
f
ea
tu
r
e
ex
tr
ac
tio
n
.
I
n
th
e
p
r
ed
ictiv
e
m
o
d
el’
s
s
u
b
s
ec
tio
n
,
w
e
d
escr
ib
ed
all
th
e
tr
ain
ed
m
o
d
els.
T
h
e
im
p
lem
en
tatio
n
d
etails
s
u
b
s
ec
tio
n
s
h
o
wca
s
ed
th
e
im
p
lem
en
tatio
n
o
f
t
h
ese
m
o
d
els.
Fin
ally
,
in
th
e
ev
alu
atio
n
m
et
r
ics
s
u
b
s
ec
tio
n
,
we
illu
s
tr
ated
th
e
v
ar
io
u
s
m
etr
ics
u
s
ed
to
ev
alu
ate
th
e
tr
ain
ed
m
o
d
els.
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.
15
,
No
.
2
,
Ap
r
il
20
25
:
1
7
8
3
-
1
7
9
2
1786
Fig
u
r
e
1
.
T
h
e
s
tep
s
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
3
.
1
.
O
v
er
v
iew
T
o
p
e
r
f
o
r
m
m
o
d
elin
g
f
o
r
t
h
e
s
to
ck
m
ar
k
et
p
r
e
d
ictio
n
,
we
c
o
llected
s
to
ck
-
r
elate
d
twee
ts
f
r
o
m
t
h
e
X
s
o
cial
m
ed
ia
p
latf
o
r
m
f
o
r
d
if
f
er
en
t
s
to
ck
s
f
r
o
m
th
e
Kag
g
le
web
s
ite.
T
h
e
ex
tr
ac
ted
twee
ts
co
n
tain
u
n
n
ec
ess
ar
y
d
ata
lik
e
s
p
ec
ial
ch
ar
ac
ter
s
,
UR
L
s
,
em
o
jis
,
h
a
s
h
tag
s
(
#
)
,
an
d
@
.
T
h
u
s
,
we
h
av
e
p
r
ep
r
o
ce
s
s
ed
th
ese
twee
ts
to
o
b
tain
o
n
ly
th
e
p
lai
n
s
en
ten
ce
s
.
T
h
en
,
we
ex
tr
ac
ted
th
e
f
e
atu
r
es
f
r
o
m
th
e
twee
ts
in
tw
o
d
if
f
er
en
t
way
s
to
en
s
u
r
e
th
e
p
o
lar
ity
.
Nex
t,
we
co
m
p
a
r
ed
t
h
e
p
o
lar
ity
o
f
t
h
e
twee
ts
with
th
e
tr
e
n
d
o
f
t
h
e
f
in
an
cial
d
ata
to
ch
o
o
s
e
o
n
ly
th
e
m
atch
ed
twe
ets
an
d
ig
n
o
r
e
th
e
o
t
h
er
twee
ts
.
T
h
e
d
ataset
s
ize
i
s
r
ed
u
ce
d
f
r
o
m
8
0
,
7
9
3
to
1
5
,
4
3
0
.
W
e
d
iv
id
ed
th
e
r
ed
u
ce
d
d
ataset
in
to
2
2
d
atasets
b
ased
o
n
th
e
s
to
ck
n
am
e.
T
h
u
s
,
we
o
b
tain
ed
2
2
d
atasets
f
o
r
2
2
s
to
ck
s
.
T
o
p
r
ed
ict
th
e
p
r
ice
o
f
ea
ch
s
to
ck
,
we
f
r
am
e
d
th
e
p
r
o
b
l
em
o
f
p
r
ice
p
r
e
d
ictio
n
as
a
r
eg
r
ess
io
n
p
r
o
b
lem
wh
e
r
e
th
e
o
u
tco
m
e
v
ar
iab
le
is
th
e
p
r
ed
icted
f
u
tu
r
e
s
to
ck
p
r
ice
d
aily
.
Dif
f
er
en
t
en
s
em
b
le
lear
n
in
g
m
o
d
els
wer
e
u
tili
ze
d
.
Fiv
e
en
s
em
b
le
lear
n
in
g
m
o
d
els,
n
am
ely
,
,
,
,
an
d
wer
e
u
s
ed
.
E
ac
h
p
r
e
d
ictiv
e
m
o
d
el
is
ev
alu
ated
o
n
f
iv
e
m
etr
ics
wh
ich
ar
e
MA
E
,
MA
PE,
MSE
,
R
MSE
,
an
d
R
2
.
E
ac
h
d
ataset
is
d
iv
id
ed
in
to
tr
ain
in
g
an
d
test
in
g
s
ets
f
o
r
ev
alu
atio
n
.
T
h
e
tr
ain
i
n
g
s
et
co
n
tain
s
8
0
%
o
f
th
e
d
ataset,
an
d
th
e
test
s
et
i
s
m
ad
e
u
p
o
f
th
e
r
em
ain
in
g
2
0
%
o
f
th
e
d
ataset.
W
e
u
tili
ze
d
s
ev
er
al
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
wh
ich
ar
e
KNN,
SVM,
an
d
lin
ea
r
r
eg
r
ess
io
n
.
B
esid
es,
we
u
tili
ze
d
a
d
ee
p
lear
n
in
g
m
o
d
el,
i.e
.
,
an
L
STM
m
o
d
el
[
2
5
]
,
t
o
en
s
u
r
e
th
e
ac
cu
r
ac
y
o
f
en
s
em
b
le
lear
n
in
g
m
o
d
els.
3
.
2
.
Da
t
a
s
et
W
e
h
av
e
c
o
llected
th
e
d
ata
s
et
o
f
d
i
f
f
er
en
t
s
to
ck
s
f
r
o
m
th
e
Kag
g
le
web
s
ite
o
n
t
h
e
f
o
llo
win
g
lin
k
(
ℎ
:
/
/
.
.
/
/
/
−
−
−
−
−
−
?
=
_
.
,
last
ac
ce
s
s
ed
o
n
2
3
Ma
r
ch
2
0
2
4
)
.
T
h
e
d
ataset
co
n
s
is
ts
o
f
two
p
ar
ts
.
T
h
e
f
ir
s
t
p
ar
t
co
n
tain
s
th
e
twee
ts
with
a
s
ize
o
f
8
0
,
7
9
3
a
n
d
f
o
u
r
f
ea
tu
r
es
wh
ich
ar
e
d
ate,
twee
t
,
s
to
ck
n
am
e,
an
d
co
m
p
an
y
n
a
m
e.
T
h
e
o
th
e
r
p
a
r
t
o
f
th
e
d
at
aset
co
n
tain
s
th
e
s
to
ck
p
r
ice
d
ata
with
a
s
ize
o
f
6
,
3
0
0
a
n
d
eig
h
t
f
ea
tu
r
es
wh
i
ch
ar
e
d
ate,
o
p
en
p
r
ice,
h
ig
h
est
p
r
ice,
lo
west
p
r
ice,
clo
s
in
g
p
r
ice,
ad
j
u
s
ted
clo
s
in
g
p
r
ice,
v
o
lu
m
e,
an
d
s
to
ck
n
am
e
.
Of
n
o
te,
th
e
ex
tr
ac
te
d
twee
ts
co
n
tain
e
d
u
n
n
ec
ess
ar
y
d
ata
lik
e
s
p
ec
ial
ch
ar
ac
ter
s
,
UR
L
s
,
em
o
jis
,
h
as
h
tag
s
(
#
)
,
an
d
@
.
T
h
u
s
,
we
h
av
e
p
r
ep
r
o
ce
s
s
ed
th
ese
twee
ts
to
o
b
tain
o
n
ly
t
h
e
clea
n
ed
s
en
ten
ce
s
.
T
h
en
,
we
ex
tr
ac
ted
th
e
f
ea
tu
r
es
in
two
way
s
to
en
s
u
r
e
th
e
p
o
lar
ity
.
Af
ter
T
h
at,
we
ch
o
s
e
th
e
twee
ts
wh
o
s
e
p
o
lar
ity
was
m
atch
ed
with
th
e
tr
en
d
o
f
th
e
f
in
an
cial
d
ata
an
d
ig
n
o
r
e
d
th
e
o
th
er
s
.
T
h
u
s
,
we
r
ed
u
ce
d
th
e
d
ataset
s
ize
f
r
o
m
8
0
,
7
9
3
to
1
5
,
4
3
0
.
W
e
d
iv
id
ed
th
e
wh
o
le
d
ataset
in
to
s
m
all
d
atasets
b
ased
o
n
th
e
s
to
ck
n
am
e.
W
e
o
b
tain
e
d
2
2
d
atasets
f
o
r
2
2
s
to
ck
n
a
m
es.
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
P
r
ed
ictin
g
s
to
ck
p
r
ices u
s
in
g
en
s
emb
le
lea
r
n
in
g
tech
n
i
q
u
es
(
S
a
lma
E
ls
a
ye
d
)
1787
3
.
3
.
F
ea
t
ures e
x
t
ra
ct
io
n
Fo
r
th
e
s
ak
e
o
f
f
ea
tu
r
e
ex
tr
ac
t
io
n
,
we
u
tili
ze
d
two
d
if
f
er
en
t
m
eth
o
d
s
to
en
s
u
r
e
th
e
co
r
r
ec
t
n
ess
o
f
th
e
p
o
lar
ity
s
co
r
e.
W
e
u
s
ed
th
e
v
alen
ce
awa
r
e
d
ictio
n
ar
y
f
o
r
s
en
tim
en
t
r
ea
s
o
n
in
g
(
VADE
R
)
m
o
d
el
[
2
9
]
.
T
h
e
VADE
R
m
o
d
el
is
a
s
en
tim
en
t
an
aly
s
is
to
o
l
th
at
ca
n
d
is
tin
g
u
is
h
b
etwe
en
p
o
la
r
ity
(
p
o
s
itiv
e
o
r
n
e
g
ativ
e)
an
d
in
ten
s
ity
o
f
f
ee
lin
g
s
.
I
t
is
in
c
lu
d
ed
in
th
e
n
atu
r
al
la
n
g
u
a
g
e
to
o
lk
it
(
NL
T
K
)
p
ac
k
ag
e
[
3
0
]
an
d
ca
n
b
e
u
s
ed
ef
f
ec
tiv
ely
o
n
p
lain
tex
t
d
ata.
T
h
e
s
en
tim
en
tal
s
co
r
e
is
in
th
e
r
an
g
e
o
f
-
1
to
1
f
o
llo
win
g
th
e
co
n
d
itio
n
d
en
o
ted
in
(
1
)
.
=
{
,
≥
0
.
5
,
0
.
5
>
≥
−
0
.
5
,
ℎ
(
1
)
wh
er
e
is
th
e
s
en
tim
en
tal
s
co
r
e
v
alu
e
.
W
e
ca
lled
th
e
f
ir
s
t
m
e
th
o
d
p
o
lar
ity
1
.
I
n
t
h
e
s
ec
o
n
d
m
eth
o
d
,
we
ch
o
s
e
th
e
m
ax
im
u
m
v
alu
e
o
f
p
o
s
itiv
e,
n
eg
ativ
e,
an
d
n
e
u
tr
al
p
er
c
en
tag
es
an
d
co
n
s
id
er
ed
it
th
e
p
o
lar
ity
s
co
r
e;
we
ca
lled
th
is
m
eth
o
d
p
o
lar
ity
2
.
T
h
en
,
we
co
m
p
u
ted
t
h
e
p
er
ce
n
tag
e
ch
a
n
g
e
o
f
th
e
cl
o
s
in
g
p
r
ice
as
th
e
p
er
ce
n
tag
e
b
etwe
en
two
c
o
n
s
e
cu
tiv
e
d
ay
s
o
f
th
e
clo
s
in
g
p
r
ic
es a
n
d
m
ad
e
th
e
s
am
e
co
n
d
itio
n
as d
en
o
ted
in
(
1
)
to
d
eter
m
in
e
its
p
o
lar
ity
s
co
r
e.
W
h
en
we
co
m
p
ar
ed
p
o
lar
it
y
1
a
n
d
p
o
lar
ity
2
with
th
e
p
o
lar
ity
o
f
th
e
d
aily
clo
s
in
g
p
r
ice
ch
a
n
g
e,
we
n
o
ti
ce
d
th
at
p
o
lar
ity
1
was
m
atc
h
ed
with
1
5
,
4
3
0
r
o
ws
o
f
th
e
d
aily
clo
s
in
g
p
r
ice
ch
an
g
e
wh
ile
p
o
lar
ity
2
was m
atch
ed
with
8
,
8
5
4
r
o
ws
o
f
th
e
d
aily
clo
s
in
g
p
r
ice
ch
a
n
g
e.
T
h
u
s
,
we
u
tili
ze
d
th
e
p
o
lar
ity
o
f
th
e
s
en
tim
en
tal
s
co
r
e,
i.e
.
,
p
o
lar
ity
1
in
th
e
p
r
o
p
o
s
ed
m
o
d
el.
W
e
m
er
g
ed
all
th
e
co
lu
m
n
s
o
f
th
e
two
d
atasets
(
twee
ts
d
at
aset
an
d
clo
s
in
g
p
r
ice
ch
a
n
g
e
s
d
ataset)
b
ased
o
n
th
e
d
ate
an
d
s
to
ck
n
am
e
to
g
et
o
n
e
d
ataset
m
er
g
in
g
th
e
twee
ts
’
p
o
lar
ity
a
n
d
th
e
s
to
ck
p
r
ice
in
f
o
r
m
atio
n
.
T
h
u
s
,
t
h
e
f
i
n
al
d
ataset
co
n
tain
s
th
e
f
o
llo
w
in
g
f
ea
t
u
r
es:
d
ate,
s
to
ck
n
a
m
e,
ad
ju
s
ted
clo
s
e,
s
en
tim
en
t sco
r
e,
an
d
p
o
lar
ity
.
W
e
d
iv
id
ed
ea
ch
d
ataset
in
a
r
atio
o
f
8
0
% :
2
0
%
f
o
r
tr
ain
in
g
an
d
test
in
g
s
ets.
3
.
4
.
T
he
pred
ict
iv
e
m
o
dels
Fo
r
th
e
p
r
e
d
ictiv
e
m
o
d
el,
we
f
r
am
ed
th
e
p
r
o
b
lem
o
f
s
to
ck
p
r
ice
p
r
e
d
ictio
n
as
a
r
e
g
r
ess
io
n
p
r
o
b
lem
.
W
e
p
r
o
p
o
s
ed
u
s
in
g
d
if
f
er
e
n
t
e
n
s
em
b
le
lear
n
in
g
m
o
d
els
[
3
1
]
to
p
r
e
d
ict
th
e
s
to
ck
p
r
ices.
E
n
s
em
b
le
lear
n
in
g
is
a
m
ac
h
in
e
lear
n
in
g
a
p
p
r
o
ac
h
th
at
in
v
o
lv
es
tr
ain
in
g
s
ev
er
al
lear
n
er
s
to
s
o
lv
e
th
e
s
am
e
is
s
u
e.
T
h
e
en
s
em
b
le
m
o
d
els
ar
e
b
r
o
a
d
ly
ca
teg
o
r
iz
ed
in
to
s
tack
in
g
,
b
len
d
in
g
,
b
ag
g
in
g
,
a
n
d
b
o
o
s
tin
g
.
Stack
i
n
g
is
an
ad
v
an
ce
d
en
s
em
b
le
lear
n
in
g
s
tr
ateg
y
in
wh
ich
in
d
iv
id
u
al
m
o
d
el
p
r
e
d
ic
tio
n
s
ar
e
lay
er
ed
an
d
u
tili
ze
d
as
in
p
u
t
to
tr
ain
th
e
m
eta
-
m
o
d
el.
T
h
is
m
eta
-
m
o
d
e
l
is
th
en
ap
p
lied
to
th
e
test
s
et
to
m
ak
e
p
r
ed
ictio
n
s
.
T
h
e
tr
ain
in
g
d
ata
s
et
is
d
iv
id
ed
in
to
n
p
a
r
ts
.
T
h
e
b
asic
m
o
d
el
is
tr
ain
ed
f
o
r
ea
ch
n
−1
p
ar
t.
B
len
d
in
g
is
a
m
eth
o
d
s
im
ilar
to
s
tack
in
g
in
th
o
s
e
p
r
ed
ictio
n
s
ar
e
m
a
d
e
u
s
in
g
a
v
ali
d
atio
n
s
et
f
r
o
m
th
e
t
r
ain
in
g
s
et.
T
h
e
tr
ain
in
g
d
ata
s
et
is
d
iv
id
ed
in
to
tr
ain
in
g
a
n
d
v
alid
atio
n
s
ets.
B
ag
g
in
g
is
an
ap
p
r
o
ac
h
th
at
co
m
b
in
es
t
h
e
f
in
d
in
g
s
o
f
in
d
iv
id
u
al
m
o
d
els
to
p
r
o
v
id
e
a
m
o
r
e
g
en
er
alize
d
o
u
tco
m
e.
I
n
d
iv
id
u
al
m
o
d
els,
h
o
wev
er
,
ar
e
n
o
t g
iv
e
n
th
e
s
am
e
d
ataset.
I
n
s
tead
,
th
e
b
o
o
ts
tr
ap
p
in
g
ap
p
r
o
ac
h
is
u
s
e
d
to
b
u
ild
r
ep
lace
m
en
t
s
u
b
s
ets
o
f
t
h
e
o
r
ig
in
al
d
ataset.
I
n
t
h
e
b
o
o
s
tin
g
a
p
p
r
o
ac
h
,
e
ac
h
co
n
s
ec
u
tiv
e
m
o
d
el
attem
p
ts
to
f
ix
th
e
er
r
o
r
s
in
th
e
p
r
io
r
m
o
d
el.
As
a
r
esu
lt,
s
u
b
s
eq
u
en
t
m
o
d
els
r
ely
o
n
th
e
p
r
io
r
m
o
d
el.
B
o
o
s
tin
g
cr
e
ates
a
s
u
b
s
et
f
r
o
m
th
e
e
n
tire
d
ataset.
A
b
asic
m
o
d
el
is
tr
ain
ed
u
s
in
g
th
is
s
u
b
s
et.
T
h
is
m
o
d
el
m
ak
es
p
r
e
d
ictio
n
s
th
r
o
u
g
h
o
u
t
th
e
wh
o
le
d
ataset.
I
n
co
r
r
ec
t
f
o
r
ec
asts
h
av
e
b
ee
n
n
o
ticed
.
T
h
en
,
an
o
th
er
b
ase
m
o
d
el
is
tr
ain
ed
to
f
ix
th
e
p
r
io
r
m
o
d
el
’
s
m
is
tak
es.
3
.
5
.
I
m
plem
ent
a
t
io
n
det
a
ils
W
e
u
tili
ze
d
th
e
class
with
a
lo
s
s
f
u
n
ctio
n
o
f
“
”
v
alu
e
an
d
2
0
0
iter
atio
n
s
.
W
e
u
s
e
th
e
im
p
lem
en
tatio
n
o
f
th
e
C
atB
o
o
s
t
an
d
i
p
y
wid
g
ets
p
ac
k
a
g
es.
T
h
e
p
o
o
l
is
an
in
ter
n
al
d
ata
s
tr
u
ctu
r
e
o
f
C
atB
o
o
s
t
th
at
wr
ap
s
th
e
u
tili
ze
d
d
ata
an
d
tar
g
et
v
alu
es.
T
h
e
p
o
o
l
ca
n
m
ak
e
th
e
tr
ain
in
g
p
r
o
ce
s
s
f
aster
.
T
h
en
,
we
f
e
d
th
e
m
o
d
el
with
th
e
tr
ain
in
g
d
ataset
to
f
it
th
e
m
o
d
el.
T
h
en
,
th
e
ev
alu
atio
n
f
u
n
ctio
n
r
ec
eiv
ed
th
e
tr
u
e
v
alu
es.
W
e
u
tili
ze
d
th
e
an
d
clas
s
es
with
d
ef
au
lt
p
ar
am
eter
v
alu
es
an
d
f
itted
th
e
m
o
d
el
with
X
c
o
n
tain
in
g
th
e
lis
t
o
f
v
alu
es
o
f
th
e
s
en
tim
en
t
s
co
r
e
an
d
Y
co
n
tain
in
g
th
e
lis
t
o
f
v
a
lu
es
o
f
th
e
a
d
ju
s
ted
clo
s
in
g
p
r
ices.
Stack
ed
g
en
er
aliza
tio
n
c
o
n
s
is
ts
o
f
p
ilin
g
th
e
r
esu
lt
o
f
th
e
s
in
g
le
esti
m
ato
r
s
an
d
u
s
in
g
a
m
ea
s
u
r
e
to
ca
lc
u
late
th
e
f
in
al
p
r
ed
ictio
n
.
T
h
r
o
u
g
h
s
tack
in
g
,
th
e
ef
f
ec
tiv
en
ess
o
f
ea
ch
p
r
e
d
icto
r
ca
n
b
e
u
tili
ze
d
b
y
f
ee
d
i
n
g
it
s
o
u
tp
u
t
in
to
th
e
last
p
r
ed
icto
r
.
T
h
u
s
,
we
u
tili
ze
d
th
e
with
th
e
esti
m
ato
r
s
’
p
ar
am
eter
s
wh
ic
h
ar
e
,
,
an
d
.
T
h
en
we
f
itted
th
e
m
o
d
el
with
X
tr
ain
an
d
Y
tr
ain
p
ar
am
eter
s
.
W
e
tu
n
ed
th
e
an
d
class
es
with
2
5
f
o
r
th
e
r
an
d
o
m
s
tate’
s
p
ar
am
eter
.
W
e
u
tili
ze
d
th
e
ℎ
class
with
3
n
eig
h
b
o
r
s
.
Fin
ally
,
we
u
tili
ze
d
th
e
lin
ea
r
s
u
p
p
o
r
t v
ec
t
o
r
r
e
g
r
ess
io
n
(
)
an
d
lin
ea
r
r
e
g
r
ess
io
n
with
th
e
d
e
f
au
lt p
ar
am
eter
s
.
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.
15
,
No
.
2
,
Ap
r
il
20
25
:
1
7
8
3
-
1
7
9
2
1788
3
.
6
.
E
v
a
lua
t
io
n
m
et
rics
T
o
ev
alu
ate
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
p
r
e
d
ictio
n
m
o
d
els,
we
u
s
ed
th
e
ev
alu
atio
n
m
etr
ics
as
in
[
3
2
]
wh
ich
ar
e:
T
h
e
MA
E
m
ea
s
u
r
e
[
3
3
]
e
v
alu
ates
th
e
ab
s
o
lu
te
d
if
f
er
en
ce
b
etwe
en
ac
tu
al
an
d
f
o
r
ec
asted
r
esu
lts
wh
ich
is
d
en
o
ted
i
n
(
2
)
.
I
t m
ea
s
u
r
es h
o
w
f
ar
th
e
f
o
r
ec
asts
d
if
f
er
ed
f
r
o
m
th
e
ac
tu
al
o
u
tc
o
m
e
.
M
A
E
=
1
∑
[
−
̅
]
=
1
(
2
)
wh
er
e
y
is
th
e
ac
tu
al
v
alu
e,
y
′
is
th
e
p
r
ed
icted
v
alu
e
an
d
n
r
ep
r
esen
ts
th
e
s
ize
of
th
e
test
s
e
t
.
T
h
e
MSE
m
etr
ic
is
co
m
p
u
te
d
by
av
e
r
ag
in
g
t
h
e
s
q
u
ar
e
of
th
e
d
if
f
er
en
ce
b
etwe
en
th
e
ac
tu
al
an
d
f
o
r
ec
asted
v
alu
es,
as d
e
n
o
ted
i
n
(
3
)
.
=
1
∑
(
−
̅
)
2
=
1
(
3
)
T
h
e
R
MSE
m
etr
ic
[
3
4
]
is
t
h
e
s
q
u
ar
e
r
o
o
t
of
th
e
a
v
er
ag
e
of
th
e
s
q
u
a
r
ed
v
ar
ian
ce
of
th
e
r
ea
l
an
d
f
o
r
ec
asted
r
esu
lts
wh
ich
id
d
en
o
te
d
in
(
4
)
.
=
√
1
∑
(
−
̅
)
2
=
1
(
4
)
T
h
e
MA
PE
m
etr
ic
[
3
5
]
ev
al
u
ates
a
p
r
ed
ictio
n
m
o
d
el’
s
ac
c
u
r
ac
y
.
I
t
c
o
m
p
u
tes
h
o
w
ac
c
u
r
ate
th
e
an
ticip
ated
v
alu
e
was
to
th
e
ac
tu
al
v
alu
e
b
y
av
er
ag
i
n
g
th
e
ab
s
o
lu
te
p
er
ce
n
tag
e
er
r
o
r
s
o
f
all
en
tr
ies
in
th
e
d
ataset,
as
d
en
o
ted
i
n
(
5
)
.
M
A
PE
=
1
∑
(
−
̅
)
2
∗
100
=
1
(
5
)
w
h
er
e
R
2
is
d
en
o
ted
in
(
6
)
.
I
t
co
m
p
ar
es
th
e
r
esid
u
al
s
u
m
o
f
s
q
u
ar
es
(
)
,
(
7
)
,
to
th
e
to
tal
s
u
m
o
f
s
q
u
ar
es
(
)
,
(
8
)
.
T
h
e
to
tal
s
u
m
o
f
s
q
u
ar
es
is
co
m
p
u
ted
b
y
ac
cu
m
u
latin
g
th
e
s
q
u
ar
es
o
f
th
e
p
er
p
en
d
i
cu
lar
in
ter
v
als
b
etwe
en
d
ata
p
o
in
ts
an
d
th
e
a
v
er
ag
e
lin
e.
2
=
1
−
[
]
(
6
)
w
h
e
r
e
=
(
−
̅
)
2
(
7
)
=
∑
(
−
̅
)
2
=
1
(
8
)
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
4
.
1
.
Set
up
T
h
e
ex
p
er
im
e
n
ts
wer
e
co
n
d
u
ct
ed
on
a
PC
with
a
64
-
b
it
W
in
d
o
ws
11
OS
with
an
I
n
tel
7
-
co
r
e
p
r
o
ce
s
s
o
r
r
u
n
n
in
g
at
3
.
2
0
GHz
a
n
d
1
6
GB
R
AM
.
Scik
it
lear
n
s
lib
r
ar
ies
wer
e
u
s
ed
to
im
p
lem
e
n
t
th
e
en
s
em
b
le
lear
n
in
g
an
d
m
ac
h
in
e
lear
n
in
g
m
o
d
els.
T
h
e
u
tili
ze
d
s
o
u
r
ce
co
d
e
an
d
d
ataset
is
p
u
b
licly
av
ailab
le
[
3
6
]
.
4
.
2
.
Resul
t
s
I
n
th
is
s
ec
tio
n
,
we
ev
alu
ate
d
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
all
m
o
d
els
u
s
in
g
v
ar
io
u
s
m
etr
ics,
n
am
el
y
,
MA
PE,
MA
E
,
MSE
,
R
M
SE,
an
d
R
2
.
T
h
e
co
m
p
ar
is
o
n
b
etwe
en
th
e
p
r
o
p
o
s
ed
en
s
em
b
le
lear
n
in
g
m
o
d
els,
ML
m
o
d
els,
an
d
an
ex
is
tin
g
wo
r
k
u
tili
zin
g
a
h
y
b
r
id
C
NN
-
L
STM
m
o
d
el
[
2
5
]
r
ev
ea
le
d
th
at
th
e
en
s
em
b
le
lear
n
in
g
m
o
d
els,
e.
g
.
,
,
,
an
d
p
er
f
o
r
m
b
etter
f
o
r
m
o
s
t
o
f
th
e
d
if
f
er
en
t
s
to
ck
s
.
C
o
n
s
id
er
in
g
th
e
MA
PE
m
etr
ic
to
d
eter
m
in
e
th
e
m
o
s
t
ef
f
ec
tiv
e
alg
o
r
ith
m
,
th
e
lis
ted
MA
PE
v
alu
es
in
T
ab
le
1
s
h
o
w
th
at
t
h
e
T
SLA
d
ataset
is
r
ed
u
ce
d
f
r
o
m
0
.
2
2
f
o
r
th
e
C
NN
-
L
STM
m
o
d
el
[
2
5
]
to
0
.
1
5
f
o
r
th
e
m
o
d
el.
A
d
etailed
r
esu
lts
o
f
th
e
MA
PE,
MA
E
,
an
d
R
2
m
etr
ics
f
o
r
th
e
en
s
em
b
le
lear
n
in
g
m
o
d
els
an
d
th
e
h
y
b
r
i
d
C
NN
-
L
STM
m
o
d
el
[
2
5
]
f
o
r
th
e
T
SLA,
MSFT,
AM
Z
N,
GOOG
,
AM
D,
an
d
NFLX
d
atasets
ar
e
s
h
o
wn
in
T
ab
le
1
.
Usi
n
g
T
SLA,
MSFT,
AM
Z
N,
GOOG
,
an
d
AM
D
d
atasets
a
s
ex
am
p
les,
th
e
b
ar
ch
ar
ts
in
Fig
u
r
e
s
2
an
d
3
s
h
o
w
th
e
c
o
m
p
ar
is
o
n
b
etwe
en
th
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
P
r
ed
ictin
g
s
to
ck
p
r
ices u
s
in
g
en
s
emb
le
lea
r
n
in
g
tech
n
i
q
u
es
(
S
a
lma
E
ls
a
ye
d
)
1789
,
,
an
d
h
y
b
r
id
C
NN
-
L
STM
[
2
5
]
m
o
d
els’
p
er
f
o
r
m
an
ce
b
ased
o
n
th
e
R
MSE
m
etr
ic
an
d
MSE
m
etr
ic.
T
h
e
r
esu
lts
p
r
o
v
ed
th
at
t
h
e
p
r
o
p
o
s
ed
m
o
d
els
p
er
f
o
r
m
b
etter
th
an
th
e
o
th
er
tech
n
iq
u
es
with
m
o
s
t
o
f
th
e
d
atasets
.
T
h
e
v
is
u
al
r
ep
r
esen
tat
io
n
th
r
o
u
g
h
b
ar
ch
ar
ts
en
a
b
le
s
clea
r
co
m
p
ar
is
o
n
o
f
p
er
f
o
r
m
a
n
ce
d
if
f
er
en
ce
s
ac
r
o
s
s
all
test
ed
m
o
d
els an
d
d
ata
s
ets.
T
ab
le
1
.
A
co
m
p
ar
is
o
n
b
etwe
en
d
if
f
er
e
n
t m
o
d
els b
ased
o
n
M
APE,
MA
E
,
an
d
R
2
m
etr
ics f
o
r
m
an
y
s
to
c
k
s
S
t
o
c
k
N
a
m
e
/
m
e
t
r
i
c
e
s
S
t
a
c
k
i
n
gR
e
g
e
s
s
o
r
C
a
tB
o
o
s
tC
l
a
s
s
if
i
e
r
C
a
tB
o
o
s
tR
e
g
r
e
s
s
o
r
B
a
gg
in
gR
e
g
r
e
s
s
o
r
G
r
a
d
i
e
n
tB
o
o
s
t
i
ng
C
N
N
-
L
S
T
M
[
23
]
M
A
P
E
0
.
1
6
9
0
.
2
1
4
0
.
1
5
5
0
.
1
8
3
0
.
1
7
0
0
.
2
2
2
T
S
L
A
M
A
E
R2
4
9
.
1
3
2
-
0
.
6
46
7
4
.
3
1
1
-
2
.
2
60
5
5
.
0
5
0
-
0
.
6
45
6
4
.
4
8
2
-
1
.
4
70
6
0
.
3
0
5
-
1
.
1
49
6
1
.
8
8
1
-
1
.
2
30
M
A
P
E
0
.
0
5
3
0
.
1
3
4
0
.
1
0
5
0
.
1
3
2
0
.
1
1
5
0
.
2
2
7
M
S
F
T
M
A
E
R2
1
6
.
5
1
1
-
0
.
0
70
4
3
.
0
0
7
-
6
.
4
26
3
4
.
3
6
6
-
3
.
7
78
4
2
.
6
0
0
-
6
.
1
72
7
3
.
2
4
5
-
4
.
5
04
5
8
.
6
7
0
-
1
0
.
99
7
M
A
P
E
0
.
1
8
7
0
.
1
6
4
0
.
1
8
4
0
.
1
7
4
0
.
1
7
8
0
.
2
9
3
A
M
Z
N
M
A
E
R2
3
2
.
2
1
0
-
2
9
.
87
7
2
8
.
1
9
5
-
3
3
.
71
3
3
1
.
7
7
4
-
2
9
.
30
1
3
0
.
0
3
8
-
3
1
.
66
6
3
0
.
6
9
3
-
3
0
.
22
3
3
8
.
8
0
3
-
4
5
.
21
7
M
A
P
E
0
.
0
4
2
0
.
1
5
0
0
.
1
1
9
0
.
1
3
5
0
.
1
3
7
0
.
2
0
8
G
O
OG
M
A
E
R2
6
.
2
0
6
-
1
.
3
76
2
1
.
8
2
5
-
2
5
.
79
2
1
7
.
3
0
9
-
1
3
.
17
8
1
9
.
6
3
1
-
1
8
.
21
7
1
9
.
9
1
9
-
1
9
.
26
5
4
2
.
8
4
6
-
2
7
.
25
8
M
A
P
E
0
.
1
4
7
0
.
2
3
0
0
.
1
8
0
0
.
2
0
9
0
.
1
9
9
0
.
2
6
5
A
M
D
M
A
E
R2
2
1
.
2
1
5
-
0
.
9
62
3
1
.
2
6
1
-
3
.
1
77
2
5
.
7
3
4
-
1
.
6
80
2
8
.
9
9
7
-
2
.
4
52
2
7
.
6
9
9
-
2
.
1
41
2
7
.
2
7
8
-
1
.
8
95
M
A
P
E
0
.
2
1
3
0
.
6
1
6
0
.
4
3
9
0
.
4
5
9
0
.
4
9
2
2
.
8
1
4
N
F
L
X
M
A
E
R2
1
3
5
.
8
22
-
6
1
.
59
3
3
9
1
.
7
66
-
5
24
.
4
4
2
9
7
.
4
47
-
2
70
.
8
7
4
2
9
2
.
5
22
-
3
42
.
4
6
8
3
1
3
.
6
70
-
3
68
.
8
6
0
4
6
8
.
6
03
-
7
28
.
3
4
1
Fig
u
r
e
2
.
T
h
e
MSE
v
alu
es f
o
r
v
ar
io
u
s
m
o
d
els
Fig
u
r
e
3
.
T
h
e
R
MSE
v
alu
es f
o
r
v
ar
io
u
s
m
o
d
els
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.
15
,
No
.
2
,
Ap
r
il
20
25
:
1
7
8
3
-
1
7
9
2
1790
I
n
Fig
u
r
e
2
,
th
e
s
tack
in
g
r
eg
r
ess
o
r
g
en
er
ally
o
u
tp
er
f
o
r
m
s
in
ac
cu
r
ac
y
,
as
in
d
icate
d
b
y
lo
wer
MA
PE
v
alu
es
f
o
r
a
m
ajo
r
ity
o
f
th
e
s
to
ck
s
.
T
h
is
s
u
g
g
ests
its
r
o
b
u
s
tn
ess
in
h
an
d
lin
g
f
in
an
cial
d
ata’
s
co
m
p
lex
ities
.
T
h
e
h
ig
h
MA
PE
f
o
r
NFLX
u
n
d
e
r
th
e
h
y
b
r
id
C
NN
-
L
STM
[
2
5
]
m
o
d
el
s
ig
n
als
p
o
te
n
tial
o
v
er
f
itti
n
g
o
r
m
o
d
e
l
in
co
m
p
atib
ilit
y
with
h
ig
h
l
y
v
o
latile
s
to
ck
d
ata.
I
n
Fig
u
r
e
3
,
ag
ain
,
th
e
s
tack
in
g
r
e
g
r
ess
o
r
co
n
s
is
ten
tly
s
h
o
ws
lo
wer
R
MSE
ac
r
o
s
s
al
l
s
to
c
k
s
,
in
d
icatin
g
h
ig
h
e
r
p
r
ed
icti
o
n
ac
cu
r
ac
y
.
I
n
co
n
tr
ast,
th
e
C
atB
o
o
s
t
c
lass
if
ier
ten
d
s
to
ex
h
ib
it
h
ig
h
er
R
MSE
,
p
ar
ticu
lar
ly
f
o
r
T
SLA,
wh
ic
h
co
u
ld
s
u
g
g
est
less
p
r
ed
ictiv
e
r
eliab
ilit
y
f
o
r
th
at
s
to
ck
.
T
h
e
d
etailed
co
m
p
ar
is
o
n
ac
r
o
s
s
d
if
f
er
en
t
s
to
ck
s
s
u
g
g
ests
s
p
ec
if
ic
m
o
d
els
ex
ce
l
in
ce
r
tain
ar
ea
s
;
f
o
r
in
s
tan
ce
,
Stack
in
g
R
eg
r
ess
o
r
g
en
er
ally
o
u
tp
er
f
o
r
m
s
in
ac
c
u
r
ac
y
,
as
in
d
icate
d
b
y
lo
wer
MA
PE
v
alu
es
f
o
r
a
m
ajo
r
ity
o
f
th
e
s
to
ck
s
.
T
h
is
s
u
g
g
ests
its
r
o
b
u
s
tn
ess
in
h
an
d
lin
g
f
in
an
cial
d
ata’
s
co
m
p
lex
i
ties
.
T
h
e
s
tr
ik
in
g
ly
h
ig
h
MA
PE
f
o
r
NFLX
u
n
d
e
r
th
e
h
y
b
r
id
C
NN
-
L
STM
m
o
d
el
[
2
5
]
s
ig
n
als
p
o
ten
tial
o
v
er
f
itti
n
g
o
r
m
o
d
el
in
co
m
p
atib
ilit
y
with
h
ig
h
ly
v
o
latile
s
to
ck
d
ata.
T
h
e
n
eg
ativ
e
R
2
v
al
u
es
ac
r
o
s
s
m
o
d
els
an
d
s
to
ck
s
u
n
d
e
r
s
co
r
e
th
e
ch
allen
g
e
o
f
m
o
d
elin
g
s
to
ck
b
eh
a
v
io
r
ac
c
u
r
ately
,
h
ig
h
li
g
h
tin
g
th
e
f
in
an
cial
m
a
r
k
et’
s
u
n
p
r
e
d
ictab
ilit
y
an
d
th
e
n
ec
ess
ity
f
o
r
s
o
p
h
is
ticated
m
o
d
elin
g
tec
h
n
iq
u
es th
at
ca
n
ad
ap
t to
its
v
o
latile
n
atu
r
e
.
5.
CO
NCLU
SI
O
N
I
n
th
is
wo
r
k
,
we
u
tili
ze
d
e
n
s
em
b
le
lear
n
in
g
m
o
d
els
to
p
r
e
d
ict
th
e
p
r
ices
o
f
2
2
s
to
ck
s
b
ased
o
n
th
e
co
llected
twee
ts
f
r
o
m
th
e
X
s
o
cial
m
ed
ia
p
latf
o
r
m
.
We
p
r
o
p
o
s
ed
m
er
g
in
g
th
e
twee
ts
with
th
e
s
to
ck
clo
s
in
g
p
r
ic
e
ch
an
g
es
in
one
d
ataset
to
be
ab
le
to
p
r
ed
ict
th
e
s
to
ck
p
r
ice
c
h
an
g
e
b
ased
on
th
e
twee
ts
.
Fir
s
t,
we
p
r
ep
r
o
ce
s
s
ed
t
h
e
o
b
t
a
i
n
e
d
t
w
ee
ts
to
e
li
m
i
n
a
te
t
h
e
u
n
s
tr
u
ctu
r
ed
d
a
t
a
.
T
h
e
n
,
w
e
e
x
t
r
ac
t
e
d
t
h
e
t
w
e
et
s
’
p
o
l
a
r
i
ty
w
i
t
h
t
w
o
d
i
f
f
e
r
e
n
t
m
eth
o
d
s
to
en
s
u
r
e
th
e
co
r
r
ec
tn
ess
of
th
e
p
o
lar
ity
.
Nex
t,
we
d
iv
id
ed
th
e
d
ataset
b
ased
on
th
e
s
to
ck
n
am
e
in
to
2
2
d
atasets
.
T
h
en
,
we
u
t
ilized
s
ev
er
al
en
s
em
b
le
lear
n
in
g
m
o
d
els
f
o
r
th
e
p
r
ed
ictiv
e
t
ask
.
T
h
e
p
r
o
p
o
s
ed
en
s
em
b
le
lear
n
in
g
m
o
d
els
wer
e
ev
alu
ated
a
g
ain
s
t
s
ev
er
al
m
ac
h
in
e
lear
n
i
n
g
an
d
d
ee
p
le
ar
n
in
g
m
o
d
els.
Fiv
e
d
if
f
er
en
t
ev
alu
atio
n
m
etr
ics
wer
e
u
tili
ze
d
,
n
am
ely
,
MA
PE,
MA
E
,
MSE
,
R
MSE
,
an
d
R
2
.
T
h
e
ex
p
er
im
e
n
tal
r
esu
lts
o
u
tlin
ed
th
at
th
e
p
r
o
p
o
s
ed
en
s
em
b
le
lear
n
in
g
m
o
d
e
ls
p
er
f
o
r
m
b
etter
th
a
n
th
e
s
tate
-
of
-
th
e
-
a
r
t
m
o
d
el
an
d
th
e
m
ac
h
in
e
lear
n
in
g
m
o
d
els
o
n
av
er
a
g
e
f
o
r
m
o
s
t
s
to
ck
s
.
Fu
r
th
er
m
o
r
e,
th
e
f
in
d
in
g
s
o
f
ev
alu
atio
n
m
etr
ics
s
h
o
wed
th
at
th
e
s
tack
in
g
r
eg
r
ess
o
r
m
o
d
el
o
u
tp
er
f
o
r
m
ed
th
e
o
th
er
m
o
d
els,
as
it
ac
h
iev
ed
th
e
lo
west
MA
PE
v
alu
e.
Fu
tu
r
e
r
esear
c
h
will
co
n
s
id
er
m
e
r
g
in
g
f
in
a
n
cial
s
en
tim
en
t
an
aly
s
is
ap
p
r
o
ac
h
es
with
th
e
p
r
o
p
o
s
ed
m
o
d
el.
RE
F
E
R
E
NC
E
S
[
1
]
R
.
C
h
o
p
r
a
a
n
d
G
.
D
.
S
h
a
r
ma,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
i
n
s
t
o
c
k
m
a
r
k
e
t
f
o
r
e
c
a
s
t
i
n
g
:
A
c
r
i
t
i
q
u
e
,
r
e
v
i
e
w
,
a
n
d
r
e
se
a
r
c
h
a
g
e
n
d
a
,
”
J
o
u
r
n
a
l
o
f
Ri
s
k
a
n
d
Fi
n
a
n
c
i
a
l
M
a
n
a
g
e
m
e
n
t
,
v
o
l
.
1
4
,
n
o
.
1
1
,
N
o
v
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
j
r
f
m
1
4
1
1
0
5
2
6
.
[
2
]
P
a
d
m
a
n
a
y
a
n
a
,
V
a
r
s
h
a
,
a
n
d
B
h
a
v
y
a
K
,
“
S
t
o
c
k
m
a
r
k
e
t
p
r
e
d
i
c
t
i
o
n
u
si
n
g
Tw
i
t
t
e
r
se
n
t
i
m
e
n
t
a
n
a
l
y
s
i
s,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
S
c
i
e
n
t
i
f
i
c
Re
se
a
r
c
h
i
n
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
2
,
n
o
.
1
,
p
p
.
2
6
5
–
2
7
0
,
J
u
l
.
2
0
2
1
,
d
o
i
:
1
0
.
3
2
6
2
8
/
C
S
EI
T2
1
7
4
7
5
.
[
3
]
A
.
M
.
P
r
i
y
a
t
n
o
,
W
.
F
.
R
.
S
u
d
i
r
m
a
n
,
a
n
d
R
.
J
.
M
u
sr
i
d
h
o
,
“
F
e
a
t
u
r
e
se
l
e
c
t
i
o
n
u
s
i
n
g
n
o
n
-
p
a
r
a
me
t
r
i
c
c
o
r
r
e
l
a
t
i
o
n
s
a
n
d
i
mp
o
r
t
a
n
t
f
e
a
t
u
r
e
s
o
n
r
e
c
u
r
si
v
e
f
e
a
t
u
r
e
e
l
i
m
i
n
a
t
i
o
n
f
o
r
st
o
c
k
p
r
i
c
e
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
El
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
4
,
n
o
.
2
,
p
p
.
1
9
0
6
–
1
9
1
5
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
4
i
2
.
p
p
1
9
0
6
-
1
9
1
5
.
[
4
]
Y
.
Q
i
u
,
Z.
S
o
n
g
,
a
n
d
Z.
C
h
e
n
,
“
S
h
o
r
t
-
t
e
r
m
st
o
c
k
t
r
e
n
d
s
p
r
e
d
i
c
t
i
o
n
b
a
s
e
d
o
n
se
n
t
i
me
n
t
a
n
a
l
y
s
i
s
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
6
,
n
o
.
5
,
p
p
.
2
2
0
9
–
2
2
2
4
,
Ja
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
0
0
-
0
2
1
-
0
6
6
0
2
-
7.
[
5
]
R
.
J
.
K
u
o
a
n
d
T.
H
.
C
h
i
u
,
“
H
y
b
r
i
d
o
f
j
e
l
l
y
f
i
s
h
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
-
b
a
s
e
d
s
u
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
f
o
r
s
t
o
c
k
mark
e
t
t
r
e
n
d
p
r
e
d
i
c
t
i
o
n
,
”
Ap
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
5
4
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
s
o
c
.
2
0
2
4
.
1
1
1
3
9
4
.
[
6
]
P
.
C
h
h
a
j
e
r
,
M
.
S
h
a
h
,
a
n
d
A
.
K
sh
i
r
s
a
g
a
r
,
“
Th
e
a
p
p
l
i
c
a
t
i
o
n
s
o
f
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
,
su
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
s,
a
n
d
l
o
n
g
–
sh
o
r
t
t
e
r
m
m
e
mo
r
y
f
o
r
st
o
c
k
ma
r
k
e
t
p
r
e
d
i
c
t
i
o
n
,
”
D
e
c
i
si
o
n
An
a
l
y
t
i
c
s
J
o
u
rn
a
l
,
v
o
l
.
2
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
a
j
o
u
r
.
2
0
2
1
.
1
0
0
0
1
5
.
[
7
]
B
.
K
.
M
e
h
e
r
,
M
.
S
i
n
g
h
,
R
.
B
i
r
a
u
,
a
n
d
A
.
A
n
a
n
d
,
“
F
o
r
e
c
a
s
t
i
n
g
s
t
o
c
k
p
r
i
c
e
s
o
f
f
i
n
t
e
c
h
c
o
m
p
a
n
i
e
s
o
f
I
n
d
i
a
u
si
n
g
r
a
n
d
o
m
f
o
r
e
st
w
i
t
h
h
i
g
h
-
f
r
e
q
u
e
n
c
y
d
a
t
a
,
”
J
o
u
r
n
a
l
o
f
O
p
e
n
I
n
n
o
v
a
t
i
o
n
:
T
e
c
h
n
o
l
o
g
y
,
M
a
rke
t
,
a
n
d
C
o
m
p
l
e
x
i
t
y
,
v
o
l
.
1
0
,
n
o
.
1
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
o
i
t
m
c
.
2
0
2
3
.
1
0
0
1
8
0
.
[
8
]
M
.
A
.
I
st
i
a
k
e
S
u
n
n
y
,
M
.
M
.
S
.
M
a
s
w
o
o
d
,
a
n
d
A
.
G
.
A
l
h
a
r
b
i
,
“
D
e
e
p
l
e
a
r
n
i
n
g
-
b
a
se
d
s
t
o
c
k
p
r
i
c
e
p
r
e
d
i
c
t
i
o
n
u
si
n
g
LS
TM
a
n
d
bi
-
d
i
r
e
c
t
i
o
n
a
l
LS
TM
mo
d
e
l
,
”
i
n
2
n
d
N
o
v
e
l
I
n
t
e
l
l
i
g
e
n
t
a
n
d
L
e
a
d
i
n
g
Em
e
rg
i
n
g
S
c
i
e
n
c
e
s
C
o
n
f
e
r
e
n
c
e
,
N
I
L
E
S
2
0
2
0
,
I
EEE,
O
c
t
.
2
0
2
0
,
p
p
.
8
7
–
9
2
.
d
o
i
:
1
0
.
1
1
0
9
/
N
I
LES5
0
9
4
4
.
2
0
2
0
.
9
2
5
7
9
5
0
.
[
9
]
G
.
M
.
S
i
d
d
e
s
h
,
S
.
R
.
M
.
S
e
k
h
a
r
,
a
n
d
K
.
G
.
S
r
i
n
i
v
a
s
a
,
“
A
l
o
n
g
sh
o
r
t
-
t
e
r
m
mem
o
r
y
n
e
t
w
o
r
k
-
b
a
se
d
a
p
p
r
o
a
c
h
f
o
r
p
r
e
d
i
c
t
i
n
g
t
h
e
t
r
e
n
d
s
i
n
t
h
e
S
&P
5
0
0
i
n
d
e
x
,
”
J
o
u
r
n
a
l
o
f
T
h
e
I
n
st
i
t
u
t
i
o
n
o
f
E
n
g
i
n
e
e
rs
(
I
n
d
i
a
)
:
S
e
ri
e
s
B
,
v
o
l
.
1
0
5
,
n
o
.
1
,
p
p
.
1
9
–
2
6
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
0
0
3
1
-
023
-
0
0
9
5
4
-
4.
[
1
0
]
T.
S
w
a
t
h
i
,
N
.
K
a
s
i
v
i
sw
a
n
a
t
h
,
a
n
d
A
.
A
.
R
a
o
,
“
A
n
o
p
t
i
mal
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
LS
TM
f
o
r
st
o
c
k
p
r
i
c
e
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
t
w
i
t
t
e
r
sen
t
i
m
e
n
t
a
n
a
l
y
si
s
,
”
Ap
p
l
i
e
d
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
5
2
,
n
o
.
1
2
,
p
p
.
1
3
6
7
5
–
1
3
6
8
8
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
4
8
9
-
0
2
2
-
0
3
1
7
5
-
2.
[
1
1
]
J.
Y
a
o
,
“
A
u
t
o
ma
t
e
d
s
e
n
t
i
me
n
t
a
n
a
l
y
s
i
s
o
f
t
e
x
t
d
a
t
a
w
i
t
h
N
LT
K
,
”
J
o
u
r
n
a
l
o
f
P
h
y
s
i
c
s:
C
o
n
f
e
re
n
c
e
S
e
ri
e
s
,
v
o
l
.
1
1
8
7
,
n
o
.
5
,
A
p
r
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/
1
1
8
7
/
5
/
0
5
2
0
2
0
.
[
1
2
]
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
.
[
1
3
]
A
.
H
.
M
o
g
h
a
d
d
a
m,
M
.
H
.
M
o
g
h
a
d
d
a
m,
a
n
d
M
.
Esf
a
n
d
y
a
r
i
,
“
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
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
J
o
u
rn
a
l
o
f
E
c
o
n
o
m
i
c
s
,
F
i
n
a
n
c
e
a
n
d
A
d
m
i
n
i
st
r
a
t
i
v
e
S
c
i
e
n
c
e
,
v
o
l
.
2
1
,
n
o
.
4
1
,
p
p
.
8
9
–
9
3
,
D
e
c
.
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
e
f
a
s.
2
0
1
6
.
0
7
.
0
0
2
.
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
P
r
ed
ictin
g
s
to
ck
p
r
ices u
s
in
g
en
s
emb
le
lea
r
n
in
g
tech
n
i
q
u
es
(
S
a
lma
E
ls
a
ye
d
)
1791
[
1
4
]
F
.
W
.
C
h
r
i
st
a
n
t
o
,
V
.
G
.
U
t
o
mo
,
R
.
P
r
a
t
h
i
v
i
,
a
n
d
C
.
D
e
w
i
,
“
T
h
e
i
m
p
a
c
t
o
f
f
i
n
a
n
c
i
a
l
s
t
a
t
e
m
e
n
t
i
n
t
e
g
r
a
t
i
o
n
i
n
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
st
o
c
k
p
r
i
c
e
p
r
e
d
i
c
t
i
o
n
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
6
,
n
o
.
1
,
p
p
.
3
5
–
4
2
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
5
8
1
5
/
i
j
i
t
c
s.
2
0
2
4
.
0
1
.
0
4
.
[
1
5
]
S
.
R
.
Th
u
m
u
a
n
d
G
.
N
e
l
l
o
r
e
,
“
O
p
t
i
mi
z
e
d
e
n
sem
b
l
e
su
p
p
o
r
t
v
e
c
t
o
r
r
e
g
r
e
ssi
o
n
mo
d
e
l
s
f
o
r
p
r
e
d
i
c
t
i
n
g
st
o
c
k
p
r
i
c
e
s
w
i
t
h
mu
l
t
i
p
l
e
k
e
r
n
e
l
s
,
”
Ac
t
a
I
n
f
o
rm
a
t
i
c
a
Pra
g
e
n
si
a
,
v
o
l
.
1
3
,
n
o
.
1
,
p
p
.
2
4
–
3
7
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
8
2
6
7
/
j
.
a
i
p
.
2
2
6
.
[
1
6
]
Z.
K
h
a
n
,
“
U
se
d
c
a
r
p
r
i
c
e
e
v
a
l
u
a
t
i
o
n
u
si
n
g
t
h
r
e
e
d
i
f
f
e
r
e
n
t
v
a
r
i
a
n
t
s
o
f
l
i
n
e
a
r
r
e
g
r
e
ss
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
C
o
m
p
u
t
a
t
i
o
n
a
l
a
n
d
I
n
n
o
v
a
t
i
v
e
S
c
i
e
n
c
e
s
,
v
o
l
.
1
,
p
p
.
4
0
–
4
9
,
2
0
2
2
.
[
1
7
]
P
.
S
a
d
o
r
sk
y
,
“
A
r
a
n
d
o
m
f
o
r
e
st
s
a
p
p
r
o
a
c
h
t
o
p
r
e
d
i
c
t
i
n
g
c
l
e
a
n
e
n
e
r
g
y
st
o
c
k
p
r
i
c
e
s,
”
J
o
u
r
n
a
l
o
f
Ri
sk
a
n
d
Fi
n
a
n
c
i
a
l
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
1
4
,
n
o
.
2
,
Ja
n
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
j
r
f
m1
4
0
2
0
0
4
8
.
[
1
8
]
E.
G
u
r
e
s
e
n
,
G
.
K
a
y
a
k
u
t
l
u
,
a
n
d
T
.
U
.
D
a
i
m,
“
U
s
i
n
g
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
m
o
d
e
l
s
i
n
st
o
c
k
mar
k
e
t
i
n
d
e
x
p
r
e
d
i
c
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
.
3
8
,
n
o
.
8
,
p
p
.
1
0
3
8
9
–
1
0
3
9
7
,
A
u
g
.
2
0
1
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
1
1
.
0
2
.
0
6
8
.
[
1
9
]
N
.
Tr
i
p
a
t
h
y
,
S
.
K
.
B
a
l
a
b
a
n
t
a
r
a
y
,
S
.
P
a
r
i
d
a
,
a
n
d
S
.
K
.
N
a
y
a
k
,
“
C
r
y
p
t
o
c
u
r
r
e
n
c
y
f
r
a
u
d
d
e
t
e
c
t
i
o
n
t
h
r
o
u
g
h
c
l
a
s
si
f
i
c
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
4
,
n
o
.
3
,
p
p
.
2
9
1
8
–
2
9
2
6
,
J
u
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
4
i
3
.
p
p
2
9
1
8
-
2
9
2
6
.
[
2
0
]
P
.
M
e
h
t
a
,
S
.
P
a
n
d
y
a
,
a
n
d
K
.
K
o
t
e
c
h
a
,
“
H
a
r
v
e
s
t
i
n
g
so
c
i
a
l
m
e
d
i
a
s
e
n
t
i
m
e
n
t
a
n
a
l
y
s
i
s
t
o
e
n
h
a
n
c
e
s
t
o
c
k
mark
e
t
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
,
”
Pe
e
rJ
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
7
,
p
p
.
1
–
2
1
,
A
p
r
.
2
0
2
1
,
d
o
i
:
1
0
.
7
7
1
7
/
p
e
e
r
j
-
c
s.
4
7
6
.
[
2
1
]
N
.
D
a
r
a
p
a
n
e
n
i
e
t
a
l
.
,
“
S
t
o
c
k
p
r
i
c
e
p
r
e
d
i
c
t
i
o
n
u
si
n
g
se
n
t
i
m
e
n
t
a
n
a
l
y
s
i
s
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
I
n
d
i
a
n
mar
k
e
t
s,”
a
rXi
v
:
2
2
0
4
.
0
5
7
8
3
,
A
p
r
.
2
0
2
2
.
[
2
2
]
S
.
P
.
C
h
a
t
z
i
s,
V
.
S
i
a
k
o
u
l
i
s,
A
.
P
e
t
r
o
p
o
u
l
o
s
,
E.
S
t
a
v
r
o
u
l
a
k
i
s
,
a
n
d
N
.
V
l
a
c
h
o
g
i
a
n
n
a
k
i
s,
“
F
o
r
e
c
a
st
i
n
g
s
t
o
c
k
m
a
r
k
e
t
c
r
i
s
i
s
e
v
e
n
t
s
u
si
n
g
d
e
e
p
a
n
d
st
a
t
i
st
i
c
a
l
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
,
”
E
x
p
e
rt
S
y
st
e
m
s
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
1
2
,
p
p
.
3
5
3
–
3
7
1
,
D
e
c
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
1
8
.
0
6
.
0
3
2
.
[
2
3
]
Y
.
H
a
n
,
J.
K
i
m,
a
n
d
D
.
E
n
k
e
,
“
A
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
r
a
d
i
n
g
s
y
s
t
e
m
f
o
r
t
h
e
st
o
c
k
mar
k
e
t
b
a
s
e
d
o
n
N
-
p
e
r
i
o
d
M
i
n
-
M
a
x
l
a
b
e
l
i
n
g
u
si
n
g
X
G
B
o
o
s
t
,
”
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
1
1
,
J
a
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
2
.
1
1
8
5
8
1
.
[
2
4
]
M
.
A
y
i
t
e
y
Ju
n
i
o
r
,
P
.
A
p
p
i
a
h
e
n
e
,
O
.
A
p
p
i
a
h
,
a
n
d
C
.
N
.
B
o
m
b
i
e
,
“
F
o
r
e
x
mark
e
t
f
o
r
e
c
a
s
t
i
n
g
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
:
S
y
s
t
e
m
a
t
i
c
Li
t
e
r
a
t
u
r
e
R
e
v
i
e
w
a
n
d
m
e
t
a
-
a
n
a
l
y
s
i
s,
”
J
o
u
rn
a
l
o
f
B
i
g
D
a
t
a
,
v
o
l
.
1
0
,
n
o
.
1
,
Jan
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
8
6
/
s4
0
5
3
7
-
022
-
0
0
6
7
6
-
2.
[
2
5
]
W
.
A
b
d
u
l
l
a
h
a
n
d
A
.
S
a
l
a
h
,
“
A
n
o
v
e
l
h
y
b
r
i
d
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
f
o
r
p
r
i
c
e
p
r
e
d
i
c
t
i
o
n
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
l
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
3
,
n
o
.
3
,
p
p
.
3
4
2
0
–
3
4
3
1
,
J
u
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
3
i
3
.
p
p
3
4
2
0
-
3
4
3
1
.
[
2
6
]
S
.
Za
h
e
e
r
e
t
a
l
.
,
“
A
m
u
l
t
i
-
p
a
r
a
m
e
t
e
r
f
o
r
e
c
a
st
i
n
g
f
o
r
st
o
c
k
t
i
m
e
s
e
r
i
e
s
d
a
t
a
u
si
n
g
LST
M
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
,
”
M
a
t
h
e
m
a
t
i
c
s
,
v
o
l
.
1
1
,
n
o
.
3
,
Ja
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
ma
t
h
1
1
0
3
0
5
9
0
.
[
2
7
]
Y
.
Z
h
a
o
a
n
d
G
.
Y
a
n
g
,
“
D
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
i
n
t
e
g
r
a
t
e
d
f
r
a
mew
o
r
k
f
o
r
st
o
c
k
p
r
i
c
e
m
o
v
e
me
n
t
p
r
e
d
i
c
t
i
o
n
,
”
A
p
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
3
3
,
J
a
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
s
o
c
.
2
0
2
2
.
1
0
9
9
2
1
.
[
2
8
]
S
.
M
u
k
h
e
r
j
e
e
,
B
.
S
a
d
h
u
k
h
a
n
,
N
.
S
a
r
k
a
r
,
D
.
R
o
y
,
a
n
d
S
.
D
e
,
“
S
t
o
c
k
mar
k
e
t
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
l
g
o
r
i
t
h
ms,
”
C
A
AI
T
ra
n
s
a
c
t
i
o
n
s
o
n
I
n
t
e
l
l
i
g
e
n
c
e
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
8
,
n
o
.
1
,
p
p
.
8
2
–
9
4
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
4
9
/
c
i
t
2
.
1
2
0
5
9
.
[
2
9
]
O
.
A
b
i
o
l
a
,
A
.
A
b
a
y
o
m
i
-
A
l
l
i
,
O
.
A
.
T
a
l
e
,
S
.
M
i
sr
a
,
a
n
d
O
.
A
b
a
y
o
mi
-
A
l
l
i
,
“
S
e
n
t
i
me
n
t
a
n
a
l
y
s
i
s
o
f
C
O
V
I
D
-
1
9
t
w
e
e
t
s
f
r
o
m
se
l
e
c
t
e
d
h
a
s
h
t
a
g
s
i
n
N
i
g
e
r
i
a
u
si
n
g
V
A
D
E
R
a
n
d
T
e
x
t
B
l
o
b
a
n
a
l
y
s
e
r
,
”
J
o
u
r
n
a
l
o
f
El
e
c
t
r
i
c
a
l
S
y
s
t
e
m
s
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
0
,
n
o
.
1
,
J
a
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
3
0
6
7
-
0
2
3
-
0
0
0
7
0
-
9.
[
3
0
]
B
.
A
.
A
b
d
e
l
f
a
t
t
a
h
,
S
.
M
.
D
a
r
w
i
s
h
,
a
n
d
S
.
M
.
El
k
a
f
f
a
s,
“
E
n
h
a
n
c
i
n
g
t
h
e
p
r
e
d
i
c
t
i
o
n
o
f
s
t
o
c
k
m
a
r
k
e
t
m
o
v
e
me
n
t
u
si
n
g
n
e
u
t
r
o
so
p
h
i
c
-
l
o
g
i
c
-
b
a
se
d
se
n
t
i
m
e
n
t
a
n
a
l
y
si
s
,
”
J
o
u
r
n
a
l
o
f
T
h
e
o
r
e
t
i
c
a
l
a
n
d
A
p
p
l
i
e
d
El
e
c
t
r
o
n
i
c
C
o
m
m
e
rc
e
R
e
se
a
rc
h
,
v
o
l
.
1
9
,
n
o
.
1
,
p
p
.
1
1
6
–
1
3
4
,
Jan
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
j
t
a
e
r
1
9
0
1
0
0
0
7
.
[
3
1
]
G
.
S
o
n
k
a
v
d
e
,
D
.
S
.
D
h
a
r
r
a
o
,
A
.
M
.
B
o
n
g
a
l
e
,
S
.
T.
D
e
o
k
a
t
e
,
D
.
D
o
r
e
sw
a
my
,
a
n
d
S
.
K
.
B
h
a
t
,
“
F
o
r
e
c
a
s
t
i
n
g
s
t
o
c
k
mar
k
e
t
p
r
i
c
e
s
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
s:
A
sy
s
t
e
m
a
t
i
c
r
e
v
i
e
w
,
p
e
r
f
o
r
m
a
n
c
e
a
n
a
l
y
si
s,
a
n
d
d
i
s
c
u
ss
i
o
n
o
f
i
m
p
l
i
c
a
t
i
o
n
s
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
F
i
n
a
n
c
i
a
l
S
t
u
d
i
e
s
,
v
o
l
.
1
1
,
n
o
.
3
,
J
u
l
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
i
j
f
s
1
1
0
3
0
0
9
4
.
[
3
2
]
M
.
A
l
i
,
D
.
M
.
K
h
a
n
,
H
.
M
.
A
l
sh
a
n
b
a
r
i
,
a
n
d
A
.
A
.
-
A
.
H
.
E
l
-
B
a
g
o
u
r
y
,
“
P
r
e
d
i
c
t
i
o
n
o
f
c
o
m
p
l
e
x
s
t
o
c
k
m
a
r
k
e
t
d
a
t
a
u
s
i
n
g
a
n
i
m
p
r
o
v
e
d
h
y
b
r
i
d
EM
D
-
LST
M
mo
d
e
l
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
3
,
n
o
.
3
,
Ja
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
3
0
3
1
4
2
9
.
[
3
3
]
R
.
S
i
b
i
n
d
i
,
R
.
W
.
M
w
a
n
g
i
,
a
n
d
A
.
G
.
W
a
i
t
i
t
u
,
“
A
b
o
o
s
t
i
n
g
e
n
sem
b
l
e
l
e
a
r
n
i
n
g
b
a
s
e
d
h
y
b
r
i
d
l
i
g
h
t
g
r
a
d
i
e
n
t
b
o
o
s
t
i
n
g
mac
h
i
n
e
a
n
d
e
x
t
r
e
me
g
r
a
d
i
e
n
t
b
o
o
st
i
n
g
m
o
d
e
l
f
o
r
p
r
e
d
i
c
t
i
n
g
h
o
u
se
p
r
i
c
e
s,
”
En
g
i
n
e
e
ri
n
g
R
e
p
o
r
t
s
,
v
o
l
.
5
,
n
o
.
4
,
N
o
v
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
2
/
e
n
g
2
.
1
2
5
9
9
.
[
3
4
]
E.
M
.
F
e
r
r
o
u
h
i
a
n
d
I
.
B
o
u
a
b
d
a
l
l
a
o
u
i
,
“
A
c
o
mp
a
r
a
t
i
v
e
st
u
d
y
o
f
e
n
s
e
m
b
l
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
s
f
o
r
h
i
g
h
-
f
r
e
q
u
e
n
c
y
t
r
a
d
i
n
g
,
”
S
c
i
e
n
t
i
f
i
c
Af
r
i
c
a
n
,
v
o
l
.
2
4
,
J
u
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
s
c
i
a
f
.
2
0
2
4
.
e
0
2
1
6
1
.
[
3
5
]
A
.
T.
H
a
r
y
o
n
o
,
R
.
S
a
r
n
o
,
a
n
d
K
.
R
.
S
u
n
g
k
o
n
o
,
“
S
t
o
c
k
p
r
i
c
e
f
o
r
e
c
a
st
i
n
g
i
n
I
n
d
o
n
e
s
i
a
s
t
o
c
k
e
x
c
h
a
n
g
e
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
:
A
c
o
m
p
a
r
a
t
i
v
e
st
u
d
y
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
4
,
n
o
.
1
,
p
p
.
8
6
1
–
8
6
9
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
4
i
1
.
p
p
8
6
1
-
8
6
9
.
[
3
6
]
S
t
a
r
s
-
of
-
o
r
i
o
n
,
“
S
t
o
c
k
m
o
v
e
m
e
n
t
p
r
e
d
i
c
t
i
o
n
w
i
t
h
s
e
n
t
i
m
e
n
t
a
n
a
l
y
s
i
s,”
G
i
t
h
u
b
.
A
c
c
e
ss
e
d
:
M
a
r
.
2
3
,
2
0
2
4
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
g
i
t
h
u
b
.
c
o
m/
s
t
a
r
s
-
of
-
o
r
i
o
n
/
s
t
o
c
k
-
mo
v
e
m
e
n
t
-
p
r
e
d
i
c
t
i
o
n
-
w
i
t
h
-
se
n
t
i
me
n
t
-
a
n
a
l
y
si
s
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
S
a
lm
a
Elsa
y
e
d
h
o
l
d
s
a
b
a
c
h
e
lo
r’s
d
e
g
re
e
in
c
o
m
p
u
ters
a
n
d
in
fo
rm
a
ti
o
n
fro
m
Zag
a
z
ig
Un
iv
e
rsity
,
Eg
y
p
t,
2
0
1
6
.
S
h
e
wo
r
k
e
d
a
s
a
tea
c
h
i
n
g
a
ss
istan
t
i
n
t
h
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
t
th
e
F
a
c
u
l
ty
o
f
Co
m
p
u
ters
a
n
d
In
f
o
rm
a
ti
o
n
,
6
Oc
to
b
e
r
Un
i
v
e
rsity
,
Eg
y
p
t
fo
r
2
y
e
a
rs.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
a
rti
ficia
l
in
telli
g
e
n
c
e
,
m
a
c
h
in
e
lea
rn
in
g
,
d
e
e
p
lea
rn
in
g
,
e
n
se
m
b
le
lea
rn
in
g
,
a
n
d
se
n
ti
m
e
n
t
a
n
a
ly
sis.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sa
lma
e
ls
a
ied
4
9
2
@
g
m
a
il
.
c
o
m
.
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.
15
,
No
.
2
,
Ap
r
il
20
25
:
1
7
8
3
-
1
7
9
2
1792
Ahm
a
d
S
a
la
h
re
c
e
iv
e
d
a
P
h
.
D.
d
e
g
re
e
in
c
o
m
p
u
ter
sc
ien
c
e
fro
m
Hu
n
a
n
Un
i
v
e
rsity
,
Ch
in
a
,
in
2
0
1
4
.
He
re
c
e
iv
e
d
a
m
a
ste
r’s
d
e
g
re
e
in
CS
fro
m
Ai
n
-
S
h
a
m
s
Un
iv
e
rsity
,
Ca
iro
,
Eg
y
p
t
,
in
2
0
0
9
.
He
is
c
u
rre
n
tl
y
a
n
a
ss
o
c
iate
p
ro
fe
ss
o
r
o
f
c
o
m
p
u
ter
sc
ien
c
e
a
t
Zag
a
z
ig
Un
i
v
e
rsity
,
Eg
y
p
t.
He
h
a
s
p
u
b
li
s
h
e
d
m
o
re
th
a
n
6
0
p
a
p
e
rs
in
i
n
tern
a
ti
o
n
a
l
p
e
e
r
-
re
v
iew
e
d
jo
u
r
n
a
ls,
su
c
h
a
s
th
e
IEE
E
Tran
sa
c
ti
o
n
s
o
n
P
a
ra
ll
e
l
a
n
d
Distrib
u
ted
S
y
ste
m
s
IEE
E
-
ACM
Tra
n
sa
c
ti
o
n
s
o
n
Co
m
p
u
tati
o
n
a
l
Bi
o
l
o
g
y
Bio
in
f
o
r
m
a
ti
c
s,
a
n
d
ACM
Tran
sa
c
ti
o
n
s
o
n
P
a
ra
ll
e
l
C
o
m
p
u
ti
n
g
.
His
c
u
rre
n
t
re
se
a
rc
h
in
tere
sts
a
re
p
a
ra
ll
e
l
c
o
m
p
u
ti
n
g
,
c
o
m
p
u
tati
o
n
a
l
b
i
o
lo
g
y
,
a
n
d
m
a
c
h
in
e
lea
rn
i
n
g
.
He
can
be
c
o
n
tac
ted
at
a
h
m
a
d
@
z
u
.
e
d
u
.
e
g
.
Ibra
h
im
Elh
e
n
a
wy
re
c
e
iv
e
d
th
e
M
.
S
c
.
a
n
d
P
h
.
D.
d
e
g
re
e
s
i
n
c
o
m
p
u
ter
sc
ien
c
e
fro
m
th
e
S
tate
Un
i
v
e
rsity
of
Ne
w
Yo
rk
,
USA
in
1
9
8
0
a
n
d
1
9
8
3
,
re
sp
e
c
ti
v
e
ly
.
Cu
rre
n
tl
y
,
he
is
a
p
ro
fe
ss
o
r
in
t
h
e
Co
m
p
u
ter
S
c
ien
c
e
De
p
a
rtme
n
t
,
at
Zag
a
z
ig
Un
i
v
e
rsity
.
His
c
u
rre
n
t
re
se
a
rc
h
in
tere
sts
a
re
m
a
th
e
m
a
ti
c
s,
n
e
t
wo
rk
s,
a
rti
f
icia
l
i
n
telli
g
e
n
c
e
,
o
p
ti
m
iza
ti
o
n
,
d
i
g
it
a
l
ima
g
e
p
ro
c
e
ss
in
g
,
a
n
d
p
a
tt
e
rn
re
c
o
g
n
it
io
n
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
h
e
n
a
wy
2
0
0
0
@y
a
h
o
o
.
c
o
m
.
Ma
r
wa
Abd
e
ll
a
h
is
a
lec
tu
re
r
o
f
c
o
m
p
u
ter
sc
ien
c
e
a
t
th
e
Co
m
p
u
ter
S
c
ien
c
e
De
p
a
rtme
n
t,
F
a
c
u
lt
y
of
C
o
m
p
u
ter
s
a
n
d
In
f
o
rm
a
ti
c
s,
Zag
a
z
ig
Un
iv
e
rsity
.
S
h
e
got
h
e
r
M
.
Sc
.
a
n
d
Ph
.
D
.
d
e
g
re
e
s
in
c
o
m
p
u
ter
sc
ien
c
e
fro
m
th
e
F
a
c
u
lt
y
o
f
C
o
m
p
u
ters
a
n
d
I
n
fo
rm
a
ti
c
s,
Za
g
a
z
i
g
Un
iv
e
rsity
i
n
2
0
1
3
a
n
d
2
0
2
0
,
re
s
p
e
c
ti
v
e
ly
.
He
r
a
re
a
of
in
tere
st
in
c
lu
d
e
s
a
rti
ficia
l
in
telli
g
e
n
c
e
a
n
d
m
a
c
h
in
e
lea
rn
i
n
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
m
a
rwa
a
b
d
e
ll
a
2
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.