I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
15
,
No
.
2
,
A
p
r
il
20
26
,
p
p
.
1
2
3
6
~
1
2
4
6
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
2
.
p
p
1
2
3
6
-
1
2
4
6
1236
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Technica
l ana
ly
sis
mo
del f
o
r s
tock
prediction
using
a
g
ra
mm
a
tical ev
o
lution a
lg
o
rithm
Adity
a
K
us
um
a
Set
y
a
neg
a
r
a
,
I
m
a
s
Su
k
a
esih
Sita
ng
g
a
ng
,
M
us
htho
f
a
S
c
h
o
o
l
o
f
D
a
t
a
S
c
i
e
n
c
e
,
M
a
t
h
e
mat
i
c
s
a
n
d
I
n
f
o
r
ma
t
i
c
s,
I
P
B
U
n
i
v
e
r
si
t
y
,
B
o
g
o
r
,
I
n
d
o
n
e
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
11
,
2
0
2
5
R
ev
is
ed
J
an
5
,
2
0
2
6
Acc
ep
ted
J
an
22
,
2
0
2
6
S
to
c
k
s
a
re
a
p
o
p
u
lar
in
v
e
stm
e
n
t
in
str
u
m
e
n
t
b
u
t
c
a
rry
h
ig
h
r
isk
s,
wh
e
r
e
in
v
e
sto
rs
m
a
y
i
n
c
u
r
lo
ss
e
s
wh
e
n
sto
c
k
s
a
re
b
o
u
g
h
t
a
t
h
i
g
h
p
rice
s
a
n
d
so
ld
a
t
lo
we
r
p
rice
s.
Tec
h
n
ica
l
a
n
a
ly
sis
i
s
u
se
d
to
stu
d
y
p
a
st
sto
c
k
p
rice
b
e
h
a
v
io
r
t
o
p
re
d
ict
f
u
tu
re
p
rice
s.
I
n
t
h
i
s
stu
d
y
,
g
ra
m
m
a
ti
c
a
l
e
v
o
lu
ti
o
n
(G
E)
is
a
p
p
li
e
d
a
s
a
n
e
v
o
lu
t
io
n
a
ry
c
o
m
p
u
t
in
g
tec
h
n
i
q
u
e
to
d
isc
o
v
e
r
o
p
t
ima
l
fu
n
c
ti
o
n
s
o
r
p
ro
g
ra
m
s
th
a
t
re
p
re
se
n
t
h
isto
rica
l
sto
c
k
p
rice
d
a
ta.
T
h
is
st
u
d
y
d
e
v
e
lo
p
s
G
E
-
b
a
se
d
p
re
d
icti
o
n
m
o
d
e
ls
b
y
u
ti
li
z
in
g
o
b
jec
ti
v
e
f
u
n
c
ti
o
n
s
a
n
d
se
a
r
c
h
sp
a
c
e
s
d
e
fin
e
d
th
r
o
u
g
h
g
ra
m
m
a
r.
T
h
e
m
o
d
e
l
i
n
teg
ra
tes
tec
h
n
ica
l
in
d
ica
to
rs
b
a
se
d
o
n
c
o
m
p
le
x
sta
ti
stica
l
m
o
d
e
ls
su
c
h
a
s
a
u
to
re
g
re
ss
iv
e
in
te
g
ra
ted
m
o
v
i
n
g
a
v
e
ra
g
e
(
ARIMA
)
,
p
ro
p
h
e
t,
e
x
p
o
n
e
n
ti
a
l
sm
o
o
th
i
n
g
,
a
n
d
F
ib
o
n
a
c
c
i
re
trac
e
m
e
n
ts
.
F
u
r
th
e
rm
o
re
,
th
is
stu
d
y
e
m
p
lo
y
s
G
E
to
g
e
n
e
ra
te
e
n
se
m
b
le
we
ig
h
ts
ra
n
d
o
m
l
y
,
e
n
s
u
rin
g
e
a
c
h
m
o
d
e
l
c
o
n
tri
b
u
tes
e
q
u
it
a
b
l
y
t
o
th
e
fin
a
l
p
re
d
ictio
n
fo
rm
u
la.
E
x
p
e
rime
n
t
s
we
re
c
o
n
d
u
c
ted
u
si
n
g
m
u
l
ti
p
le
st
o
c
k
d
a
tas
e
ts,
in
c
lu
d
in
g
S
M
AR,
S
&
P
5
0
0
,
th
e
Jo
h
a
n
n
e
sb
u
r
g
S
t
o
c
k
Ex
c
h
a
n
g
e
(JSE
)
,
t
h
e
Ne
w
Yo
rk
S
t
o
c
k
E
x
c
h
a
n
g
e
(NY
S
E)
,
a
n
d
A
d
a
n
i
E
n
terp
rise
s
(AD
AN
IENT
)
,
to
e
v
a
lu
a
te
th
e
m
o
d
e
l’s
a
d
a
p
tab
il
it
y
a
n
d
g
e
n
e
ra
li
z
a
ti
o
n
c
a
p
a
b
il
it
y
.
Th
e
re
su
lt
s
d
e
m
o
n
stra
te
th
a
t
th
e
p
ro
p
o
se
d
G
E
m
o
d
e
l
e
ffe
c
ti
v
e
ly
c
a
p
tu
re
s
c
o
m
p
lex
m
a
rk
e
t
p
a
tt
e
r
n
s
a
n
d
p
r
o
d
u
c
e
s
m
o
re
re
li
a
b
le
s
to
c
k
p
rice
p
re
d
ictio
n
s
c
o
m
p
a
re
d
to
d
e
e
p
lea
rn
in
g
-
b
a
se
d
a
p
p
r
o
a
c
h
e
s.
Alth
o
u
g
h
G
E
re
q
u
ires
g
re
a
ter
c
o
m
p
u
tat
io
n
a
l
ti
m
e
,
th
e
fin
d
in
g
s
su
g
g
e
st
th
a
t
G
E
p
ro
v
id
e
s
a
flex
ib
le
a
n
d
e
ffe
c
ti
v
e
fra
m
e
wo
rk
fo
r
c
o
n
stru
c
ti
n
g
h
y
b
rid
st
o
c
k
p
rice
fo
re
c
a
stin
g
m
o
d
e
ls i
n
d
y
n
a
m
ic m
a
rk
e
t
e
n
v
ir
o
n
m
e
n
ts.
K
ey
w
o
r
d
s
:
AR
I
MA
E
x
p
o
n
e
n
tial sm
o
o
th
in
g
Fib
o
n
ac
ci
r
etr
ac
em
en
ts
Gr
am
m
atica
l e
v
o
lu
tio
n
Pro
p
h
et
T
ec
h
n
ical
an
aly
s
is
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
:
I
m
as Su
k
ae
s
ih
Sit
an
g
g
an
g
Sch
o
o
l o
f
Data
Scien
ce
,
Ma
t
h
em
atics a
n
d
I
n
f
o
r
m
atics,
I
PB
Un
iv
er
s
ity
,
B
o
g
o
r
,
I
n
d
o
n
esia
St
.
Me
r
an
ti W
in
g
2
0
L
ev
el
V,
B
o
g
o
r
-
1
6
6
8
0
,
I
n
d
o
n
esia
E
m
ail: im
as.si
tan
g
g
an
g
@
ap
p
s
.
ip
b
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
Sto
ck
s
ca
n
r
e
p
r
esen
t
a
n
in
d
iv
id
u
al
’
s
o
r
an
en
tity
’
s
o
w
n
er
s
h
ip
in
a
c
o
m
p
an
y
o
r
a
lim
ited
liab
ilit
y
co
r
p
o
r
atio
n
.
I
n
t
h
is
co
n
tex
t,
f
in
an
cial
an
aly
s
ts
ap
p
ly
f
u
n
d
a
m
en
tal
an
d
tech
n
ical
an
aly
s
is
,
s
tatis
t
ical
ex
p
er
ts
f
o
cu
s
o
n
tim
e
s
er
ies an
aly
s
is
,
an
d
co
m
p
u
ter
s
cien
ce
r
esear
ch
er
s
ad
o
p
t m
ac
h
i
n
e
lear
n
in
g
ap
p
r
o
ac
h
es [
1
]
.
Sto
c
k
in
v
esto
r
s
ty
p
ically
co
n
d
u
ct
in
-
d
ep
th
an
aly
s
is
b
ef
o
r
e
ex
ec
u
tin
g
tr
an
s
ac
tio
n
s
to
m
ax
im
ize
p
r
o
f
its
an
d
m
in
im
iz
e
lo
s
s
es
to
m
ax
im
ize
p
r
o
f
its
an
d
m
in
im
ize
lo
s
s
es.
T
ec
h
n
ical
an
aly
s
is
is
a
co
m
m
o
n
ly
ap
p
lie
d
m
eth
o
d
th
at
r
ests
o
n
th
e
b
elief
th
at
p
ast
m
ar
k
et
m
o
v
em
en
ts
ar
e
lik
el
y
to
r
ea
p
p
ea
r
,
as
h
u
m
an
b
eh
av
io
r
ten
d
s
to
b
e
co
n
s
is
ten
t
ac
r
o
s
s
s
im
ilar
s
itu
atio
n
s
.
As a
r
esu
lt,
t
r
en
d
s
an
d
p
r
ice
p
atter
n
s
ar
e
v
iewe
d
as f
r
ac
tal
in
n
at
u
r
e
[
2
]
.
Sev
er
al
s
tu
d
ies
h
av
e
u
s
ed
g
r
am
m
atica
l
ev
o
lu
tio
n
(
GE
)
to
d
ev
elo
p
s
tr
ateg
ies
f
o
r
p
r
e
d
ic
tin
g
s
to
ck
p
r
ice
m
o
v
em
en
ts
,
a
m
o
n
g
th
e
m
[
3
]
−
[
9
]
.
Me
g
an
e
et
a
l.
[
4
]
in
tr
o
d
u
ce
d
p
r
o
b
ab
ilis
tic
s
tr
u
ctu
r
ed
g
r
am
m
at
ical
ev
o
lu
tio
n
(
PS
GE
)
,
co
m
b
i
n
in
g
s
tr
u
ctu
r
ed
g
r
am
m
atica
l
e
v
o
lu
tio
n
(
SGE)
an
d
p
r
o
b
a
b
ilis
tic
g
r
am
m
atica
l
ev
o
lu
tio
n
(
PGE)
to
g
u
id
e
r
u
le
s
elec
tio
n
u
s
in
g
p
r
o
b
ab
ilis
tic
g
r
am
m
ar
u
p
d
ates,
s
h
o
win
g
im
p
r
o
v
ed
p
er
f
o
r
m
an
ce
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Tech
n
ica
l a
n
a
lysi
s
mo
d
el
fo
r
s
to
ck
p
r
ed
ictio
n
u
s
in
g
a
g
r
a
mm
a
tica
l
…
(
A
d
itya
K
u
s
u
ma
S
etya
n
eg
a
r
a
)
1237
o
v
er
GE
an
d
PGE
b
u
t
n
o
t
c
o
n
s
is
ten
tly
o
u
tp
er
f
o
r
m
i
n
g
SGE
.
Me
an
wh
ile
,
Pawlak
an
d
O’
Neill
[
7
]
in
t
r
o
d
u
ce
d
th
e
g
r
am
m
atica
l
ev
o
lu
tio
n
f
o
r
co
n
s
tr
ain
t
s
y
n
th
esis
(
GE
C
S
)
alg
o
r
ith
m
to
au
to
m
ate
co
n
s
tr
ain
t
s
y
n
th
esis
in
m
ix
ed
-
in
teg
e
r
lin
ea
r
p
r
o
g
r
am
m
in
g
(
M
I
L
P
)
m
o
d
els
u
s
in
g
GE
an
d
Z
u
s
e
I
n
s
titu
te
Ma
th
em
atica
l
Pro
g
r
am
m
in
g
L
an
g
u
ag
e
(
Z
I
MPL
)
g
r
am
m
a
r
.
Ho
wev
er
,
it
i
s
ef
f
ec
tiv
en
ess
d
ep
en
d
s
h
ea
v
ily
o
n
th
e
co
m
p
let
en
ess
o
f
in
p
u
t
d
ata
an
d
m
a
y
s
till
r
eq
u
ir
e
iter
ativ
e
r
ef
in
em
e
n
t
[
7
]
.
Ad
d
itio
n
all
y
,
R
y
an
et
a
l.
[
1
0
]
co
m
p
ar
ed
v
ar
io
u
s
s
m
o
o
th
in
g
m
eth
o
d
s
,
in
cl
u
d
in
g
m
o
v
in
g
av
er
ag
e
an
d
e
x
p
o
n
en
tial
s
m
o
o
t
h
in
g
,
a
n
d
s
u
g
g
ested
th
at
co
m
b
in
in
g
au
t
o
r
eg
r
ess
iv
e
in
teg
r
ated
m
o
v
in
g
a
v
er
ag
e
(
A
R
I
MA
)
with
ex
p
o
n
en
tial sm
o
o
th
in
g
c
o
u
ld
e
n
h
an
ce
t
h
eir
m
o
d
el
’
s
ef
f
ec
tiv
en
ess
.
R
ec
en
t
s
tu
d
ies
h
av
e
in
cr
e
asin
g
ly
in
v
esti
g
ated
n
eu
r
al
f
o
r
ec
a
s
tin
g
an
d
h
y
b
r
id
e
n
s
em
b
le
a
p
p
r
o
ac
h
es
f
o
r
s
to
ck
p
r
ice
p
r
e
d
ictio
n
,
in
clu
d
in
g
h
y
b
r
id
AR
I
MA
–
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
m
o
d
els
an
d
t
r
an
s
f
o
r
m
er
-
b
ased
ap
p
r
o
ac
h
e
s
f
o
r
tim
e
s
er
ies
f
o
r
ec
asti
n
g
,
alo
n
g
with
p
er
f
o
r
m
an
ce
c
o
m
p
ar
i
s
o
n
s
ag
ain
s
t
ad
v
an
ce
d
d
ee
p
lear
n
in
g
ar
c
h
itectu
r
es
lik
e
tem
p
o
r
al
f
u
s
io
n
tr
an
s
f
o
r
m
er
s
(
T
FT)
,
N
-
B
E
AT
S,
an
d
in
f
o
r
m
er
.
Nti
et
a
l.
[
1
1
]
ev
alu
ate
d
en
s
e
m
b
le
lear
n
in
g
m
et
h
o
d
s
b
ag
g
i
n
g
,
b
o
o
s
tin
g
,
s
tack
in
g
,
a
n
d
b
len
d
in
g
u
s
in
g
d
ec
is
io
n
tr
ee
(
DT
)
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM
)
,
an
d
n
eu
r
al
n
etwo
r
k
m
o
d
els
o
n
s
to
ck
d
ata
f
r
o
m
m
u
ltip
le
ex
ch
an
g
es,
f
in
d
in
g
th
at
s
tac
k
in
g
an
d
b
len
d
in
g
ac
h
iev
e
d
h
ig
h
er
p
r
ed
ictiv
e
ac
cu
r
ac
y
b
u
t
in
cu
r
r
ed
h
ig
h
co
m
p
u
tatio
n
al
co
s
ts
an
d
ex
h
ib
ited
d
ep
en
d
en
ce
o
n
d
ataset
ch
ar
ac
ter
is
tics
.
T
h
en
,
Ag
g
r
awa
l
an
d
D
h
awa
n
[
1
2
]
c
o
m
p
a
r
e
d
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
ls
(
T
F
T
,
N
-
B
E
A
T
S
,
te
m
p
o
r
a
l
co
n
v
o
l
u
t
i
o
n
n
e
t
w
o
r
k
(
T
C
N
)
)
wit
h
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
s
(
GR
U
)
f
o
r
s
h
o
r
t
-
t
e
r
m
p
r
e
d
i
c
t
i
o
n
,
r
e
v
e
a
li
n
g
t
h
a
t
L
S
T
M
a
n
d
G
R
U
w
e
r
e
m
o
r
e
s
t
a
b
l
e
a
n
d
a
c
c
u
r
a
te
,
w
h
i
l
e
n
e
we
r
a
r
c
h
i
t
ec
t
u
r
e
s
s
t
r
u
g
g
l
e
d
t
o
g
e
n
e
r
a
l
i
z
e
ac
r
o
s
s
m
u
l
t
i
v
a
r
i
a
te
d
a
t
a
.
S
u
b
s
e
q
u
e
n
tl
y
,
L
i
a
n
d
P
a
n
[
1
3
]
p
r
o
p
o
s
ed
a
b
len
d
in
g
en
s
em
b
le
co
m
b
in
in
g
L
STM
an
d
GR
U
with
a
f
u
lly
co
n
n
ec
ted
n
eu
r
al
n
etwo
r
k
m
eta
-
lear
n
er
,
u
s
in
g
q
u
an
titat
iv
e
an
d
s
en
tim
en
t
-
b
ased
i
n
f
o
r
m
atio
n
f
r
o
m
f
in
a
n
cial
n
e
ws
to
p
r
ed
ict
th
e
S&
P
5
0
0
.
Ho
wev
er
,
th
ei
r
m
o
d
el
was
lim
ited
b
y
th
e
s
h
o
r
t
s
ix
-
m
o
n
t
h
d
ataset
an
d
it
i
s
f
o
cu
s
o
n
a
s
in
g
le
in
d
ex
.
Me
an
wh
ile,
Ab
d
u
lr
a
h
m
an
et
a
l.
[
1
4
]
p
r
o
p
o
s
ed
a
h
y
b
r
i
d
AR
I
MA
-
L
STM
m
o
d
el
en
h
an
ce
d
b
y
d
is
cr
ete
Fo
u
r
ier
tr
an
s
f
o
r
m
(
DFT
)
d
ec
o
m
p
o
s
iti
o
n
to
s
ep
ar
ate
lin
ea
r
an
d
n
o
n
l
in
ea
r
co
m
p
o
n
en
ts
,
ac
h
iev
in
g
i
m
p
r
o
v
e
d
ac
cu
r
ac
y
o
v
er
s
tan
d
alo
n
e
m
o
d
els b
u
t la
ck
in
g
s
tatis
tical
v
alid
atio
n
an
d
cr
o
s
s
-
m
ar
k
et
test
in
g
.
GE
r
ep
r
esen
ts
a
p
r
o
m
is
in
g
b
r
a
n
ch
o
f
g
en
etic
p
r
o
g
r
a
m
m
in
g
t
h
at
em
p
lo
y
s
an
e
v
o
lu
tio
n
ar
y
a
lg
o
r
ith
m
–
b
ased
s
ea
r
ch
m
ec
h
an
is
m
to
g
eth
er
with
d
o
m
ain
-
s
p
ec
if
ic
g
r
am
m
ar
s
p
ec
if
icatio
n
s
ex
p
r
ess
ed
in
B
ac
k
u
s
-
Nau
r
f
o
r
m
(
B
NF)
to
g
e
n
er
ate
s
y
m
b
o
lic
ex
p
r
ess
io
n
s
[
3
]
.
T
h
is
r
esear
ch
aim
s
to
im
p
lem
en
t
AR
I
MA
,
p
r
o
p
h
et,
ex
p
o
n
e
n
tial
s
m
o
o
th
in
g
,
an
d
Fib
o
n
ac
ci
r
etr
ac
em
e
n
ts
m
eth
o
d
s
with
in
th
e
GE
al
g
o
r
ith
m
to
p
r
o
d
u
ce
m
o
r
e
co
m
p
lex
an
d
ac
cu
r
ate
tech
n
ic
al
an
aly
s
is
in
d
icato
r
s
.
T
h
is
s
t
u
d
y
is
ex
p
ec
ted
to
p
r
o
v
id
e
s
ig
n
if
ican
t
b
en
e
f
its
in
co
n
f
ir
m
in
g
th
e
ef
f
ec
tiv
e
n
ess
o
f
GE
as
a
to
o
l
f
o
r
g
en
e
r
a
tin
g
in
n
o
v
ativ
e
s
to
ck
in
d
icato
r
s
an
d
cr
e
atin
g
a
h
ig
h
er
-
ac
c
u
r
ac
y
s
to
ck
p
r
ed
ict
io
n
s
y
s
tem
cr
ea
tin
g
a
h
ig
h
e
r
ac
cu
r
ac
y
s
to
ck
p
r
ed
ictio
n
s
y
s
tem
.
Mo
r
eo
v
e
r
,
th
e
f
in
d
in
g
s
f
r
o
m
th
is
r
esear
c
h
o
p
en
s
a
v
en
u
es
f
o
r
f
u
r
th
er
in
-
d
ep
th
r
esear
ch
in
d
ev
elo
p
in
g
m
o
r
e
r
o
b
u
s
t
an
d
ac
cu
r
ate
s
to
ck
p
r
e
d
ictio
n
s
y
s
tem
s
.
2.
ME
T
H
O
D
T
h
is
ch
ap
ter
d
is
cu
s
s
es
th
e
m
eth
o
d
o
l
o
g
y
f
o
r
d
esig
n
in
g
a
tech
n
ical
an
aly
s
is
m
o
d
el
f
o
r
s
to
ck
p
r
ed
ictio
n
s
y
s
tem
s
u
s
in
g
t
h
e
GE
alg
o
r
ith
m
.
T
h
e
m
eth
o
d
o
lo
g
ical
f
r
a
m
ewo
r
k
d
etails
th
e
r
esear
ch
p
r
o
ce
s
s
,
wh
ich
in
clu
d
es
d
ata
co
llectio
n
,
p
r
ep
r
o
ce
s
s
in
g
,
m
o
d
el
co
n
s
tr
u
ctio
n
,
tr
ain
i
n
g
a
n
d
test
in
g
p
h
ases
,
an
d
th
e
ev
alu
atio
n
an
d
an
aly
s
is
o
f
t
h
e
o
b
tain
ed
r
esu
lts
.
T
h
r
o
u
g
h
t
h
ese
s
tag
es,
th
e
r
esear
ch
m
eth
o
d
o
lo
g
y
p
r
o
v
id
es
a
co
m
p
r
eh
e
n
s
iv
e
g
u
id
e
f
o
r
d
esig
n
in
g
,
tr
ain
in
g
,
an
d
test
in
g
a
t
ec
h
n
ical
an
aly
s
is
m
o
d
el
u
s
in
g
th
e
GE
alg
o
r
it
h
m
.
Fig
u
r
e
1
p
r
esen
ts
r
esear
ch
s
tag
es d
iag
r
am
,
s
u
m
m
ar
izin
g
s
te
p
s
f
r
o
m
d
ata
co
llectio
n
to
p
er
f
o
r
m
an
ce
a
n
aly
s
is
.
T
h
is
r
esear
ch
is
b
ased
o
n
s
to
ck
d
ata
f
r
o
m
PT
Sin
ar
Ma
s
Ag
r
o
R
eso
u
r
ce
s
an
d
T
ec
h
n
o
lo
g
y
(
PT
SMART
T
b
k
)
with
th
e
s
to
ck
co
d
e
SMAR.J
K,
s
o
u
r
ce
d
f
r
o
m
Ya
h
o
o
Fin
an
ce
,
co
v
e
r
s
J
an
u
ar
y
2
0
2
2
to
J
an
u
ar
y
2
0
2
3
.
T
h
e
d
ata
u
s
ed
i
s
th
e
clo
s
in
g
p
r
ice
(
clo
s
e
p
r
ic
e)
o
f
th
e
s
to
ck
,
as
it
is
co
n
s
id
er
ed
th
e
m
o
s
t
s
tab
le
an
d
wid
ely
r
ef
er
e
n
ce
d
p
r
ice
t
h
at
r
ef
lects
m
ar
k
et
c
o
n
s
en
s
u
s
at
th
e
en
d
o
f
ea
c
h
tr
ad
i
n
g
d
ay
.
T
h
is
r
esear
ch
wi
ll
f
o
cu
s
o
n
d
ev
elo
p
in
g
a
c
o
m
p
r
eh
en
s
iv
e
p
r
ed
ictio
n
m
o
d
el
b
u
t
n
ee
d
s
to
in
clu
d
e
t
h
e
p
r
ac
tica
l
ap
p
licatio
n
o
f
t
h
e
m
o
d
el
its
elf
.
I
n
th
e
p
r
ep
r
o
ce
s
s
in
g
s
tag
e,
a
m
in
–
m
ax
s
ca
lin
g
ap
p
r
o
ac
h
is
em
p
lo
y
ed
to
n
o
r
m
alize
th
e
d
ata,
wh
er
e
f
ea
tu
r
e
v
alu
es
ar
e
m
ap
p
e
d
in
to
th
e
[
0
,
1
]
in
ter
v
al.
Featu
r
e
n
o
r
m
aliza
tio
n
is
n
ee
d
ed
to
eli
m
in
ate
th
e
ef
f
ec
t
o
f
s
ev
er
al
q
u
a
n
titativ
e
f
ea
tu
r
es
m
ea
s
u
r
ed
o
n
d
if
f
er
e
n
t
s
ca
les
[
1
5
]
.
T
h
e
d
ataset
is
p
ar
titi
o
n
e
d
in
to
two
s
u
b
s
ets,
with
8
0
%
allo
ca
ted
f
o
r
tr
ain
i
n
g
(
f
r
o
m
J
an
u
ar
y
1
,
2
0
2
0
to
J
an
u
ar
y
1
4
,
2
0
2
3
)
a
n
d
2
0
%
allo
ca
ted
f
o
r
test
in
g
(
f
r
o
m
J
an
u
ar
y
1
5
,
2
0
2
3
to
Octo
b
er
3
1
,
2
0
2
3
)
.
T
h
e
tr
ain
in
g
d
ata
h
elp
s
th
e
m
o
d
el
r
ec
o
g
n
ize
p
atter
n
s
,
wh
ile
t
h
e
test
in
g
d
ata
ev
alu
ates its
p
r
ed
i
ctiv
e
ac
cu
r
ac
y
.
T
h
e
B
NF
g
r
am
m
ar
is
d
esig
n
ed
to
d
ef
in
e
th
e
s
y
n
tactic
r
u
l
es
th
at
s
h
ap
e
p
o
ten
tial
p
r
o
g
r
am
s
in
th
e
p
o
p
u
latio
n
[
1
6
]
.
T
h
is
i
n
clu
d
es
b
asic
o
p
er
at
o
r
s
,
m
at
h
em
a
tical
f
u
n
ctio
n
s
,
an
d
f
ea
tu
r
es
s
u
ch
as
AR
I
MA
,
p
r
o
p
h
et,
ex
p
o
n
en
tial
s
m
o
o
th
i
n
g
,
an
d
Fib
o
n
ac
ci
r
etr
ac
em
e
n
ts
.
T
h
e
g
r
am
m
atica
l
r
u
les
h
elp
s
tr
u
ctu
r
e
th
e
f
u
n
ctio
n
s
cr
ea
ted
by
GE
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
26
:
1
2
3
6
-
1
2
4
6
1238
Fig
u
r
e
1
.
R
esear
ch
s
tag
es d
iag
r
am
T
h
is
s
tu
d
y
em
p
lo
y
s
two
B
N
F
,
th
e
f
ir
s
t
B
NF
i
s
u
tili
ze
d
f
o
r
p
r
ep
r
o
ce
s
s
in
g
s
to
ck
d
ata
b
y
co
n
v
er
tin
g
th
e
r
aw
d
ata
in
t
o
a
s
tr
u
ctu
r
e
d
f
o
r
m
th
at
is
ap
p
r
o
p
r
iate
f
o
r
an
aly
tical
p
u
r
p
o
s
es.
Ad
d
iti
o
n
ally
,
th
is
B
NF
is
d
esig
n
ed
to
r
e
d
u
ce
n
o
is
e
in
h
i
g
h
ly
v
o
latile
d
ata,
th
er
e
b
y
im
p
r
o
v
in
g
d
ata
q
u
ality
an
d
s
u
p
p
o
r
tin
g
m
o
r
e
ac
cu
r
ate
p
r
ed
ictio
n
s
.
T
h
e
d
etailed
d
esig
n
o
f
th
e
f
ir
s
t BNF
is
p
r
esen
ted
in
T
ab
le
1
.
T
h
e
s
ec
o
n
d
B
NF
is
d
ev
elo
p
e
d
to
co
n
s
tr
u
ct
p
r
ed
ictiv
e
m
o
d
els
b
y
in
teg
r
ati
n
g
m
u
ltip
le
f
o
r
ec
asti
n
g
m
eth
o
d
s
,
i
n
clu
d
in
g
AR
I
MA
,
p
r
o
p
h
et,
e
x
p
o
n
en
tial
s
m
o
o
t
h
i
n
g
,
a
n
d
Fib
o
n
ac
ci
r
etr
ac
em
e
n
ts
.
T
h
is
in
teg
r
atio
n
aim
s
to
p
r
o
d
u
ce
a
r
o
b
u
s
t
an
d
ad
ap
tiv
e
m
o
d
el
ca
p
a
b
le
o
f
h
a
n
d
lin
g
co
m
p
lex
s
to
ck
d
ata
p
at
ter
n
s
.
T
h
e
d
etailed
d
esig
n
o
f
th
e
s
ec
o
n
d
B
N
F
is
p
r
esen
ted
in
T
ab
le
2
.
T
h
e
s
tu
d
y
is
co
n
d
u
cted
u
n
d
e
r
two
p
r
im
a
r
y
s
ce
n
ar
io
s
: u
s
in
g
o
n
ly
th
e
s
ec
o
n
d
B
NF a
n
d
co
m
b
in
in
g
b
o
th
B
NFs
to
o
p
tim
ize
th
e
an
aly
s
is
an
d
p
r
e
d
ictio
n
p
r
o
ce
s
s
.
T
ab
le
1
.
B
ac
k
u
s
-
N
au
r
f
o
r
m
d
a
ta
tr
an
s
f
o
r
m
atio
n
T
ab
le
2
.
B
ac
k
u
s
-
N
au
r
f
o
r
m
f
o
r
ec
asti
n
g
m
o
d
el
N
o
n
-
t
e
r
mi
n
a
l
P
r
o
d
u
c
t
i
o
n
r
u
l
e
s
<
st
a
r
t
>
:=
<
e
x
p
r
e
ss
i
o
n
>
<
e
x
p
r
e
ss
i
o
n
>
:=
<
e
x
p
r
e
ss
i
o
n
>
<
o
p
e
r
a
t
o
r
>
<
e
x
p
r
e
ssi
o
n
>
|
<
v
a
r
i
a
b
l
e
>
|
(
0
.
<
d
i
g
i
t
>
*
<
a
r
i
ma
>
)
|
(
0
.
<
d
i
g
i
t
>
*
<
p
r
o
p
h
e
t
>
)
|
(
0
.
<
d
i
g
i
t
>
*
<
e
x
p
sm
o
o
t
h
>
)
|
<
f
i
b
o
n
a
c
c
i
>
<
o
p
e
r
a
t
o
r
>
:=
+
|
-
<
v
a
r
i
a
b
l
e
>
:=
y
t
-
<
c
o
ns
t
a
n
t
>
<
c
o
n
s
t
a
n
t
>
:=
0
|
<
d
i
g
i
t
>
|
<
d
i
g
i
t
>
<
c
o
n
st
a
n
t
>
<
d
i
g
i
t
>
:=
1
|
2
|
3
|
4
|
5
|
6
|
7
|
8
|
9
<
a
r
i
m
a
>
:=
A
R
I
M
A
(
[
d
a
t
a
_
t
r
a
i
n
]
,
[
d
a
t
a
_
t
e
st
_
l
e
n
g
t
h
]
,
[
d
a
y
s_
i
n
t
e
r
v
a
l
]
,
<
d
i
g
i
t
>
,
<
d
i
g
i
t
>
,
<
d
i
g
i
t
>
)
<
p
r
o
p
h
e
t
>
:=
P
r
o
p
h
e
t
(
[
d
a
t
a
_
t
r
a
i
n
]
,
[
d
a
t
a
_
t
e
s
t
_
l
e
n
g
t
h
]
)
<
e
x
p
sm
o
o
t
h
>
:=
Ex
p
S
mo
o
t
h
i
n
g
(
[
d
a
t
a
_
t
r
a
i
n
]
,
[
d
a
t
a
_
t
e
st
_
l
e
n
]
,
0
.
<
d
i
g
i
t
>
,
0
.
<
d
i
g
i
t
>
)
<
f
i
b
o
n
a
c
c
i
>
:=
F
i
b
R
e
t
r
a
c
e
me
n
t
s(
[
d
a
t
a
_
t
r
a
i
n
]
,
<
c
o
n
st
a
n
t
>
,
<
c
o
n
st
a
n
t
>
,
<
c
o
n
s
t
a
n
t
>
)
Mo
d
el
co
n
s
tr
u
ctio
n
in
v
o
l
v
es in
itializin
g
th
e
p
o
p
u
latio
n
,
tr
a
n
s
latin
g
ch
r
o
m
o
s
o
m
es,
ev
al
u
atin
g
f
itn
ess
,
an
d
ap
p
ly
in
g
g
en
etic
o
p
er
at
o
r
s
s
u
ch
as
cr
o
s
s
o
v
er
an
d
m
u
tatio
n
to
p
r
o
d
u
ce
n
ew
g
e
n
er
ati
o
n
s
.
T
h
e
tr
an
s
lated
ch
r
o
m
o
s
o
m
es
ar
e
r
ep
r
esen
ted
as
f
u
n
ctio
n
s
an
d
ass
e
s
s
ed
u
s
in
g
r
o
o
t
m
ea
n
s
q
u
ar
e
er
r
o
r
(
R
MSE
)
to
m
ea
s
u
r
e
N
o
n
-
t
e
r
mi
n
a
l
P
r
o
d
u
c
t
i
o
n
r
u
l
e
s
<
st
a
r
t
>
::=
<
e
x
p
r
e
ss
i
o
n
>
<
e
x
p
r
e
ss
i
o
n
>
::=
<
e
x
p
r
e
ss
i
o
n
>
<
o
p
e
r
a
t
o
r
>
<
e
x
p
r
e
ss
i
o
n
>
|
<
f
u
n
c
t
i
o
n
>
(
<
e
x
p
r
e
ssi
o
n
>
)
|
<
v
a
r
i
a
b
l
e
>
|
<
c
o
n
s
t
a
n
t
>
<
o
p
e
r
a
t
o
r
>
::=
+
|
-
|
*
|
/
<
f
u
n
c
t
i
o
n
>
::=
si
n
|
c
o
s |
t
a
n
|
s
q
r
t
|
a
b
s
<
v
a
r
i
a
b
l
e
>
::=
y
t
-
1
|
y
t
-
2
|
y
t
-
3
|
y
t
-
4
|
y
t
-
5
|
y
t
-
6
|
y
t
-
7
|
y
t
-
8
|
y
t
-
9
<
c
o
n
s
t
a
n
t
>
::=
0
|
<
d
i
g
i
t
>
|
<
d
i
g
i
t
>
<
c
o
n
st
a
n
t
>
<
d
i
g
i
t
>
::=
1
|
2
|
3
|
4
|
5
|
6
|
7
|
8
|
9
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Tech
n
ica
l a
n
a
lysi
s
mo
d
el
fo
r
s
to
ck
p
r
ed
ictio
n
u
s
in
g
a
g
r
a
mm
a
tica
l
…
(
A
d
itya
K
u
s
u
ma
S
etya
n
eg
a
r
a
)
1239
p
r
ed
ictio
n
ac
cu
r
ac
y
ag
ain
s
t
ac
tu
al
v
alu
es.
T
o
en
s
u
r
e
v
alid
a
n
d
ef
f
icien
t
ch
r
o
m
o
s
o
m
e
tr
a
n
s
latio
n
,
a
d
u
p
licate
an
d
p
r
u
n
e
m
ec
h
a
n
is
m
is
a
p
p
lied
d
u
r
in
g
th
e
m
ap
p
in
g
p
r
o
ce
s
s
.
T
h
e
d
u
p
licate
s
t
ep
h
a
n
d
les
in
v
alid
c
h
r
o
m
o
s
o
m
es b
y
r
eg
en
e
r
atin
g
v
alid
o
n
es,
wh
ile
th
e
p
r
u
n
e
s
t
ep
m
ar
k
s
th
e
last
u
s
ed
elem
en
t to
in
d
icate
th
e
en
d
o
f
a
v
alid
e
x
p
r
ess
io
n
,
e
f
f
ec
t
iv
ely
ig
n
o
r
in
g
u
n
u
s
ed
c
o
d
o
n
s
to
im
p
r
o
v
e
t
r
an
s
latio
n
ef
f
i
cien
cy
an
d
r
ed
u
ce
co
m
p
u
tatio
n
al
o
v
e
r
h
ea
d
.
T
h
ese
f
u
n
ctio
n
s
ev
o
lv
e
ac
r
o
s
s
g
en
e
r
atio
n
s
u
n
til
an
o
p
tim
al
s
o
lu
ti
o
n
is
ac
h
iev
ed
.
T
h
e
h
ig
h
est
f
itn
ess
v
alu
e
is
co
n
s
i
d
er
ed
th
e
o
p
tim
al
s
o
lu
tio
n
;
a;
a
lo
wer
R
M
SE
v
alu
e
r
esu
lts
in
a
h
ig
h
er
f
itn
ess
s
co
r
e,
in
d
icatin
g
a
m
o
d
el
with
b
etter
p
r
ed
ictiv
e
ca
p
ab
ilit
y
[
1
7
]
.
Fig
u
r
e
2
illu
s
tr
at
es th
e
GE
d
iag
r
am
,
p
r
o
v
i
d
in
g
a
d
etailed
v
is
u
aliza
tio
n
o
f
t
h
e
ev
o
lu
tio
n
ar
y
p
r
o
ce
s
s
an
d
its
co
m
p
o
n
en
ts
,
in
clu
d
in
g
in
itializatio
n
,
tr
a
n
s
latio
n
,
f
itn
ess
ev
alu
atio
n
,
an
d
th
e
ap
p
licatio
n
o
f
g
en
etic
o
p
er
at
o
r
s
.
I
n
t
h
e
t
r
ai
n
i
n
g
p
r
o
c
e
s
s
,
f
u
n
c
t
i
o
n
s
a
r
e
p
r
o
g
r
es
s
i
v
e
l
y
r
e
f
i
n
e
d
b
a
s
e
d
o
n
h
is
t
o
r
i
c
al
s
t
o
c
k
d
a
t
a
t
o
i
d
e
n
t
i
f
y
t
h
e
b
es
t
-
p
er
f
o
r
m
i
n
g
m
o
d
e
l
,
w
h
i
c
h
is
s
u
b
s
e
q
u
e
n
t
l
y
t
e
s
t
e
d
o
n
u
n
s
e
e
n
d
a
t
a
u
s
i
n
g
m
e
a
n
a
b
s
o
l
u
t
e
p
e
r
c
e
n
t
a
g
e
e
r
r
o
r
(
MA
PE
)
a
s
t
h
e
e
v
a
l
u
a
ti
o
n
m
e
t
r
i
c
.
F
i
n
a
ll
y
,
p
a
r
a
m
e
t
e
r
o
p
t
i
m
i
z
a
ti
o
n
a
n
d
c
o
m
p
u
t
a
t
i
o
n
al
e
f
f
i
c
i
e
n
c
y
a
r
e
a
n
al
y
z
e
d
.
Fig
u
r
e
2
.
Gr
am
m
atica
l
ev
o
lu
ti
o
n
d
iag
r
am
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
ec
tio
n
p
r
esen
ts
th
e
ex
p
er
im
en
tal
r
esu
lts
an
d
ev
alu
atio
n
m
etr
ics u
s
ed
in
th
e
p
r
o
p
o
s
ed
p
r
ed
ictio
n
f
r
am
ewo
r
k
.
All
ex
p
er
im
en
ts
i
n
th
is
s
tu
d
y
we
r
e
co
n
d
u
cted
u
s
in
g
Py
th
o
n
3
.
1
1
.
0
,
alo
n
g
w
ith
th
e
s
cik
it
-
lear
n
,
AR
I
MA
,
p
r
o
p
h
et,
an
d
ex
p
o
n
e
n
tial
s
m
o
o
th
in
g
lib
r
ar
ies.
T
h
e
p
r
im
ar
y
d
ataset
was
d
iv
id
ed
in
to
a
tr
ain
in
g
s
et
co
n
tain
in
g
7
4
5
s
am
p
les
(
8
0
%
o
f
th
e
to
tal
d
ata)
an
d
a
test
in
g
s
et
with
1
8
7
s
am
p
les
(
2
0
%
o
f
th
e
to
tal
d
ata)
to
tr
ain
th
e
m
o
d
el
an
d
ass
ess
it
s
p
er
f
o
r
m
a
n
ce
.
Mo
d
el
p
er
f
o
r
m
an
ce
was
m
ea
s
u
r
ed
u
s
in
g
R
MSE
,
R
2
s
co
r
e,
an
d
MA
PE
.
T
h
e
p
r
ed
ictio
n
r
esu
lts
ar
e
s
u
m
m
ar
ized
in
th
e
T
a
b
le
3
.
I
n
th
is
s
tu
d
y
,
a
co
m
p
ar
ativ
e
an
aly
s
is
was
co
n
d
u
cte
d
o
n
t
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
GE
m
o
d
el
al
o
n
g
s
id
e
th
r
ee
o
th
e
r
p
r
ed
ictio
n
m
o
d
els:
AR
I
MA
[
1
8
]
−
[2
0
]
,
p
r
o
p
h
et
[
2
1
]
−
[
2
4
]
,
ex
p
o
n
en
ti
al
s
m
o
o
th
in
g
[2
5
]
,
[
2
6
]
,
an
d
Fib
o
n
ac
ci
r
etr
ac
e
m
en
ts
[
2
7
]
.
E
ac
h
m
o
d
el
was
ev
alu
ated
u
s
in
g
th
e
s
am
e
s
to
ck
d
ata,
with
id
en
tical
tr
ain
in
g
an
d
test
in
g
d
ata
s
p
lits
,
an
d
co
n
s
is
ten
t
p
r
ep
r
o
ce
s
s
in
g
m
eth
o
d
s
.
3
.
1
.
E
v
a
lua
t
i
o
n o
f
t
he
bes
t
i
nd
iv
idu
a
l
T
h
i
s
s
t
u
d
y
e
v
a
l
u
at
es
i
n
d
i
v
i
d
u
a
ls
i
n
t
h
e
G
E
m
o
d
e
l
u
s
i
n
g
R
MSE
a
s
t
h
e
p
r
i
m
a
r
y
f
i
t
n
es
s
m
e
t
r
ic
t
o
m
e
a
s
u
r
e
p
r
e
d
i
c
t
i
o
n
e
r
r
o
r
.
A
t
t
h
e
e
n
d
o
f
e
a
c
h
g
e
n
e
r
a
t
i
o
n
,
m
o
d
e
l
p
e
r
f
o
r
m
a
n
c
e
i
s
f
u
r
t
h
e
r
ass
e
s
s
e
d
u
s
i
n
g
M
A
P
E
a
n
d
t
h
e
R
²
s
c
o
r
e
,
w
h
e
r
e
M
AP
E
m
e
as
u
r
e
s
t
h
e
a
v
e
r
a
g
e
p
e
r
c
e
n
t
a
g
e
e
r
r
o
r
a
n
d
R
²
i
n
d
ic
a
t
es
t
h
e
d
e
g
r
e
e
o
f
v
a
r
i
a
n
c
e
i
n
t
h
e
d
a
t
as
e
t
t
h
a
t
c
a
n
b
e
a
tt
r
i
b
u
t
e
d
t
o
t
h
e
m
o
d
e
l
.
T
h
e
e
q
u
a
t
i
o
n
s
u
s
e
d
i
n
t
h
is
e
v
a
l
u
a
t
i
o
n
a
r
e
s
h
o
w
n
i
n
(
1
)
t
o
(
6
)
[
2
8
]
−
[3
2
].
=
1
−
ɛ
(
1
)
=
√
1
∑
(
−
ŷ
)
2
=
1
(
2
)
=
1
∑
|
−
ŷ
|
100%
=
1
(
3
)
2
=
1
−
(
4
)
=
∑
(
−
ŷ
)
2
=
1
(
5
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
26
:
1
2
3
6
-
1
2
4
6
1240
=
∑
(
−
ӯ
)
2
=
1
(
6
)
T
h
e
ter
m
s
u
s
ed
in
th
e
eq
u
atio
n
s
ar
e
d
ef
in
ed
as
f
o
llo
ws:
ε
is
a
s
m
all
co
n
s
tan
t
ad
d
ed
to
av
o
i
d
d
iv
is
io
n
b
y
ze
r
o
,
d
en
o
tes
th
e
to
tal
n
u
m
b
er
o
f
d
ata
p
o
i
n
ts
,
ᵢ
r
ep
r
esen
ts
th
e
ac
tu
al
v
alu
es,
an
d
ŷ
ᵢ
in
d
icate
s
th
e
p
r
ed
icted
v
alu
es
g
en
er
ate
d
b
y
th
e
r
eg
r
ess
io
n
m
o
d
el.
Fo
r
th
e
R
²
m
etr
ic,
ӯ
ᵢ
is
th
e
m
ea
n
o
f
t
h
e
o
b
s
er
v
e
d
v
al
u
es,
wh
ile
ᵣ
ₑₛ
an
d
ₜₒₜ
d
en
o
te
th
e
r
esid
u
al
an
d
to
tal
s
u
m
s
o
f
s
q
u
ar
es,
r
esp
ec
tiv
ely
.
T
h
ese
d
ef
i
n
itio
n
s
co
llectiv
ely
s
u
p
p
o
r
t th
e
ev
alu
atio
n
o
f
m
o
d
el
p
er
f
o
r
m
an
ce
.
T
ab
le
3
.
Su
m
m
a
r
y
o
f
p
r
ed
ictio
n
r
esu
lts
M
o
d
e
l
R
u
n
n
i
n
g
t
i
me
(
s)
R
2
s
c
o
r
e
R
M
S
E
(
R
p
)
M
A
P
E
P
a
r
a
me
t
e
r
S
i
mp
l
e
e
x
p
o
n
e
n
t
i
a
l
smo
o
t
h
i
n
g
0
.
5
-
0
.
1
5
3
9
6
.
8
5
0
.
0
7
α =
0
.
9
1
3
D
o
u
b
l
e
e
x
p
o
n
e
n
t
i
a
l
smo
o
t
h
i
n
g
0
.
6
0
.
3
7
2
9
3
.
8
4
0
.
0
4
α =
0
.
6
;
β
=
0
.
2
H
o
l
t
’
s
w
i
n
t
e
r
Ex
p
o
n
e
n
t
i
a
l
sm
o
o
t
h
i
n
g
0
.
8
0
.
3
6
2
9
4
.
9
1
0
.
0
5
A
d
d
i
t
i
v
e
+
D
a
m
p
e
d
α =
0
.
6
;
β
=
0
.
1
5
;
γ
=
0
.
1
5
F
a
c
e
b
o
o
k
p
r
o
p
h
e
t
1
.
5
-
0
.
5
2
8
4
5
6
.
5
5
0
.
0
7
7
sea
s
o
n
a
l
i
t
y
=
'm
u
l
t
i
p
l
i
c
a
t
i
v
e
';
d
a
i
l
y
_
s
e
a
so
n
a
l
i
t
y
=
Tr
u
e
;
w
e
e
k
l
y
_
sea
so
n
a
l
i
t
y
=
F
a
l
se
;
y
e
a
r
l
y
_
s
e
a
s
o
n
a
l
i
t
y
=
Tr
u
e
A
R
I
M
A
1
-
0
.
3
0
2
4
2
1
.
4
0
.
0
7
8
d
i
f
f
=
3
0
d
a
y
s;
(
p
,
d
,
q
)
=
(
1
,
0
,
0
)
G
r
a
mm
a
t
i
c
a
l
e
v
o
l
u
t
i
o
n
6
1
2
9
0
.
7
8
4
1
7
1
.
7
1
0
.
0
2
8
1
P
o
p
u
l
a
t
i
o
n
=
5
0
;
G
e
n
e
r
a
t
i
o
n
=
2
0
;
C
r
o
s
so
v
e
r
=
0
.
9
;
M
u
t
a
t
i
o
n
=
0
.
5
;
S
e
l
e
c
t
i
o
n
M
e
t
h
o
d
=
R
o
u
l
e
t
t
e
W
h
e
e
l
;
3
.
2
.
O
pti
m
a
l
chro
m
o
s
o
m
e
a
nd
t
ra
ns
la
t
io
n pro
c
ess
I
n
th
is
s
tu
d
y
,
th
e
s
ea
r
ch
f
o
r
th
e
o
p
tim
al
ch
r
o
m
o
s
o
m
e
b
e
g
in
s
with
an
in
itial
p
o
p
u
latio
n
o
f
1
0
0
ch
r
o
m
o
s
o
m
es.
E
ac
h
ch
r
o
m
o
s
o
m
e
is
th
en
tr
an
s
lated
in
to
a
m
ath
em
atica
l
f
o
r
m
u
la,
an
d
th
e
r
esu
ltin
g
f
o
r
m
u
la
is
test
ed
u
s
in
g
test
d
ata.
T
h
e
ch
r
o
m
o
s
o
m
e
with
th
e
h
ig
h
est
f
it
n
ess
v
alu
e,
in
d
icatin
g
th
e
b
est
p
er
f
o
r
m
a
n
ce
b
ased
o
n
th
e
test
d
ata,
is
d
esig
n
ated
as th
e
o
p
tim
al
ch
r
o
m
o
s
o
m
e.
I
f
th
e
tr
an
s
latio
n
p
r
o
ce
s
s
r
esu
lts
in
an
in
v
alid
f
o
r
m
u
la,
th
e
ch
r
o
m
o
s
o
m
e
will
b
e
d
u
p
licated
u
p
to
a
m
ax
im
u
m
lim
it
o
f
6
0
0
c
h
r
o
m
o
s
o
m
es.
I
f
th
e
d
u
p
licatio
n
ex
c
ee
d
s
th
is
lim
it
with
o
u
t
p
r
o
d
u
c
in
g
a
v
alid
f
o
r
m
u
la,
a
n
ew
ch
r
o
m
o
s
o
m
e
is
g
en
e
r
at
ed
to
r
ep
lace
th
e
in
v
alid
o
n
e
.
T
h
is
ap
p
r
o
ac
h
aim
s
to
m
ain
tai
n
th
e
q
u
ality
o
f
th
e
ch
r
o
m
o
s
o
m
e
p
o
p
u
latio
n
a
n
d
e
n
s
u
r
e
th
at
th
e
tr
a
n
s
latio
n
p
r
o
c
ess
p
r
o
d
u
ce
s
r
eliab
le
s
o
lu
tio
n
s
.
T
h
e
tr
an
s
latio
n
p
r
o
ce
s
s
aim
s
to
p
r
o
d
u
ce
t
h
e
m
o
s
t
ac
cu
r
ate
p
r
ed
ictio
n
f
o
r
m
u
la.
On
ce
a
v
alid
f
o
r
m
u
la
is
g
en
er
ated
,
p
r
u
n
in
g
is
ap
p
lie
d
to
r
em
o
v
e
ir
r
ele
v
an
t
o
r
r
e
d
u
n
d
an
t
ch
r
o
m
o
s
o
m
es,
s
im
p
lify
in
g
th
e
m
o
d
el
an
d
im
p
r
o
v
in
g
ef
f
icien
c
y
b
y
r
etain
in
g
o
n
ly
co
m
p
o
n
e
n
ts
th
at
s
ig
n
if
ican
tl
y
co
n
tr
ib
u
te
to
p
r
ed
ictio
n
ac
cu
r
ac
y
.
As
s
h
o
wn
in
T
a
b
le
4
,
tr
an
s
latio
n
is
p
er
f
o
r
m
ed
b
y
m
o
d
u
latin
g
ea
ch
c
h
r
o
m
o
s
o
m
e
v
al
u
e
ac
c
o
r
d
in
g
to
t
h
e
B
NF
g
r
am
m
ar
r
u
les,
wh
er
e
ea
ch
m
o
d
u
latio
n
r
esu
lt
d
eter
m
i
n
es
th
e
ap
p
lied
e
x
p
r
ess
io
n
r
u
le.
T
h
i
s
p
r
o
ce
s
s
co
n
tin
u
es
u
n
til all
ch
r
o
m
o
s
o
m
e
v
alu
es a
r
e
u
s
ed
o
r
a
v
alid
f
o
r
m
u
la
is
o
b
tain
ed
.
T
ab
le
4
.
T
h
e
b
est m
o
d
el
p
r
ed
i
ctio
n
B
e
st
c
h
r
o
m
o
s
o
me
B
e
st
m
o
d
e
l
p
r
e
d
i
c
t
i
o
n
[
2
2
,
4
9
,
8
4
,
2
1
,
4
8
,
9
5
,
9
9
,
3
8
,
7
8
,
6
,
4
9
,
7
2
,
2
5
,
3
9
,
2
9
,
4
8
,
4
9
,
4
1
,
4
7
,
1
0
,
1
1
,
4
2
,
4
1
,
3
5
,
2
4
,
8
4
,
6
6
,
7
8
,
3
7
,
5
8
,
8
3
,
2
,
4
1
,
3
5
,
8
6
,
5
1
,
3
1
,
2
,
6
2
,
8
4
,
9
4
,
8
0
,
4
1
,
7
3
,
4
1
,
2
9
,
1
2
,
6
2
,
7
7
,
2
,
2
7
,
8
6
,
9
1
,
3
1
,
8
0
,
4
1
,
7
5
,
7
,
7
5
,
5
0
,
8
0
,
6
5
,
5
6
,
6
4
,
4
4
,
1
9
,
7
1
,
7
,
5
2
,
2
2
,
9
8
,
2
1
,
4
6
,
5
7
,
1
1
,
2
1
,
3
4
,
8
3
,
4
4
,
4
1
,
8
3
,
2
9
,
6
2
,
2
4
,
3
0
,
8
0
,
1
2
,
5
9
,
9
6
,
9
4
,
5
7
,
4
5
,
2
1
,
8
6
,
9
6
,
1
,
1
8
,
8
9
,
3
0
,
7
7
,
1
,
8
7
,
5
7
,
1
5
,
6
2
,
9
5
,
3
7
,
8
,
5
5
,
5
7
,
2
2
,
2
6
,
1
1
,
1
2
,
6
3
,
3
6
,
2
4
,
6
2
,
4
2
,
3
,
4
1
,
4
4
,
8
3
,
3
4
,
5
3
,
4
3
,
5
7
,
4
6
,
7
9
,
8
8
,
4
0
,
3
5
,
8
8
,
3
2
,
1
9
,
7
,
2
4
,
5
3
,
6
5
,
1
4
,
9
9
,
3
1
,
4
7
,
3
7
,
4
1
,
8
0
,
2
2
,
9
1
,
1
8
,
3
,
1
,
4
7
,
8
,
9
8
,
2
0
,
7
7
,
7
3
,
5
6
,
9
0
,
1
7
,
8
4
,
6
2
,
1
2
,
8
8
,
8
9
,
3
3
,
6
9
,
8
8
,
5
8
,
6
1
,
8
3
,
3
7
,
2
5
,
6
6
,
8
7
,
5
8
,
8
9
,
5
8
,
4
4
,
1
5
,
4
7
,
1
1
,
3
6
,
4
9
,
3
1
,
5
3
,
3
7
,
3
9
,
1
0
0
,
6
2
,
7
6
,
1
,
7
2
,
8
2
,
8
1
,
9
4
,
6
0
,
6
0
,
6
5
,
5
]
(
(
(
0
.
7
*
ma
.
M
o
d
e
l
a
r
i
ma
(
d
a
t
a
_
s
a
h
a
m,
1
8
7
,
1
,
4
,
3
,
4
)
)
+
(
(
0
.
5
*
me
s.
h
o
l
t
_
e
x
p
smo
o
t
h
(
d
a
t
a
_
s
a
h
a
m,
1
8
7
,
0
.
7
,
0
.
6
)
)
+
(
0
.
1
*
ma
.
mo
d
e
l
_
a
r
i
m
a
(
d
a
t
a
_
sa
h
a
m
,
1
8
7
,
1
,
6
,
3
,
2
)
)
)
)
/
1
.
3
I
n
th
is
f
o
r
m
u
la,
th
e
weig
h
ts
0
.
7
,
0
.
5
,
a
n
d
0
.
1
r
ep
r
esen
t
t
h
e
c
o
n
tr
ib
u
tio
n
s
o
f
e
ac
h
m
o
d
el,
s
p
ec
if
ically
AR
I
MA
an
d
ex
p
o
n
en
tial
s
m
o
o
th
in
g
.
T
h
e
to
tal
weig
h
t
is
1
.
3
,
o
b
tain
e
d
b
y
s
u
m
m
in
g
th
e
i
n
d
iv
id
u
al
weig
h
ts
.
T
h
e
f
in
al
f
o
r
ec
ast
is
g
en
er
at
ed
th
r
o
u
g
h
a
weig
h
te
d
in
teg
r
atio
n
o
f
p
r
ed
ictio
n
s
f
r
o
m
i
n
d
iv
id
u
al
m
o
d
els,
f
o
llo
wed
b
y
n
o
r
m
aliza
tio
n
u
s
in
g
th
e
to
tal
weig
h
t.
T
h
i
s
ap
p
r
o
ac
h
alig
n
s
with
th
e
en
s
em
b
le
c
o
n
ce
p
t,
co
m
b
in
in
g
m
u
ltip
le
p
r
ed
ictiv
e
m
o
d
els co
m
b
i
n
in
g
m
u
ltip
le
p
r
ed
ictiv
e
m
o
d
els to
e
n
h
an
ce
a
cc
u
r
ac
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Tech
n
ica
l a
n
a
lysi
s
mo
d
el
fo
r
s
to
ck
p
r
ed
ictio
n
u
s
in
g
a
g
r
a
mm
a
tica
l
…
(
A
d
itya
K
u
s
u
ma
S
etya
n
eg
a
r
a
)
1241
T
h
e
en
s
em
b
le
m
eth
o
d
in
t
h
is
co
n
tex
t
u
tili
ze
s
a
weig
h
ted
a
v
er
ag
e
o
f
m
u
ltip
le
m
o
d
el
p
r
e
d
ictio
n
s
,
a
tech
n
iq
u
e
th
at
h
as
b
ee
n
em
p
l
o
y
ed
s
in
ce
ea
r
ly
r
esear
ch
o
n
e
n
s
em
b
le
m
o
d
els
[
3
3
]
,
[
3
4
]
.
E
ac
h
o
u
tp
u
t
f
r
o
m
th
e
b
ase
m
o
d
els
is
ass
ig
n
ed
a
weig
h
t
b
ased
o
n
its
p
e
r
f
o
r
m
an
ce
cr
iter
i
a,
with
th
e
to
tal
we
ig
h
t
o
f
all
m
o
d
els
s
u
m
m
in
g
to
o
n
e
[
3
5
]
.
T
h
e
p
er
f
o
r
m
an
ce
ev
al
u
atio
n
o
f
th
e
r
e
s
u
ltin
g
f
o
r
m
u
la
y
ield
ed
r
esu
lt
s
:
R
²
s
co
r
e:
0
.
7
8
3
8
;
R
MSE
: 1
7
1
.
7
1
2
3
; M
APE:
0
.
0
2
8
1
.
3
.
3
.
Resul
t
s
a
na
ly
s
is
a
nd
pa
ra
m
et
er
t
un
ing
Af
ter
id
en
tif
y
in
g
th
e
b
est
ch
r
o
m
o
s
o
m
e,
p
ar
a
m
eter
t
u
n
in
g
was
co
n
d
u
cted
u
s
in
g
th
e
g
r
id
s
ea
r
ch
m
eth
o
d
to
o
p
tim
ize
m
o
d
el
p
er
f
o
r
m
an
ce
.
Var
io
u
s
p
ar
am
eter
co
m
b
in
atio
n
s
wer
e
ev
al
u
ated
b
y
v
a
r
y
in
g
p
o
p
u
latio
n
s
ize
(
1
0
,
5
0
,
1
0
0
)
,
n
u
m
b
e
r
o
f
g
en
er
atio
n
s
(
1
0
,
3
0
,
5
0
)
,
cr
o
s
s
o
v
er
p
r
o
b
ab
il
ity
(
0
.
2
,
0
.
5
,
0
.
8
)
,
m
u
tatio
n
p
r
o
b
ab
ilit
y
(
0
.
2
,
0
.
5
,
0
.
8
)
,
an
d
p
ar
e
n
t selec
tio
n
m
eth
o
d
s
(
r
o
u
lette
wh
ee
l,
r
an
k
-
b
ased
,
an
d
to
u
r
n
am
e
n
t
s
elec
tio
n
)
[
3
6
]
−
[3
8
].
E
x
p
er
i
m
en
tal
r
esu
lts
d
em
o
n
s
tr
ated
th
at
ea
ch
p
ar
am
eter
co
m
b
i
n
atio
n
s
ig
n
if
ican
tly
in
f
lu
en
ce
d
m
o
d
el
p
er
f
o
r
m
a
n
c
e
an
d
co
m
p
u
tatio
n
al
ef
f
icien
c
y
.
I
n
th
e
f
ir
s
t
tr
ial,
GE
ac
h
iev
ed
an
R
²
o
f
0
.
7
6
3
4
,
R
MSE
o
f
1
7
9
.
6
6
3
2
,
an
d
M
APE
o
f
0
.
0
2
3
7
,
with
a
co
m
p
u
tatio
n
tim
e
o
f
4
7
0
7
s
ec
o
n
d
s
.
T
h
e
s
ec
o
n
d
tr
ial
s
h
o
wed
s
lig
h
t
im
p
r
o
v
em
en
t
w
ith
an
R
²
o
f
0
.
7
6
3
8
,
R
MSE
o
f
1
7
9
.
5
1
2
9
,
an
d
a
lo
wer
MA
P
E
o
f
0
.
0
2
3
4
,
with
a
co
m
p
u
tatio
n
tim
e
o
f
2
8
4
4
s
ec
o
n
d
s
.
T
h
e
th
ir
d
tr
ial
d
eliv
er
ed
th
e
b
est
p
er
f
o
r
m
an
ce
with
an
R
²
o
f
0
.
7
8
3
8
,
R
MSE
o
f
1
7
1
.
7
1
2
3
,
an
d
MA
PE
o
f
0
.
0
2
8
1
in
a
co
m
p
u
tatio
n
t
im
e
o
f
6
1
2
9
s
ec
o
n
d
s
.
T
h
e
f
o
u
r
th
t
r
ial,
u
s
in
g
a
p
o
p
u
latio
n
s
ize
o
f
1
0
0
an
d
5
0
g
en
er
atio
n
s
,
r
e
q
u
ir
ed
2
6
,
8
4
5
s
ec
o
n
d
s
b
u
t
s
h
o
wed
n
o
s
ig
n
if
ican
t
ac
cu
r
ac
y
im
p
r
o
v
em
en
t
(
R
²
=0
.
7
6
7
1
,
R
MSE
=1
7
8
.
2
3
1
8
,
MA
PE
2
=
0
.
0
2
5
)
.
T
h
is
s
u
g
g
ests
th
at
in
cr
ea
s
in
g
p
o
p
u
latio
n
s
ize
an
d
g
en
er
atio
n
s
ca
n
r
aise
co
m
p
u
tatio
n
al
co
s
ts
with
o
u
t
p
r
o
p
o
r
tio
n
al
p
er
f
o
r
m
an
ce
g
ain
s
.
T
h
e
b
est
co
n
f
i
g
u
r
atio
n
u
s
ed
a
p
o
p
u
latio
n
s
ize
o
f
5
0
,
2
0
g
en
er
a
tio
n
s
,
a
cr
o
s
s
o
v
er
p
r
o
b
a
b
ilit
y
o
f
0
.
9
,
a
m
u
tatio
n
p
r
o
b
ab
ilit
y
o
f
0
.
5
,
a
n
d
r
o
u
let
te
wh
ee
l
s
elec
tio
n
,
ac
h
iev
in
g
th
e
h
ig
h
est
R
²
with
r
elativ
ely
lo
w
co
m
p
u
tatio
n
ti
m
e.
Fig
u
r
e
3
co
m
p
a
r
es
th
e
p
r
ed
icted
an
d
ac
tu
al
s
to
ck
p
r
ice
s
,
d
em
o
n
s
tr
atin
g
th
e
m
o
d
el’
s
p
er
f
o
r
m
a
n
ce
.
Fig
u
r
e
3
.
T
h
e
b
est p
r
e
d
ictio
n
m
o
d
el
Ho
wev
er
,
th
e
r
o
u
lette
wh
ee
l
m
eth
o
d
h
as
lim
itatio
n
s
in
s
m
all
p
o
p
u
latio
n
s
o
r
wh
e
n
cr
o
s
s
o
v
er
an
d
m
u
tatio
n
p
r
o
b
ab
ilit
ies
ar
e
lo
w.
Un
d
er
th
ese
co
n
d
itio
n
s
,
h
ig
h
-
f
itn
ess
in
d
iv
id
u
als
ten
d
to
b
e
r
ep
ea
ted
ly
s
elec
ted
,
r
esu
ltin
g
in
i
d
en
tical
ch
r
o
m
o
s
o
m
es
an
d
r
ed
u
ce
d
p
o
p
u
latio
n
d
iv
er
s
ity
,
w
h
ich
ca
n
lead
to
s
u
b
o
p
tim
al
s
o
lu
tio
n
s
.
T
h
er
ef
o
r
e
,
ca
r
ef
u
l
p
ar
am
eter
s
elec
tio
n
an
d
ap
p
r
o
p
r
iate
p
ar
en
t
s
elec
tio
n
m
eth
o
d
s
ar
e
r
eq
u
ir
ed
to
m
ain
tain
d
iv
er
s
ity
.
Alter
n
ativ
e
ap
p
r
o
ac
h
es
s
u
ch
as
to
u
r
n
am
en
t
o
r
r
an
k
-
b
ased
s
elec
tio
n
,
alo
n
g
with
d
iv
er
s
ity
-
p
r
eser
v
in
g
tec
h
n
iq
u
es,
ca
n
h
el
p
s
u
s
tain
ex
p
lo
r
atio
n
an
d
p
r
e
v
en
t p
r
em
atu
r
e
co
n
v
er
g
e
n
ce
.
Ov
er
all,
th
e
r
esu
lts
s
h
o
w
t
h
at
ap
p
r
o
p
r
iate
p
ar
am
eter
tu
n
in
g
ca
n
s
u
b
s
tan
tially
im
p
r
o
v
e
G
E
p
er
f
o
r
m
an
ce
d
esp
ite
its
h
ig
h
co
m
p
u
tatio
n
al
c
o
s
t.
T
h
e
f
in
d
in
g
s
h
ig
h
lig
h
t
th
e
im
p
o
r
tan
ce
o
f
b
alan
cin
g
ex
p
lo
r
atio
n
an
d
ex
p
lo
itatio
n
t
o
ac
h
iev
e
r
o
b
u
s
t
p
r
ed
ictiv
e
ac
cu
r
ac
y
a
n
d
p
r
o
v
id
e
g
u
id
a
n
ce
f
o
r
d
e
v
elo
p
in
g
m
o
r
e
ef
f
icien
t
an
d
ad
a
p
tiv
e
m
eth
o
d
s
.
Fig
u
r
es
4
to
7
p
r
esen
t
alter
n
ativ
e
m
o
d
els
g
en
er
ated
u
s
in
g
d
if
f
er
en
t
p
a
r
am
eter
co
n
f
ig
u
r
atio
n
s
,
illu
s
tr
atin
g
th
e
im
p
ac
t o
f
p
ar
am
eter
v
ar
iatio
n
s
o
n
m
o
d
el
p
er
f
o
r
m
an
ce
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
26
:
1
2
3
6
-
1
2
4
6
1242
Fig
u
r
e
4
.
Alter
n
ativ
e
m
o
d
els o
f
v
ar
io
u
s
p
ar
am
eter
c
o
n
f
ig
u
r
a
t
io
n
s
Fig
u
r
e
5
.
Alter
n
ativ
e
m
o
d
els o
f
v
ar
io
u
s
p
ar
am
eter
c
o
n
f
ig
u
r
at
io
n
s
Fig
u
r
e
6
.
Alter
n
ativ
e
m
o
d
els o
f
v
ar
io
u
s
p
ar
am
eter
c
o
n
f
ig
u
r
at
io
n
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Tech
n
ica
l a
n
a
lysi
s
mo
d
el
fo
r
s
to
ck
p
r
ed
ictio
n
u
s
in
g
a
g
r
a
mm
a
tica
l
…
(
A
d
itya
K
u
s
u
ma
S
etya
n
eg
a
r
a
)
1243
Fig
u
r
e
7
.
Alter
n
ativ
e
m
o
d
els o
f
v
ar
io
u
s
p
ar
am
eter
c
o
n
f
ig
u
r
at
io
n
s
Af
ter
ev
alu
atin
g
th
e
p
r
o
p
o
s
e
d
GE
m
o
d
el
o
n
th
e
SMAR
s
to
ck
d
ataset,
f
u
r
th
er
e
x
p
er
i
m
en
ts
wer
e
co
n
d
u
cte
d
o
n
s
ev
er
al
ad
d
itio
n
al
s
to
ck
d
atasets
u
s
ed
in
p
r
ev
io
u
s
s
tu
d
ies
to
as
s
ess
th
e
m
o
d
el’
s
g
en
er
aliza
tio
n
ab
ilit
y
an
d
en
ab
le
f
air
co
m
p
ar
is
o
n
.
T
ab
le
5
co
m
p
ar
es
th
e
p
r
ed
ictio
n
p
er
f
o
r
m
an
ce
o
f
th
e
p
r
o
p
o
s
ed
GE
m
o
d
el
with
th
at
o
f
L
i
an
d
Pan
[
1
3
]
o
n
th
e
S&
P
5
0
0
I
n
d
ex
d
ataset
u
s
in
g
R
²,
R
M
SE,
an
d
MA
PE
.
T
h
e
p
r
o
p
o
s
ed
GE
m
o
d
el
was
ap
p
lied
to
s
to
ck
p
r
ice
p
r
ed
ictio
n
o
n
th
e
J
o
h
a
n
n
esb
u
r
g
Sto
ck
E
x
ch
a
n
g
e
(
J
SE)
an
d
th
e
New
Yo
r
k
Sto
ck
E
x
ch
an
g
e
(
NYSE
)
,
wit
h
p
er
f
o
r
m
an
c
e
ev
alu
ated
u
s
in
g
k
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
to
e
n
s
u
r
e
r
eliab
le
r
esu
lts
.
T
h
e
ev
alu
ati
o
n
m
etr
ics
f
o
r
b
o
th
d
atasets
ar
e
s
u
m
m
ar
ized
in
T
ab
le
6
.
T
ab
le
7
c
o
m
p
ar
e
s
th
e
p
r
o
p
o
s
ed
GE
m
o
d
el
with
th
e
r
esu
lts
r
ep
o
r
te
d
b
y
Ag
g
r
awa
l
a
n
d
Dh
awa
n
[
1
2
]
f
o
r
th
e
Ad
an
i
E
n
ter
p
r
is
es
(
ADAN
I
E
NT
)
s
to
ck
u
s
in
g
R
²,
R
MSE
,
an
d
MA
PE.
T
ab
le
5
.
C
o
m
p
a
r
is
o
n
o
f
p
r
e
d
ictio
n
r
esu
lts
b
etwe
en
GE
an
d
th
e
s
tu
d
y
b
y
L
i a
n
d
Pan
[
1
3
]
S
t
u
d
y
M
o
d
e
l
R²
S
c
o
r
e
R
M
S
E
M
A
P
E
Li
a
n
d
P
a
n
[
1
3
]
LSTM
N
o
t
r
e
p
o
r
t
e
d
2
0
.
9
6
N
o
t
r
e
p
o
r
t
e
d
DP
-
LSTM
N
o
t
r
e
p
o
r
t
e
d
1
8
.
1
8
N
o
t
r
e
p
o
r
t
e
d
G
R
U
N
o
t
r
e
p
o
r
t
e
d
1
5
.
7
9
N
o
t
r
e
p
o
r
t
e
d
A
v
e
r
a
g
i
n
g
e
n
se
mb
l
e
N
o
t
r
e
p
o
r
t
e
d
1
5
.
2
1
N
o
t
r
e
p
o
r
t
e
d
W
e
i
g
h
t
e
d
a
v
g
.
e
n
sem
b
l
e
N
o
t
r
e
p
o
r
t
e
d
1
5
.
1
5
N
o
t
r
e
p
o
r
t
e
d
B
l
e
n
d
i
n
g
e
n
se
mb
l
e
N
o
t
r
e
p
o
r
t
e
d
1
3
.
6
5
N
o
t
r
e
p
o
r
t
e
d
Th
i
s
st
u
d
y
GE
0
.
1
8
4
2
(
a
v
g
)
2
9
.
5
5
(
a
v
g
)
1
.
3
6
(
a
v
g
)
T
ab
le
6
.
Per
f
o
r
m
an
ce
o
f
GE
m
o
d
el
o
n
J
SE
an
d
NYSE
d
ata
s
ets u
s
in
g
k
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
S
t
o
c
k
e
x
c
h
a
n
g
e
R²
s
c
o
r
e
R
M
S
E
M
A
P
E
JS
E
M
i
n
-
0
.
0
0
4
4
1
0
7
0
.
8
1
3
6
0
.
0
5
6
7
M
a
x
0
.
4
2
6
7
2
1
7
1
.
5
3
7
7
0
.
1
2
6
3
A
v
g
0
.
1
5
4
0
1
8
0
2
.
9
3
0
.
0
9
5
7
N
Y
S
E
M
i
n
-
0
.
0
8
7
3
1
.
4
6
8
1
0
.
0
3
7
7
M
a
x
0
.
4
4
9
4
2
.
0
6
3
1
0
.
0
5
4
6
A
v
g
0
.
2
6
0
4
1
.
6
9
7
0
0
.
0
4
4
4
T
ab
le
7
.
C
o
m
p
a
r
is
o
n
o
f
GE
r
e
s
u
lts
with
Ag
g
r
awa
l
an
d
Dh
a
wan
[
1
2
]
f
o
r
ADAN
I
E
NT
s
to
ck
S
t
u
d
y
M
o
d
e
l
R
² Sc
o
r
e
R
M
S
E
M
A
P
E
(
%)
Th
i
s
s
t
u
d
y
G
E
0
.
5
9
4
7
2
3
0
.
8
7
5
.
6
2
A
g
g
r
a
w
a
l
a
n
d
D
h
a
w
a
n
[
1
2
]
LSTM
0
.
9
3
1
5
.
3
8
0
.
5
4
G
R
U
0
.
9
5
1
3
.
5
9
0
.
5
1
TFT
0
.
1
8
4
0
.
6
7
1
.
6
6
TC
N
-
4
.
0
6
5
8
.
5
2
2
.
3
7
N
-
B
EA
TS
-
1
2
2
.
3
6
5
2
.
3
9
4
2
.
4
2
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
26
:
1
2
3
6
-
1
2
4
6
1244
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
d
em
o
n
s
tr
ates
th
at
th
e
GE
m
eth
o
d
ef
f
ec
tiv
ely
g
e
n
er
ates
ac
cu
r
ate
an
d
r
eliab
le
p
r
ed
ictiv
e
m
o
d
els
b
y
in
teg
r
atin
g
co
m
p
l
ex
s
tatis
tica
l
tech
n
iq
u
es
an
d
tech
n
ical
in
d
icato
r
s
.
T
h
e
b
est
p
er
f
o
r
m
a
n
ce
was
ac
h
iev
ed
u
s
in
g
a
GE
c
o
n
f
ig
u
r
atio
n
with
a
p
o
p
u
latio
n
s
i
ze
o
f
5
0
,
2
0
g
e
n
er
atio
n
s
,
a
cr
o
s
s
o
v
er
p
r
o
b
a
b
ilit
y
o
f
0
.
9
,
an
d
a
m
u
tatio
n
p
r
o
b
a
b
ilit
y
o
f
0
.
5
,
y
ield
i
n
g
an
R
²
o
f
0
.
7
8
3
8
,
R
MSE
o
f
1
7
1
.
7
1
2
3
,
an
d
MA
PE
o
f
0
.
0
2
8
1
in
d
icatin
g
s
u
p
er
io
r
p
r
ed
ictiv
e
ac
cu
r
ac
y
co
m
p
a
r
ed
to
tr
ad
i
tio
n
al
m
eth
o
d
s
.
T
h
ese
f
in
d
in
g
s
h
ig
h
lig
h
t
GE
’
s
p
o
ten
tial
as
an
alter
n
ativ
e
ap
p
r
o
ac
h
in
s
to
ck
p
r
ice
p
r
ed
ict
io
n
,
o
f
f
er
in
g
a
d
ap
tiv
e
an
d
ef
f
icien
t
f
o
r
m
u
las
in
r
esp
o
n
s
e
to
m
ar
k
et
d
y
n
am
ic
s
.
Fu
r
th
er
m
o
r
e,
a
d
d
itio
n
al
e
x
p
er
im
en
ts
c
o
n
d
u
cted
o
n
v
a
r
io
u
s
s
to
ck
d
atasets
in
clu
d
in
g
th
o
s
e
f
r
o
m
t
h
e
S&
P
5
0
0
I
n
d
ex
,
J
SE,
NYSE
,
an
d
ADAN
I
E
NT
f
u
r
th
er
v
alid
ate
t
h
e
v
er
s
atility
o
f
th
e
p
r
o
p
o
s
ed
GE
m
o
d
el.
Alth
o
u
g
h
th
e
m
o
d
el
p
e
r
f
o
r
m
an
ce
v
ar
i
es a
cr
o
s
s
d
if
f
er
en
t m
ar
k
ets,
th
e
r
esu
lts
co
n
s
is
ten
tly
d
em
o
n
s
tr
ate
GE
’
s
ca
p
a
b
ilit
y
t
o
ad
ap
t
t
o
d
iv
e
r
s
e
f
in
an
cial
d
ata
ch
ar
ac
ter
is
tics
wh
ile
m
ai
n
tain
in
g
co
m
p
etitiv
e
p
r
ed
ictiv
e
ac
cu
r
ac
y
c
o
m
p
a
r
e
d
to
ad
v
an
ce
d
d
ee
p
lear
n
in
g
an
d
en
s
em
b
le
-
b
ased
ap
p
r
o
ac
h
es
r
ep
o
r
ted
in
p
r
ev
io
u
s
s
tu
d
ies.
Fu
tu
r
e
wo
r
k
s
h
o
u
ld
f
o
cu
s
o
n
au
to
m
ated
p
a
r
am
eter
o
p
tim
izatio
n
u
s
i
n
g
tec
h
n
iq
u
es
lik
e
r
an
d
o
m
s
ea
r
ch
,
B
ay
esian
o
p
ti
m
izatio
n
,
o
r
g
en
etic
al
g
o
r
ith
m
s
,
an
d
ex
p
lo
r
e
d
ee
p
e
r
tu
n
in
g
o
f
p
ar
am
eter
s
in
AR
I
MA
,
p
r
o
p
h
et,
an
d
ex
p
o
n
en
tial
s
m
o
o
th
in
g
m
o
d
els
to
en
h
an
ce
m
o
d
el
r
esp
o
n
s
iv
en
e
s
s
.
E
x
p
an
d
in
g
GE
test
in
g
ac
r
o
s
s
v
ar
io
u
s
in
d
u
s
tr
ial
s
ec
to
r
s
o
r
g
lo
b
al
m
ar
k
ets
is
also
cr
u
cial
to
v
alid
ate
its
g
e
n
er
aliza
b
ilit
y
an
d
r
o
b
u
s
tn
ess
.
Ultim
ately
,
th
is
r
esear
ch
u
n
d
e
r
s
co
r
es th
e
p
r
o
m
is
e
o
f
ev
o
l
u
tio
n
ar
y
co
m
p
u
tatio
n
in
f
in
an
cial
m
ar
k
et
an
aly
s
is
an
d
p
av
es th
e
way
f
o
r
th
e
d
ev
elo
p
m
en
t
o
f
m
o
r
e
ad
a
p
tiv
e
an
d
r
eliab
le
p
r
e
d
ictiv
e
alg
o
r
ith
m
s
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
e
p
u
b
licatio
n
c
o
s
t
was
p
ar
tially
s
u
p
p
o
r
te
d
b
y
Sch
o
o
l
o
f
Data
Scien
ce
,
Ma
th
em
atics
an
d
I
n
f
o
r
m
atics I
PB
Un
iv
er
s
ity
an
d
p
ar
tially
f
u
n
d
e
d
b
y
th
e
au
th
o
r
’
s
p
er
s
o
n
al
c
o
n
tr
ib
u
tio
n
.
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
t
r
ib
u
to
r
R
o
les
T
a
x
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
i
d
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
Ad
ity
a
Ku
s
u
m
a
Sety
an
eg
ar
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
I
m
a
s
S
u
k
a
e
s
i
h
S
i
t
a
n
g
g
a
n
g
✓
✓
✓
✓
✓
✓
✓
✓
Mu
s
h
th
o
f
a
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
t
h
o
r
s
tates
th
at
n
o
f
i
n
an
cial
o
r
p
e
r
s
o
n
al
r
elatio
n
s
h
ip
s
ex
is
t
th
at
c
o
u
ld
b
e
p
er
ce
iv
ed
as
in
f
lu
en
cin
g
th
e
f
in
d
in
g
s
o
f
th
i
s
wo
r
k
.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
a
t
a
s
e
t
u
s
ed
i
n
t
h
i
s
s
tu
d
y
w
a
s
o
b
t
a
i
n
ed
f
r
o
m
Y
ah
o
o
F
i
n
an
c
e
.
T
h
e
d
a
t
a
w
er
e
d
i
r
ec
t
l
y
d
o
w
n
lo
ad
e
d
f
r
o
m
h
t
t
p
s
:
/
/f
in
a
n
ce
.
y
a
h
o
o
.
c
o
m
/
an
d
a
r
e
a
v
a
i
l
a
b
l
e
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
e
s
t
to
th
e
c
o
r
r
e
s
p
o
n
d
in
g
a
u
t
h
o
r
.
RE
F
E
R
E
NC
E
S
[
1
]
A
.
S
.
S
a
u
d
a
n
d
S
.
S
h
a
k
y
a
,
“
Te
c
h
n
i
c
a
l
i
n
d
i
c
a
t
o
r
e
mp
o
w
e
r
e
d
i
n
t
e
l
l
i
g
e
n
t
st
r
a
t
e
g
i
e
s
t
o
p
r
e
d
i
c
t
s
t
o
c
k
t
r
a
d
i
n
g
si
g
n
a
l
s
,
”
J
o
u
rn
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
rk
e
t
,
a
n
d
C
o
m
p
l
e
x
i
t
y
,
v
o
l
.
1
0
,
n
o
.
4
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
o
i
t
mc
.
2
0
2
4
.
1
0
0
3
9
8
.
[
2
]
J.
A
y
a
l
a
,
M
.
G
.
-
T
o
r
r
e
s,
J.
L
.
V
.
N
o
g
u
e
r
a
,
F
.
G
.
-
V
e
l
a
,
a
n
d
F
.
D
i
v
i
n
a
,
“
Te
c
h
n
i
c
a
l
a
n
a
l
y
si
s
st
r
a
t
e
g
y
o
p
t
i
m
i
z
a
t
i
o
n
u
si
n
g
a
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
i
n
s
t
o
c
k
m
a
r
k
e
t
i
n
d
i
c
e
s
,
”
K
n
o
w
l
e
d
g
e
-
B
a
s
e
d
S
y
st
e
m
s
,
v
o
l
.
2
2
5
,
A
u
g
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
k
n
o
s
y
s.2
0
2
1
.
1
0
7
1
1
9
.
[
3
]
P
.
C
a
r
v
a
l
h
o
,
J.
M
é
g
a
n
e
,
N
.
L
o
u
r
e
n
ç
o
,
a
n
d
P
.
M
a
c
h
a
d
o
,
“
C
o
n
t
e
x
t
mat
t
e
r
s:
a
d
a
p
t
i
v
e
m
u
t
a
t
i
o
n
f
o
r
g
r
a
mm
a
r
s,”
G
e
n
e
t
i
c
Pro
g
ra
m
m
i
n
g
(
E
u
r
o
G
P
2
0
2
3
)
,
C
h
a
m,
S
w
i
t
z
e
r
l
a
n
d
:
S
p
r
i
n
g
e
r
,
M
a
r
.
2
0
2
3
,
p
p
.
1
1
7
-
1
3
2
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
031
-
2
9
5
7
3
-
7
_8
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Tech
n
ica
l a
n
a
lysi
s
mo
d
el
fo
r
s
to
ck
p
r
ed
ictio
n
u
s
in
g
a
g
r
a
mm
a
tica
l
…
(
A
d
itya
K
u
s
u
ma
S
etya
n
eg
a
r
a
)
1245
[
4
]
J.
M
e
g
a
n
e
,
N
.
L
o
u
r
e
n
c
o
,
a
n
d
P
.
M
a
c
h
a
d
o
,
“
P
r
o
b
a
b
i
l
i
st
i
c
st
r
u
c
t
u
r
e
d
g
r
a
mm
a
t
i
c
a
l
e
v
o
l
u
t
i
o
n
,
”
i
n
2
0
2
2
I
EEE
C
o
n
g
res
s
o
n
Ev
o
l
u
t
i
o
n
a
r
y
C
o
m
p
u
t
a
t
i
o
n
(
C
EC
)
,
P
a
d
u
a
,
I
t
a
l
y
,
2
0
2
2
,
p
p
.
1
-
9
,
d
o
i
:
1
0
.
1
1
0
9
/
C
E
C
5
5
0
6
5
.
2
0
2
2
.
9
8
7
0
3
9
7
.
[
5
]
I
.
G
.
Tso
u
l
o
s,
C
.
S
t
y
l
i
o
s,
a
n
d
V
.
C
h
a
r
a
l
a
m
p
o
u
s
,
“
C
O
V
I
D
1
9
p
r
e
d
i
c
t
i
v
e
m
o
d
e
l
s
b
a
se
d
o
n
g
r
a
mm
a
t
i
c
a
l
e
v
o
l
u
t
i
o
n
,
”
S
N
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
4
,
n
o
.
2
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s4
2
9
7
9
-
022
-
0
1
6
3
2
-
w
.
[
6
]
J.
Jes
c
h
k
e
,
D
.
S
u
n
,
A
.
Jams
h
i
d
n
e
j
a
d
,
a
n
d
B
.
D
.
S
c
h
u
t
t
e
r
,
“
G
r
a
mm
a
t
i
c
a
l
-
e
v
o
l
u
t
i
o
n
-
b
a
se
d
p
a
r
a
met
e
r
i
z
e
d
m
o
d
e
l
p
r
e
d
i
c
t
i
v
e
c
o
n
t
r
o
l
f
o
r
u
r
b
a
n
t
r
a
f
f
i
c
n
e
t
w
o
r
k
s
,
”
C
o
n
t
ro
l
E
n
g
i
n
e
e
r
i
n
g
Pra
c
t
i
c
e
,
v
o
l
.
1
3
2
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
n
e
n
g
p
r
a
c
.
2
0
2
2
.
1
0
5
4
3
1
.
[
7
]
T.
P
.
P
a
w
l
a
k
a
n
d
M
.
O
’
N
e
i
l
l
,
“
G
r
a
m
mat
i
c
a
l
e
v
o
l
u
t
i
o
n
f
o
r
c
o
n
st
r
a
i
n
t
s
y
n
t
h
e
si
s fo
r
m
i
x
e
d
-
i
n
t
e
g
e
r
l
i
n
e
a
r
p
r
o
g
r
a
m
mi
n
g
,
”
S
w
a
rm
a
n
d
Ev
o
l
u
t
i
o
n
a
r
y
C
o
m
p
u
t
a
t
i
o
n
,
v
o
l
.
6
4
,
J
u
l
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
sw
e
v
o
.
2
0
2
1
.
1
0
0
8
9
6
.
[
8
]
A
.
V
.
B
.
R
o
d
r
í
g
u
e
z
,
B
.
I
.
A
.
-
C
e
r
e
z
o
,
a
n
d
C
.
A
.
C
.
C
o
e
l
l
o
,
“
I
mp
r
o
v
i
n
g
mu
l
t
i
-
o
b
j
e
c
t
i
v
e
e
v
o
l
u
t
i
o
n
a
r
y
a
l
g
o
r
i
t
h
ms
u
s
i
n
g
g
r
a
mm
a
t
i
c
a
l
e
v
o
l
u
t
i
o
n
,
”
S
w
a
rm
a
n
d
Ev
o
l
u
t
i
o
n
a
r
y
C
o
m
p
u
t
a
t
i
o
n
,
v
o
l
.
8
4
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
sw
e
v
o
.
2
0
2
3
.
1
0
1
4
3
4
.
[
9
]
J.
M
é
g
a
n
e
,
N
.
L
o
u
r
e
n
ç
o
,
a
n
d
P
.
M
a
c
h
a
d
o
,
“
C
o
-
e
v
o
l
u
t
i
o
n
a
r
y
p
r
o
b
a
b
i
l
i
s
t
i
c
st
r
u
c
t
u
r
e
d
g
r
a
mm
a
t
i
c
a
l
e
v
o
l
u
t
i
o
n
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
G
e
n
e
t
i
c
a
n
d
E
v
o
l
u
t
i
o
n
a
ry
C
o
m
p
u
t
a
t
i
o
n
C
o
n
f
e
re
n
c
e
,
N
e
w
Y
o
r
k
,
N
Y
,
U
S
A
:
A
C
M
,
J
u
l
.
2
0
2
2
,
p
p
.
9
9
1
–
999
,
d
o
i
:
1
0
.
1
1
4
5
/
3
5
1
2
2
9
0
.
3
5
2
8
8
3
3
.
[
1
0
]
C
.
R
y
a
n
,
M
.
K
s
h
i
r
sag
a
r
,
P
.
C
h
a
u
d
h
a
r
i
,
a
n
d
R
.
J
a
c
h
a
k
,
“
G
ETS:
g
r
a
m
mat
i
c
a
l
e
v
o
l
u
t
i
o
n
b
a
se
d
o
p
t
i
mi
z
a
t
i
o
n
o
f
sm
o
o
t
h
i
n
g
p
a
r
a
m
e
t
e
r
s
i
n
u
n
i
v
a
r
i
a
t
e
t
i
me
seri
e
s
f
o
r
e
c
a
st
i
n
g
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
1
2
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Ag
e
n
t
s
a
n
d
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
S
C
I
TEPR
ESS
-
S
c
i
e
n
c
e
a
n
d
Te
c
h
n
o
l
o
g
y
P
u
b
l
i
c
a
t
i
o
n
s,
2
0
2
0
,
p
p
.
5
9
5
–
6
0
2
,
d
o
i
:
1
0
.
5
2
2
0
/
0
0
0
8
9
6
3
3
0
5
9
5
0
6
0
2
.
[
1
1
]
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
c
o
m
p
r
e
h
e
n
si
v
e
e
v
a
l
u
a
t
i
o
n
o
f
e
n
sem
b
l
e
l
e
a
r
n
i
n
g
f
o
r
st
o
c
k
-
ma
r
k
e
t
p
r
e
d
i
c
t
i
o
n
,
”
J
o
u
rn
a
l
o
f
Bi
g
D
a
t
a
,
v
o
l
.
7
,
n
o
.
1
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
0
5
3
7
-
0
2
0
-
0
0
2
9
9
-
5.
[
1
2
]
T.
A
g
g
r
a
w
a
l
a
n
d
M
.
D
h
a
w
a
n
,
“
S
t
a
t
e
-
of
-
t
h
e
-
a
r
t
v
s
p
r
o
m
i
n
e
n
t
m
o
d
e
l
s
:
a
n
e
mp
i
r
i
c
a
l
a
n
a
l
y
si
s
o
f
v
a
r
i
o
u
s
n
e
u
r
a
l
n
e
t
w
o
r
k
s
o
n
st
o
c
k
mark
e
t
p
r
e
d
i
c
t
i
o
n
,
”
E
n
g
i
n
e
e
ri
n
g
a
r
c
h
i
v
e
,
2
0
2
2
,
d
o
i
:
1
0
.
3
1
2
2
4
/
2
7
4
5
.
[
1
3
]
Y
.
Li
a
n
d
Y
.
P
a
n
,
“
A
n
o
v
e
l
e
n
se
mb
l
e
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
f
o
r
st
o
c
k
p
r
e
d
i
c
t
i
o
n
b
a
se
d
o
n
s
t
o
c
k
p
r
i
c
e
s
a
n
d
n
e
w
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
D
a
t
a
S
c
i
e
n
c
e
a
n
d
An
a
l
y
t
i
c
s
,
v
o
l
.
1
3
,
n
o
.
2
,
p
p
.
1
3
9
–
1
4
9
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
1
0
6
0
-
021
-
0
0
2
7
9
-
9.
[
1
4
]
U
.
F
.
I
.
A
b
d
u
l
r
a
h
ma
n
,
N
.
U
ssi
p
h
,
a
n
d
B
.
H
.
-
A
c
q
u
a
h
,
“
A
h
y
b
r
i
d
A
R
I
M
A
-
LSTM
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
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
e
r E
n
g
i
n
e
e
ri
n
g
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
2
,
n
o
.
8
,
p
p
.
4
8
–
5
1
,
2
0
2
0
.
[1
5
]
A
.
S
u
b
a
si
,
“
D
a
t
a
p
r
e
p
r
o
c
e
ss
i
n
g
,
”
i
n
Pra
c
t
i
c
a
l
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
f
o
r
D
a
t
a
An
a
l
y
si
s
U
si
n
g
Py
t
h
o
n
,
El
s
e
v
i
e
r
,
2
0
2
0
,
p
p
.
2
7
–
89
,
d
o
i
:
1
0
.
1
0
1
6
/
B
9
7
8
-
0
-
12
-
8
2
1
3
7
9
-
7
.
0
0
0
0
2
-
3.
[1
6
]
R
.
B
.
-
M
.
-
T
o
n
i
s,
R
.
B
u
c
e
a
,
a
n
d
M
.
To
n
i
s,
“
A
u
t
o
ma
t
i
n
g
sc
i
e
n
t
i
f
i
c
p
a
p
e
r
scree
n
i
n
g
w
i
t
h
b
a
c
k
u
s
-
n
a
u
r
f
o
r
m
(
B
N
F
)
g
r
a
m
mars
,
”
D
i
d
a
c
t
i
c
a
D
a
n
u
b
i
e
n
si
s
,
v
o
l
.
4
,
n
o
.
1
,
2
0
2
4
,
p
p
.
4
6
-
57
.
[1
7
]
D
.
K
.
S
h
a
r
ma,
M
.
C
h
a
t
t
e
r
j
e
e
,
G
.
K
a
u
r
,
a
n
d
S
.
V
a
v
i
l
a
l
a
,
“
D
e
e
p
l
e
a
r
n
i
n
g
a
p
p
l
i
c
a
t
i
o
n
s
f
o
r
d
i
sea
se
d
i
a
g
n
o
s
i
s,”
i
n
D
e
e
p
L
e
a
r
n
i
n
g
f
o
r
Me
d
i
c
a
l
A
p
p
l
i
c
a
t
i
o
n
s
w
i
t
h
U
n
i
q
u
e
D
a
t
a
,
E
l
se
v
i
e
r
,
2
0
2
2
,
p
p
.
3
1
–
51
,
d
o
i
:
1
0
.
1
0
1
6
/
B
9
7
8
-
0
-
12
-
8
2
4
1
4
5
-
5
.
0
0
0
0
5
-
8.
[1
8
]
T.
-
T.
-
H
.
P
h
a
n
a
n
d
X
.
H
.
N
g
u
y
e
n
,
“
C
o
mb
i
n
i
n
g
s
t
a
t
i
st
i
c
a
l
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
mo
d
e
l
s
w
i
t
h
A
R
I
M
A
f
o
r
w
a
t
e
r
l
e
v
e
l
f
o
r
e
c
a
s
t
i
n
g
:
t
h
e
c
a
se
o
f
t
h
e
R
e
d
R
i
v
e
r
,
”
A
d
v
a
n
c
e
s
i
n
Wa
t
e
r
Re
s
o
u
rce
s
,
v
o
l
.
1
4
2
,
A
u
g
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
d
v
w
a
t
r
e
s.
2
0
2
0
.
1
0
3
6
5
6
.
[
19
]
E.
D
a
v
e
,
A
.
Le
o
n
a
r
d
o
,
M
.
J
e
a
n
i
c
e
,
a
n
d
N
.
H
a
n
a
f
i
a
h
,
“
F
o
r
e
c
a
s
t
i
n
g
I
n
d
o
n
e
s
i
a
e
x
p
o
r
t
s
u
s
i
n
g
a
h
y
b
r
i
d
m
o
d
e
l
A
R
I
M
A
-
LSTM
,
”
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
7
9
,
p
p
.
4
8
0
–
4
8
7
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
2
1
.
0
1
.
0
3
1
.
[2
0
]
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
.
[2
1
]
B
.
K
.
Jh
a
a
n
d
S
.
P
a
n
d
e
,
“
Ti
me
s
e
r
i
e
s
f
o
r
e
c
a
s
t
i
n
g
mo
d
e
l
f
o
r
su
p
e
r
m
a
r
k
e
t
sal
e
s
u
s
i
n
g
F
B
-
p
r
o
p
h
e
t
,
”
i
n
Pro
c
e
e
d
i
n
g
s
-
5
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
i
n
g
M
e
t
h
o
d
o
l
o
g
i
e
s
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
,
I
C
C
MC
2
0
2
1
,
2
0
2
1
,
p
p
.
5
4
7
–
5
5
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
M
C
5
1
0
1
9
.
2
0
2
1
.
9
4
1
8
0
3
3
.
[2
2
]
J.
M
.
S
a
n
g
e
e
t
h
a
a
n
d
K
.
J.
A
l
f
i
a
,
“
F
i
n
a
n
c
i
a
l
st
o
c
k
mar
k
e
t
f
o
r
e
c
a
st
u
si
n
g
e
v
a
l
u
a
t
e
d
l
i
n
e
a
r
r
e
g
r
e
ss
i
o
n
b
a
se
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
,
”
M
e
a
s
u
r
e
m
e
n
t
:
S
e
n
s
o
rs
,
v
o
l
.
3
1
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
m
e
a
s
e
n
.
2
0
2
3
.
1
0
0
9
5
0
.
[2
3
]
J.
C
h
e
n
g
,
S
.
Ti
w
a
r
i
,
D
.
K
h
a
l
e
d
,
M
.
M
a
h
e
n
d
r
u
,
a
n
d
U
.
S
h
a
h
z
a
d
,
“
F
o
r
e
c
a
st
i
n
g
b
i
t
c
o
i
n
p
r
i
c
e
s
u
si
n
g
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
:
C
o
m
b
i
n
a
t
i
o
n
o
f
M
L,
S
A
R
I
M
A
,
a
n
d
F
a
c
e
b
o
o
k
p
r
o
p
h
e
t
mo
d
e
l
s,
”
T
e
c
h
n
o
l
o
g
i
c
a
l
F
o
re
c
a
s
t
i
n
g
a
n
d
S
o
c
i
a
l
C
h
a
n
g
e
,
v
o
l
.
1
9
8
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
t
e
c
h
f
o
r
e
.
2
0
2
3
.
1
2
2
9
3
8
.
[2
4
]
S
.
R
.
R
i
a
d
y
,
“
S
t
o
c
k
p
r
i
c
e
p
r
e
d
i
c
t
i
o
n
u
si
n
g
p
r
o
p
h
e
t
F
a
c
e
b
o
o
k
a
l
g
o
r
i
t
h
m fo
r
B
B
C
A
a
n
d
TL
K
M
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
s
i
n
D
a
t
a
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
y
st
e
m
s
,
v
o
l
.
4
,
n
o
.
2
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
2
5
0
0
8
/
i
j
a
d
i
s
.
v
4
i
2
.
1
2
5
8
.
[2
5
]
I
.
K
.
S
u
w
i
n
t
a
n
a
,
I
.
G
.
A
.
O
.
S
u
d
i
a
d
n
y
a
n
i
,
a
n
d
N
.
G
.
A
.
P
.
H
.
S
a
p
t
a
r
i
n
i
,
“
D
e
v
e
l
o
p
i
n
g
w
e
b
-
b
a
s
e
d
a
p
p
l
i
c
a
t
i
o
n
o
f
sal
e
s
f
o
r
e
c
a
st
i
n
g
sy
st
e
m
u
si
n
g
t
r
i
p
l
e
e
x
p
o
n
e
n
t
i
a
l
s
mo
o
t
h
i
n
g
met
h
o
d
f
o
r
sma
l
l
a
n
d
me
d
i
u
m
g
a
r
me
n
t
e
n
t
e
r
p
r
i
ses
,
”
i
n
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
(
I
C
S
T
2
0
1
8
)
,
2
0
1
8
,
d
o
i
:
1
0
.
2
9
9
1
/
i
c
st
-
1
8
.
2
0
1
8
.
2
1
5
.
[2
6
]
L.
K
u
mar,
S
.
K
h
e
d
l
e
k
a
r
,
a
n
d
U
.
K
.
K
h
e
d
l
e
k
a
r
,
“
A
c
o
m
p
a
r
a
t
i
v
e
a
ss
e
ssm
e
n
t
o
f
h
o
l
t
w
i
n
t
e
r
e
x
p
o
n
e
n
t
i
a
l
smo
o
t
h
i
n
g
a
n
d
a
u
t
o
r
e
g
r
e
ss
i
v
e
i
n
t
e
g
r
a
t
e
d
mo
v
i
n
g
a
v
e
r
a
g
e
f
o
r
i
n
v
e
n
t
o
r
y
o
p
t
i
mi
z
a
t
i
o
n
i
n
s
u
p
p
l
y
c
h
a
i
n
s,”
S
u
p
p
l
y
C
h
a
i
n
A
n
a
l
y
t
i
c
s
,
v
o
l
.
8
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
s
c
a
.
2
0
2
4
.
1
0
0
0
8
4
.
[2
7
]
L.
L
u
s
i
n
d
a
h
a
n
d
E
.
S
u
mi
r
a
t
,
“
I
mp
l
e
m
e
n
t
a
t
i
o
n
o
f
f
i
b
o
n
a
c
c
i
r
e
t
r
a
c
e
m
e
n
t
s
a
n
d
e
x
p
o
n
e
n
t
i
a
l
m
o
v
i
n
g
a
v
e
r
a
g
e
(
E
M
A
)
t
r
a
d
i
n
g
s
t
r
a
t
e
g
y
i
n
I
n
d
o
n
e
si
a
s
t
o
c
k
e
x
c
h
a
n
g
e
,
”
E
u
r
o
p
e
a
n
J
o
u
r
n
a
l
o
f
Bu
s
i
n
e
ss
a
n
d
M
a
n
a
g
e
m
e
n
t
R
e
se
a
rc
h
,
v
o
l
.
6
,
n
o
.
4
,
p
p
.
4
0
2
–
40
8
,
A
u
g
.
2
0
2
1
,
d
o
i
:
1
0
.
2
4
0
1
8
/
e
j
b
mr
.
2
0
2
1
.
6
.
4
.
1
0
3
3
.
[2
8
]
S
.
M
.
A
y
e
n
e
a
n
d
A
.
M
.
Y
i
b
r
e
,
“
W
i
n
d
p
o
w
e
r
p
r
e
d
i
c
t
i
o
n
b
a
se
d
o
n
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
s
:
t
h
e
c
a
s
e
o
f
A
d
a
m
a
w
i
n
d
f
a
r
m
,
”
H
e
l
i
y
o
n
,
v
o
l
.
1
0
,
n
o
.
2
1
,
N
o
v
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
h
e
l
i
y
o
n
.
2
0
2
4
.
e
3
9
5
7
9
.
[
29
]
T.
I
i
d
a
,
“
I
d
e
n
t
i
f
y
i
n
g
c
a
u
s
e
s
o
f
e
r
r
o
r
s
b
e
t
w
e
e
n
t
w
o
w
a
v
e
-
r
e
l
a
t
e
d
d
a
t
a
u
s
i
n
g
p
e
r
f
o
r
m
a
n
c
e
m
e
t
r
i
c
s,
”
A
p
p
l
i
e
d
O
c
e
a
n
R
e
se
a
rc
h
,
v
o
l
.
1
4
8
,
J
u
l
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
p
o
r
.
2
0
2
4
.
1
0
4
0
2
4
.
[3
0
]
A
.
M
.
K
h
a
n
a
n
d
M
.
O
si
ń
s
k
a
,
“
C
o
mp
a
r
i
n
g
f
o
r
e
c
a
st
i
n
g
a
c
c
u
r
a
c
y
o
f
s
e
l
e
c
t
e
d
g
r
e
y
a
n
d
t
i
m
e
s
e
r
i
e
s
m
o
d
e
l
s
b
a
s
e
d
o
n
e
n
e
r
g
y
c
o
n
su
mp
t
i
o
n
i
n
B
r
a
z
i
l
a
n
d
I
n
d
i
a
,
”
E
x
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
.
2
1
2
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
2
.
1
1
8
8
4
0
.
[3
1
]
Ü
.
A
ğ
b
u
l
u
t
,
A
.
E.
G
ü
r
e
l
,
a
n
d
Y
.
B
i
ç
e
n
,
“
P
r
e
d
i
c
t
i
o
n
o
f
d
a
i
l
y
g
l
o
b
a
l
so
l
a
r
r
a
d
i
a
t
i
o
n
u
si
n
g
d
i
f
f
e
r
e
n
t
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
:
e
v
a
l
u
a
t
i
o
n
a
n
d
c
o
m
p
a
r
i
s
o
n
,
”
Re
n
e
w
a
b
l
e
a
n
d
S
u
st
a
i
n
a
b
l
e
En
e
rg
y
R
e
v
i
e
w
s
,
v
o
l
.
1
3
5
,
J
a
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
s
e
r
.
2
0
2
0
.
1
1
0
1
1
4
.
[3
2
]
D
.
C
h
i
c
c
o
,
M
.
J
.
W
a
r
r
e
n
s,
a
n
d
G
.
Ju
r
man
,
“
Th
e
c
o
e
f
f
i
c
i
e
n
t
o
f
d
e
t
e
r
mi
n
a
t
i
o
n
R
-
sq
u
a
r
e
d
i
s
m
o
r
e
i
n
f
o
r
m
a
t
i
v
e
t
h
a
n
S
M
A
P
E
,
M
A
E,
M
A
P
E,
M
S
E
a
n
d
R
M
S
E
i
n
r
e
g
r
e
ss
i
o
n
a
n
a
l
y
si
s
e
v
a
l
u
a
t
i
o
n
,
”
P
e
e
rJ
C
o
m
p
u
t
e
r S
c
i
e
n
c
e
,
v
o
l
.
7
,
Ju
l
.
2
0
2
1
,
d
o
i
:
1
0
.
7
7
1
7
/
p
e
e
r
j
-
c
s
.
6
2
3
.
[3
3
]
J.
Y
u
a
n
,
J.
Li
,
a
n
d
J.
H
a
o
,
“
A
r
e
l
i
a
b
l
e
e
n
sem
b
l
e
f
o
r
e
c
a
s
t
i
n
g
m
o
d
e
l
i
n
g
a
p
p
r
o
a
c
h
f
o
r
c
o
m
p
l
e
x
t
i
me
ser
i
e
s
w
i
t
h
d
i
st
r
i
b
u
t
i
o
n
a
l
l
y
r
o
b
u
st
o
p
t
i
m
i
z
a
t
i
o
n
,
”
C
o
m
p
u
t
e
rs
a
n
d
O
p
e
r
a
t
i
o
n
s
Re
se
a
r
c
h
,
v
o
l
.
1
7
3
,
Ja
n
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
r
.
2
0
2
4
.
1
0
6
8
3
1
.
[3
4
]
L.
Li
,
J.
L
o
n
g
,
a
n
d
M
.
Y
u
a
n
,
“
N
o
v
e
l
w
i
n
d
s
p
e
e
d
e
n
s
e
mb
l
e
f
o
r
e
c
a
st
i
n
g
s
y
st
e
m
b
a
se
d
o
n
t
h
e
c
r
i
t
i
c
w
e
i
g
h
i
n
g
p
r
i
n
c
i
p
l
e
o
f
f
u
z
z
y
i
n
f
o
r
mat
i
o
n
g
r
a
n
u
l
a
t
i
o
n
a
n
d
r
e
v
e
r
s
e
mi
x
e
d
-
f
r
e
q
u
e
n
c
y
mo
d
e
l
i
n
g
,
”
E
n
e
r
g
y
,
v
o
l
.
3
3
0
,
S
e
p
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
e
r
g
y
.
2
0
2
5
.
1
3
6
4
1
9
.
[3
5
]
H
.
W
u
a
n
d
D
.
L
e
v
i
n
so
n
,
“
Th
e
e
n
s
e
mb
l
e
a
p
p
r
o
a
c
h
t
o
f
o
r
e
c
a
st
i
n
g
:
a
r
e
v
i
e
w
a
n
d
s
y
n
t
h
e
s
i
s,”
T
r
a
n
s
p
o
rt
a
t
i
o
n
R
e
se
a
rc
h
P
a
r
t
C
:
Em
e
rg
i
n
g
T
e
c
h
n
o
l
o
g
i
e
s
,
v
o
l
.
1
3
2
,
N
o
v
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
t
r
c
.
2
0
2
1
.
1
0
3
3
5
7
.
[3
6
]
H
.
M
a
,
M
.
L
i
,
S
.
L
v
,
L.
W
a
n
g
,
a
n
d
S
.
D
e
n
g
,
“
R
o
u
l
e
t
t
e
w
h
e
e
l
-
b
a
s
e
d
l
e
v
e
l
l
e
a
r
n
i
n
g
e
v
o
l
u
t
i
o
n
a
r
y
a
l
g
o
r
i
t
h
m
f
o
r
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
o
f
h
i
g
h
-
d
i
me
n
si
o
n
a
l
d
a
t
a
,
”
A
p
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
6
3
,
S
e
p
.
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
9
4
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.