I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
3
7
,
No
.
3
,
Ma
r
ch
20
2
5
,
p
p
.
1
96
4
~
1
97
5
I
SS
N:
2
502
-
4
7
52
,
DOI
:
1
0
.
1
1
5
9
1
/ijee
cs
.v
3
7
.
i
3
.
pp
1
96
4
-
1
97
5
1964
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Foreca
sting
bit
co
in price
f
luc
tuatio
ns: a tim
e series
ana
ly
sis
a
ppro
a
ch f
o
r pre
dictive
mo
delling
Am
ine Ba
t
s
i
1
,
2
,
M
o
ha
m
ed
B
i
niz
1
,
3
,
Ra
chid E
l A
y
a
chi
1
,
2
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
La
b
o
r
a
t
o
r
y
TI
A
D
,
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
s
a
n
d
Te
c
h
n
i
c
s,
S
u
l
t
a
n
M
o
u
l
a
y
S
l
i
ma
n
e
U
n
i
v
e
r
si
t
y
,
B
e
n
i
M
e
l
l
a
l
,
M
o
r
o
c
c
o
2
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
s
a
n
d
Te
c
h
n
i
c
s
,
S
u
l
t
a
n
M
o
u
l
a
y
S
l
i
m
a
n
e
U
n
i
v
e
r
s
i
t
y
,
B
e
n
i
M
e
l
l
a
l
,
M
o
r
o
c
c
o
3
F
a
c
u
l
t
y
o
f
P
o
l
y
d
i
s
c
i
p
l
i
n
a
r
y
,
S
u
l
t
a
n
M
o
u
l
a
y
S
l
i
ma
n
e
U
n
i
v
e
r
si
t
y
,
B
e
n
i
M
e
l
l
a
l
,
M
o
r
o
c
c
o
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
11
,
2
0
2
4
R
ev
is
ed
Sep
28
,
2
0
2
4
Acc
ep
ted
Oct
7
,
2
0
2
4
Th
e
re
c
e
n
t
flu
c
tu
a
ti
o
n
s
in
t
h
e
p
r
ice
o
f
Bit
c
o
in
,
m
a
rk
e
d
b
y
b
o
th
s
ig
n
ifi
c
a
n
t
in
c
re
a
se
s
a
n
d
su
b
se
q
u
e
n
t
d
e
c
re
a
s
e
s,
h
a
s
a
tt
ra
c
ted
m
e
d
ia
a
n
d
p
u
b
li
c
a
tt
e
n
ti
o
n
.
Co
n
se
q
u
e
n
tl
y
,
m
a
n
y
re
se
a
rc
h
e
rs
h
a
v
e
e
x
p
l
o
re
d
v
a
rio
u
s
fa
c
to
rs
i
n
flu
e
n
c
i
n
g
Bit
c
o
in
’
s
p
rice
a
n
d
t
h
e
u
n
d
e
rly
i
n
g
p
a
tt
e
r
n
s
o
f
it
s
flu
c
tu
a
ti
o
n
s.
Th
is
p
a
p
e
r
a
ims
to
p
re
d
ict
a
n
d
a
n
a
ly
se
s
th
e
f
a
c
to
rs
a
ffe
c
ti
n
g
Bit
c
o
i
n
’
s
p
rice
b
y
c
re
a
ti
n
g
a
u
n
i
q
u
e
d
a
tas
e
t
wit
h
n
e
a
rly
4
0
fe
a
tu
re
s
a
n
d
d
e
riv
i
n
g
two
c
h
il
d
d
a
tas
e
ts
u
sin
g
c
o
rre
latio
n
a
n
d
m
u
t
u
a
l
i
n
fo
rm
a
ti
o
n
a
s
fe
a
tu
re
se
lec
ti
o
n
t
e
c
h
n
iq
u
e
s.
Ad
d
it
i
o
n
a
ll
y
,
we
train
m
a
c
h
in
e
l
e
a
rn
in
g
m
o
d
e
ls,
i
n
c
lu
d
in
g
li
n
e
a
r
re
g
re
ss
io
n
(LR),
e
x
trem
e
g
ra
d
ien
t
b
o
o
sti
n
g
(XG
Bo
o
st),
s
u
p
p
o
rt
v
e
c
to
r
r
e
g
re
ss
io
n
(S
VR),
F
a
c
e
b
o
o
k
P
ro
p
h
e
t
(
F
B
P
ro
p
h
e
t),
a
n
d
b
id
i
re
c
ti
o
n
a
l
g
a
ted
re
c
u
rre
n
t
uni
t
(BI
-
G
RU),
to
p
re
d
ict
Bit
c
o
in
’
s
n
e
x
t
-
d
a
y
p
rice
.
T
h
e
m
o
d
e
l
’
s
p
e
rfo
rm
a
n
c
e
is
e
v
a
lu
a
ted
u
sin
g
m
e
a
n
sq
u
a
re
e
rro
r
(M
S
E),
m
e
a
n
a
b
so
lu
te
e
rro
r
(M
AE),
m
e
a
n
a
b
so
lu
te
p
e
rc
e
n
tag
e
e
rro
r
(M
APE
),
a
n
d
R2
s
c
o
re
m
e
tri
c
s.
Ou
r
fin
d
i
n
g
s
i
n
d
ica
te
th
a
t
m
a
c
h
in
e
lea
rn
in
g
tec
h
n
iq
u
e
s
a
re
e
ffe
c
ti
v
e
in
p
re
d
ictin
g
Bit
c
o
in
’
s
p
rice
a
n
d
c
o
u
l
d
b
e
v
a
lu
a
b
le
fo
r
in
v
e
sto
rs
se
e
k
in
g
t
o
m
a
x
imiz
e
p
ro
fit
s.
K
ey
w
o
r
d
s
:
B
itco
in
C
r
y
p
to
cu
r
r
e
n
cies
Featu
r
e
s
elec
tio
n
Fo
r
ec
asti
n
g
Ma
ch
in
e
lear
n
in
g
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
:
Am
in
e
B
atsi
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
L
ab
o
r
ato
r
y
T
I
AD,
Facu
lty
o
f
Scien
ce
s
an
d
T
ec
h
n
ics
Su
ltan
Mo
u
lay
Sli
m
an
e
Un
iv
e
r
s
ity
B
en
i M
ellal,
Mo
r
o
cc
o
E
m
ail:
b
atsi
am
in
e@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
B
itco
in
,
estab
lis
h
ed
as
a
d
ec
en
tr
alize
d
d
ig
ital
cu
r
r
en
cy
in
2
0
0
8
b
y
th
e
p
s
eu
d
o
n
y
m
o
u
s
f
ig
u
r
e
Sato
s
h
i
Nak
am
o
to
,
r
e
v
o
lu
tio
n
ized
th
e
f
in
an
cial
lan
d
s
ca
p
e
with
its
in
n
o
v
ativ
e
f
r
am
ewo
r
k
o
u
tlin
ed
in
th
e
p
ap
er
titl
ed
“
B
itco
in
:
a
p
ee
r
-
to
-
p
ee
r
(
P
2
P)
elec
tr
o
n
ic
ca
s
h
s
y
s
tem
”
[
1
]
.
As
a
c
r
y
p
t
o
cu
r
r
e
n
cy
,
B
itco
in
r
elies
o
n
cr
y
p
to
g
r
ap
h
ic
tech
n
iq
u
es
f
o
r
s
ec
u
r
ity
[
2
]
,
o
p
er
ates
in
d
ep
e
n
d
en
tly
o
f
g
o
v
er
n
m
en
tal
o
r
f
in
an
cial
co
n
tr
o
l,
an
d
h
as
b
ec
o
m
e
r
e
n
o
wn
e
d
f
o
r
its
in
h
er
en
t
v
o
latilit
y
[
3
]
,
[
4
]
.
T
h
e
p
r
im
ar
y
ch
allen
g
e
i
n
p
r
e
d
ic
tin
g
B
itco
in
p
r
ices
lies
in
its
m
ar
k
et
d
y
n
am
ics,
ch
ar
ac
ter
ized
b
y
r
ap
id
an
d
s
u
b
s
tan
tial
p
r
ice
m
o
v
em
e
n
ts
with
in
s
h
o
r
t
tim
e
f
r
am
es.
As
a
r
elativ
ely
n
ew
a
n
d
v
o
lat
ile
ass
et
class
,
B
itco
in
’
s
p
r
ice
f
o
r
ec
asti
n
g
is
co
m
p
licated
b
y
n
u
m
er
o
u
s
f
ac
t
o
r
s
,
in
clu
d
in
g
tech
n
o
lo
g
ical
a
d
v
an
ce
m
en
ts
,
g
o
v
er
n
m
e
n
t
s
u
p
p
o
r
t
an
d
r
eg
u
latio
n
[
5
]
,
s
o
cio
ec
o
n
o
m
ic
c
h
an
g
es
[
6
]
,
s
h
if
ts
in
in
v
esto
r
s
en
tim
en
t
[
7
]
,
an
d
th
e
im
p
ac
t o
f
ev
en
ts
lik
e
th
e
C
OVI
D
-
1
9
p
an
d
em
i
c
[
8
]
,
[
9
]
.
I
n
th
e
d
o
m
ain
o
f
cr
y
p
to
cu
r
r
en
cy
m
ar
k
et
p
r
e
d
ictio
n
[
1
0
]
,
b
o
t
h
d
ee
p
lear
n
in
g
an
d
tr
ad
itio
n
a
l
m
ac
h
in
e
lear
n
in
g
m
o
d
els
h
av
e
b
ee
n
em
p
lo
y
ed
.
Sig
n
if
ica
n
t
co
n
tr
ib
u
ti
o
n
s
in
clu
d
e
m
u
lti
-
lay
er
p
e
r
ce
p
tr
o
n
s
(
ML
Ps
)
[
1
1
]
,
wh
ich
h
av
e
d
em
o
n
s
tr
ated
s
u
cc
ess
in
ca
p
tu
r
in
g
co
m
p
lex
p
atter
n
s
in
d
ata
,
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NNs),
k
n
o
wn
f
o
r
th
eir
ef
f
ec
tiv
en
ess
in
ch
ar
ac
te
r
r
ec
o
g
n
iti
o
n
a
n
d
tex
t
class
if
icatio
n
[
1
2
]
-
[
1
4
]
an
d
r
ec
u
r
r
e
n
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
F
o
r
ec
a
s
tin
g
b
itco
in
p
r
ice
flu
ct
u
a
tio
n
s
:
a
time
s
eries
a
n
a
lysi
s
a
p
p
r
o
a
ch
f
o
r
p
r
ed
ictive
…
(
A
min
e
B
a
ts
i
)
1965
n
eu
r
al
n
etwo
r
k
s
(
R
NNs),
wit
h
th
eir
v
ar
ian
ts
L
STM
an
d
GR
U
[
1
5
]
,
[
1
6
]
,
wh
ich
ar
e
p
r
o
f
icien
t
in
m
o
d
elin
g
tim
e
-
d
ep
en
d
e
n
t
d
ata,
as
well
as
co
m
b
in
atio
n
s
o
f
C
NN
an
d
L
STM
[
1
7
]
.
T
r
ad
itio
n
al
m
ac
h
in
e
lear
n
in
g
m
o
d
els
,
s
u
ch
as
lin
ea
r
r
e
g
r
ess
io
n
(
L
R
)
,
s
u
p
p
o
r
t
v
ec
to
r
r
eg
r
e
s
s
io
n
(
SVR
)
,
an
d
ex
tr
em
e
g
r
a
d
ien
t
b
o
o
s
tin
g
(
XGBo
o
s
t)
[
1
8
]
,
o
f
f
er
r
o
b
u
s
t
p
er
f
o
r
m
an
ce
an
d
ar
e
o
f
te
n
ea
s
ier
to
in
ter
p
r
et.
Ad
d
iti
o
n
ally
,
tim
e
s
er
ies
f
o
r
ec
asti
n
g
m
et
h
o
d
s
l
ik
e
au
to
r
eg
r
ess
iv
e
in
teg
r
ated
m
o
v
in
g
av
er
a
g
e
(
AR
I
MA
)
,
a
u
to
r
e
g
r
ess
i
on
(
AR
)
,
an
d
m
o
v
in
g
av
er
a
g
e
(
MA
)
[
1
9
]
,
as
well
as
Face
b
o
o
k
Pro
p
h
et
(
FB
Pro
p
h
et
)
,
h
av
e
b
ee
n
ap
p
lied
t
o
p
r
ed
ict
cr
y
p
to
cu
r
r
en
c
y
p
r
ices
[
2
0
]
,
[
2
1
]
.
Desp
ite
th
ese
ad
v
an
ce
m
e
n
ts
,
p
r
ed
ictin
g
B
itco
in
p
r
ices
r
e
m
ain
s
a
s
ig
n
if
ican
t
c
h
allen
g
e
d
u
e
to
t
h
e
co
m
p
lex
ity
a
n
d
v
o
latilit
y
o
f
th
e
m
ar
k
et.
E
x
is
tin
g
m
o
d
els
o
f
ten
f
ail
to
ac
co
u
n
t
f
o
r
th
e
m
u
ltifa
ce
ted
f
ac
to
r
s
in
f
lu
en
cin
g
B
itco
in
p
r
ices.
T
h
er
e
is
a
n
ee
d
f
o
r
a
co
m
p
r
e
h
en
s
iv
e
m
o
d
el
th
at
in
te
g
r
ate
s
a
wid
e
r
a
n
g
e
o
f
v
ar
iab
les to
im
p
r
o
v
e
p
r
ed
ictio
n
ac
cu
r
ac
y
.
T
h
is
r
esear
ch
aim
s
t
o
d
e
v
el
o
p
a
n
ac
cu
r
ate
an
d
r
elia
b
le
m
o
d
el
f
o
r
p
r
ed
ictin
g
B
itco
in
p
r
ices
b
y
co
m
p
ilin
g
d
ata
f
r
o
m
d
iv
e
r
s
e
d
o
m
ai
n
s
th
at
in
f
lu
en
ce
B
itco
in
’
s
p
r
ice
m
o
v
em
en
ts
.
T
h
ese
d
o
m
ai
n
s
in
clu
d
e
B
itco
in
-
s
p
ec
i
f
ic
v
ar
iab
les
(
o
p
en
,
h
ig
h
,
clo
s
e,
an
d
lo
w
)
,
tech
n
o
lo
g
ical
asp
ec
ts
o
f
B
itco
in
cr
y
p
t
o
cu
r
r
e
n
cies,
m
ar
k
et
f
ea
tu
r
es,
co
m
m
o
d
ities
,
p
u
b
lic
r
ec
o
g
n
itio
n
,
g
e
o
p
o
liti
ca
l
f
ac
to
r
s
,
an
d
m
ar
k
et
s
en
tim
en
t
in
d
ex
es,
alo
n
g
with
tech
n
ical
in
d
icato
r
s
.
B
y
in
teg
r
atin
g
th
ese
f
ac
to
r
s
in
to
a
co
m
p
r
eh
en
s
iv
e
d
ataset,
we
s
ee
k
to
ca
p
tu
r
e
th
e
co
m
p
lex
ity
o
f
B
itco
in
p
r
ice
d
y
n
am
ics
m
o
r
e
ef
f
ec
tiv
ely
t
h
an
p
r
ev
i
o
u
s
m
o
d
els.
T
h
e
f
o
ll
o
win
g
s
ec
tio
n
s
will
d
em
o
n
s
tr
ate
th
e
m
eth
o
d
o
lo
g
y
u
s
ed
to
g
ath
er
an
d
p
r
e
p
r
o
ce
s
s
th
e
d
ata,
th
e
m
o
d
el
d
ev
elo
p
m
e
n
t p
r
o
ce
s
s
,
an
d
th
e
ev
alu
atio
n
o
f
th
e
m
o
d
el
’
s
p
e
r
f
o
r
m
an
ce
.
T
h
e
r
esu
lts
will
b
e
d
is
cu
s
s
ed
in
th
e
co
n
tex
t
o
f
th
eir
r
elev
an
ce
t
o
th
e
f
ield
,
h
ig
h
lig
h
tin
g
h
o
w
o
u
r
a
p
p
r
o
ac
h
ad
d
r
ess
es
th
e
lim
itatio
n
s
o
f
p
r
ev
i
o
u
s
wo
r
k
s
an
d
co
n
tr
ib
u
tes
to
th
e
ad
v
an
ce
m
e
n
t o
f
c
r
y
p
to
c
u
r
r
e
n
c
y
p
r
ice
p
r
ed
ictio
n
m
o
d
els.
2.
M
E
T
H
O
D
T
h
is
s
ec
tio
n
p
r
esen
ts
th
e
m
et
h
o
d
o
lo
g
y
u
s
ed
i
n
th
is
s
tu
d
y
,
as
illu
s
tr
ated
in
Fig
u
r
e
1
.
T
h
e
p
r
im
ar
y
o
b
jectiv
e
is
to
d
ev
el
o
p
an
ac
c
u
r
ate
p
r
ed
ictiv
e
m
o
d
el
f
o
r
f
o
r
ec
asti
n
g
B
itco
in
p
r
ices.
T
o
ac
co
m
p
lis
h
th
is
,
th
e
s
tu
d
y
co
m
b
in
es
h
is
to
r
ical
d
ata
an
aly
s
is
f
r
o
m
d
iv
er
s
e
f
ield
s
an
d
d
o
m
ain
s
,
s
y
s
tem
atic
d
ata
p
r
ep
r
o
ce
s
s
in
g
,
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
es,
m
ac
h
in
e
lear
n
i
n
g
al
g
o
r
ith
m
s
,
an
d
p
e
r
f
o
r
m
an
ce
e
v
alu
atio
n
m
etr
ics.
T
h
ese
s
tep
s
ar
e
d
esig
n
ed
t
o
en
s
u
r
e
t
h
e
m
o
d
el
’
s
r
eliab
ilit
y
an
d
im
p
r
o
v
e
its
p
r
ed
ictiv
e
ac
cu
r
ac
y
.
Fig
u
r
e
1
.
Fo
llo
wed
p
r
o
ce
s
s
in
m
eth
o
d
o
l
o
g
y
2
.
1
.
I
dentif
y
ing
v
a
ria
bles
T
h
e
in
itial
s
tep
i
s
to
id
en
tify
v
ar
iab
les
th
at
ca
n
h
av
e
a
s
ig
n
if
ican
t
im
p
ac
t
o
n
B
itco
in
’
s
p
r
ice.
B
itco
in
b
lo
ck
ch
ain
m
etr
ics,
m
ar
k
et
u
n
ce
r
tain
ty
in
d
ex
es
an
d
g
eo
p
o
liti
ca
l
r
is
k
m
ea
s
u
r
es
ar
e
all
im
p
o
r
tan
t.
T
h
ese
f
ea
tu
r
es
h
av
e
b
ee
n
i
d
en
tifie
d
as
p
r
o
b
ab
le
d
r
i
v
er
s
o
f
B
itco
in
p
r
ice
v
ar
iatio
n
s
,
an
d
th
ey
s
er
v
e
as
th
e
f
o
u
n
d
atio
n
f
o
r
d
e
v
elo
p
in
g
an
e
f
f
ec
t
iv
e
f
o
r
ec
asti
n
g
m
o
d
el.
T
h
e
T
ab
le
1
g
r
o
u
p
s
all
th
e
f
ea
t
u
r
es u
s
ed
in
t
h
e
s
tu
d
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
3
,
Ma
r
ch
20
2
5
:
1
96
4
-
1
97
5
1966
T
ab
le
1
.
Featu
r
es a
n
d
d
escr
ip
t
io
n
s
F
e
a
t
u
r
e
s
D
e
f
i
n
i
t
i
o
n
s
O
p
e
n
Th
e
i
n
i
t
i
a
l
p
r
i
c
e
o
f
B
i
t
c
o
i
n
a
t
t
h
e
b
e
g
i
n
n
i
n
g
o
f
t
r
a
d
i
n
g
sess
i
o
n
.
C
l
o
se
Th
e
f
i
n
a
l
p
r
i
c
e
o
f
B
i
t
c
o
i
n
a
t
t
h
e
e
n
d
o
f
a
t
r
a
d
i
n
g
s
e
ssi
o
n
.
H
i
g
h
Th
e
ma
x
i
mu
m
v
a
l
u
e
o
f
B
i
t
c
o
i
n
p
r
i
c
e
i
n
d
u
r
i
n
g
a
t
r
a
d
i
n
g
p
e
r
i
o
d
.
Lo
w
Th
e
mi
n
i
mu
m
v
a
l
u
e
o
f
B
i
t
c
o
i
n
p
r
i
c
e
i
n
d
u
r
i
n
g
a
t
r
a
d
i
n
g
p
e
r
i
o
d
.
C
r
y
p
t
o
c
u
r
r
e
n
c
y
mar
k
e
t
c
a
p
i
t
a
l
i
z
a
t
i
o
n
Th
e
a
g
g
r
e
g
a
t
e
w
o
r
t
h
o
f
a
l
l
c
r
y
p
t
o
c
u
r
r
e
n
c
i
e
s
i
n
U
S
D
.
B
i
t
c
o
i
n
m
a
r
k
e
t
c
a
p
i
t
a
l
i
z
a
t
i
o
n
Th
e
t
o
t
a
l
mo
n
e
t
a
r
y
v
a
l
u
e
o
f
a
l
l
B
i
t
c
o
i
n
s
i
n
c
i
r
c
u
l
a
t
i
o
n
i
n
U
S
D
.
C
r
y
p
t
o
c
u
r
r
e
n
c
y
mar
k
e
t
c
a
p
i
t
a
l
i
z
a
t
i
o
n
e
x
c
l
u
d
i
n
g
B
i
t
c
o
i
n
Th
e
a
g
g
r
e
g
a
t
e
w
o
r
t
h
o
f
a
l
l
c
r
y
p
t
o
c
u
r
r
e
n
c
i
e
s
e
x
c
l
u
d
i
n
g
B
i
t
c
o
i
n
i
n
U
S
D
.
V
o
l
u
me
Th
e
t
o
t
a
l
q
u
a
n
t
i
t
y
o
f
b
i
t
c
o
i
n
s
t
r
a
d
e
d
d
u
r
i
n
g
a
t
r
a
d
i
n
g
p
e
r
i
o
d
.
C
h
a
n
g
e
Th
e
d
a
i
l
y
p
e
r
c
e
n
t
a
g
e
c
h
a
n
g
e
i
n
t
h
e
w
o
r
t
h
o
f
B
i
t
c
o
i
n
.
B
i
t
c
o
i
n
d
o
m
i
n
a
n
c
e
Th
e
p
e
r
c
e
n
t
a
g
e
o
f
t
h
e
t
o
t
a
l
c
r
y
p
t
o
c
u
r
r
e
n
c
y
mark
e
t
c
a
p
i
t
a
l
i
z
a
t
i
o
n
t
h
a
t
i
s re
p
r
e
se
n
t
e
d
b
y
B
i
t
c
o
i
n
.
Et
h
e
r
e
u
m
d
o
mi
n
a
n
c
e
Th
e
p
e
r
c
e
n
t
a
g
e
o
f
t
h
e
t
o
t
a
l
c
r
y
p
t
o
c
u
r
r
e
n
c
y
mark
e
t
c
a
p
i
t
a
l
i
z
a
t
i
o
n
t
h
a
t
i
s re
p
r
e
se
n
t
e
d
b
y
Et
h
e
r
e
u
m
A
c
t
i
v
e
C
r
y
p
t
o
c
u
r
r
e
n
c
i
e
s
Th
e
n
u
m
b
e
r
o
f
a
c
t
i
v
e
o
r
w
i
d
e
l
y
t
r
a
d
e
d
c
r
y
p
t
o
c
u
r
r
e
n
c
i
e
s.
N
u
mb
e
r
o
f
t
r
a
n
sa
c
t
i
o
n
s
Th
e
n
u
m
b
e
r
o
f
B
i
t
c
o
i
n
t
r
a
n
sac
t
i
o
n
s e
a
c
h
d
a
y
.
M
i
n
i
n
g
d
i
f
f
i
c
u
l
t
y
Th
e
d
i
f
f
i
c
u
l
t
y
o
f
mi
n
i
n
g
a
n
e
w
b
l
o
c
k
o
n
t
h
e
B
i
t
c
o
i
n
b
l
o
c
k
c
h
a
i
n
.
H
a
sh
r
a
t
e
Th
e
a
v
e
r
a
g
e
c
o
m
p
u
t
i
n
g
p
o
w
e
r
u
s
e
d
t
o
mi
n
e
B
i
t
c
o
i
n
d
a
i
l
y
.
Tr
a
n
s
a
c
t
i
o
n
s
f
e
e
s
Th
e
a
v
e
r
a
g
e
d
a
i
l
y
c
o
st
o
f
B
i
t
c
o
i
n
t
r
a
n
sac
t
i
o
n
s
.
Tr
a
n
s
a
c
t
i
o
n
v
a
l
u
e
Th
e
a
v
e
r
a
g
e
v
a
l
u
e
i
n
d
o
l
l
a
r
s
o
f
B
i
t
c
o
i
n
t
r
a
n
s
a
c
t
i
o
n
s e
v
e
r
y
d
a
y
.
S
e
n
t
c
o
i
n
i
n
U
S
D
C
o
i
n
w
a
s s
e
n
t
i
n
U
S
D
p
e
r
d
a
y
.
M
i
n
e
r
s
’
r
e
v
e
n
u
e
Th
e
t
o
t
a
l
a
m
o
u
n
t
o
f
mo
n
e
y
e
a
r
n
e
d
b
y
t
h
e
mi
n
e
r
s o
f
B
i
t
c
o
i
n
w
h
e
n
c
o
n
f
i
r
mi
n
g
t
r
a
n
s
a
c
t
i
o
n
s.
N
u
mb
e
r
o
f
b
i
t
c
o
i
n
s i
n
c
i
r
c
u
l
a
t
i
o
n
Th
e
t
o
t
a
l
n
u
m
b
e
r
o
f
b
i
t
c
o
i
n
s
i
n
e
x
c
h
a
n
g
e
a
n
d
u
se
.
R
e
l
a
t
i
v
e
s
t
r
e
n
g
t
h
i
n
d
e
x
D
e
t
e
r
m
i
n
e
s w
h
e
t
h
e
r
a
f
i
n
a
n
c
i
a
l
a
sse
t
i
s o
v
e
r
b
o
u
g
h
t
o
r
o
v
e
r
so
l
d
b
y
m
e
a
s
u
r
i
n
g
t
h
e
si
z
e
o
f
r
e
c
e
n
t
p
r
i
c
e
f
l
u
c
t
u
a
t
i
o
n
s
B
o
l
l
i
n
g
e
r
b
a
n
d
s
(
U
p
p
e
r
/
M
i
d
d
l
e
/
Lo
w
e
r
)
D
e
t
e
r
m
i
n
e
t
h
e
l
e
v
e
l
s
o
f
p
o
t
e
n
t
i
a
l
su
p
p
o
r
t
a
n
d
r
e
si
s
t
a
n
c
e
o
f
a
n
a
s
set
’
s
p
r
i
ce
S
mo
o
t
h
m
o
v
i
n
g
a
v
e
r
a
g
e
U
sed
f
o
r
i
d
e
n
t
i
f
y
i
n
g
p
r
i
c
e
t
r
e
n
d
s
i
n
f
i
n
a
n
c
i
a
l
i
n
s
t
r
u
m
e
n
t
s
G
e
o
p
o
l
i
t
i
c
a
l
r
i
s
k
i
n
d
e
x
U
S
A
[
2
2
]
A
n
i
n
d
i
c
a
t
o
r
t
h
a
t
q
u
a
n
t
i
f
i
e
s t
h
e
i
m
p
a
c
t
o
f
p
o
l
i
t
i
c
a
l
a
n
d
e
c
o
n
o
m
i
c
r
i
s
k
t
o
a
c
o
u
n
t
r
y
’
s s
t
a
b
i
l
i
t
y
a
n
d
i
n
v
e
s
t
me
n
t
i
n
g
l
o
b
a
l
m
a
r
k
e
t
s.
Ec
o
n
o
mi
c
p
o
l
i
c
y
u
n
c
e
r
t
a
i
n
t
y
i
n
d
e
x
U
S
A
[
2
3
]
A
n
i
n
d
e
x
t
h
a
t
mea
s
u
r
e
s
t
h
e
l
e
v
e
l
o
f
u
n
c
e
r
t
a
i
n
t
y
su
r
r
o
u
n
d
i
n
g
e
c
o
n
o
mi
c
p
o
l
i
c
y
,
w
h
i
c
h
i
n
f
l
u
e
n
c
e
s
i
n
v
e
st
m
e
n
t
d
e
c
i
s
i
o
n
s
a
n
d
e
c
o
n
o
mi
c
p
e
r
f
o
r
ma
n
c
e
.
C
o
n
s
u
mer
p
r
i
c
e
i
n
d
e
x
[
2
4
]
A
mea
s
u
r
e
o
f
a
v
e
r
a
g
e
p
r
i
c
e
i
n
c
r
e
a
ses
i
n
a
b
a
s
k
e
t
o
f
g
o
o
d
s a
n
d
s
e
r
v
i
c
e
s
p
u
r
c
h
a
s
e
d
b
y
f
a
mi
l
i
e
s
,
i
n
d
i
c
a
t
i
n
g
t
h
e
r
a
t
e
o
f
i
n
f
l
a
t
i
o
n
.
G
o
l
d
p
r
i
c
e
C
u
r
r
e
n
t
mar
k
e
t
v
a
l
u
e
o
f
a
n
o
u
n
c
e
o
f
g
o
l
d
i
n
U
S
D
.
O
i
l
p
r
i
c
e
Th
e
c
u
r
r
e
n
t
g
l
o
b
a
l
mar
k
e
t
p
r
i
c
e
o
f
w
e
st
T
e
x
a
s
i
n
t
e
r
me
d
i
a
t
e
(
W
TI
)
c
r
u
d
e
o
i
l
,
a
b
e
n
c
h
m
a
r
k
f
o
r
o
i
l
p
r
i
c
e
s.
Tw
i
t
t
e
r
/
G
o
o
g
l
e
t
r
e
n
d
B
i
t
c
o
i
n
Tw
i
t
t
e
r
a
n
d
G
o
o
g
l
e
Tr
e
n
d
s r
e
f
e
r
t
o
t
h
e
p
u
b
l
i
c
i
n
t
e
r
e
st
o
n
B
i
t
c
o
i
n
e
x
p
r
e
sse
d
t
h
r
o
u
g
h
Tw
i
t
t
e
r
m
e
n
t
i
o
n
s a
n
d
G
o
o
g
l
e
s
e
a
r
c
h
e
s.
Tw
i
t
t
e
r
m
a
r
k
e
t
u
n
c
e
r
t
a
i
n
t
y
i
n
En
g
l
i
sh
A
mea
s
u
r
e
o
f
m
a
r
k
e
t
u
n
c
e
r
t
a
i
n
t
y
d
e
v
e
l
o
p
e
d
f
r
o
m Tw
i
t
t
e
r
d
a
t
a
a
n
d
s
e
n
t
i
me
n
t
a
n
a
l
y
s
i
s
o
f
t
w
e
e
t
s.
Tw
i
t
t
e
r
e
c
o
n
o
m
i
c
u
n
c
e
r
t
a
i
n
t
y
i
n
En
g
l
i
sh
[
2
5
]
Th
e
e
c
o
n
o
mi
c
u
n
c
e
r
t
a
i
n
t
y
i
n
d
e
x
i
s
d
e
r
i
v
e
d
f
r
o
m Tw
i
t
t
e
r
d
a
t
a
,
a
n
d
i
t
r
e
f
l
e
c
t
s
sen
t
i
me
n
t
s
a
n
d
t
a
l
k
s
a
b
o
u
t
e
c
o
n
o
mi
c
c
o
n
d
i
t
i
o
n
s
a
n
d
u
n
c
e
r
t
a
i
n
t
i
e
s
.
C
O
V
I
D
-
1
9
n
e
w
d
e
a
t
h
/
c
a
se
Th
e
t
e
r
m
“
C
O
V
I
D
-
1
9
n
e
w
d
e
a
t
h
s
”
r
e
f
e
r
s t
o
t
h
e
n
u
m
b
e
r
o
f
n
e
w
l
y
r
e
p
o
r
t
e
d
C
O
V
I
D
-
1
9
d
e
a
t
h
s,
w
h
e
r
e
a
s
“
C
O
V
I
D
-
1
9
n
e
w
c
a
ses
”
r
e
f
e
r
s t
o
t
h
e
n
u
m
b
e
r
o
f
n
e
w
l
y
r
e
p
o
r
t
e
d
C
O
V
I
D
-
1
9
i
n
f
e
c
t
i
o
n
s.
2
.
2
.
Da
t
a
c
o
llect
io
n
A
d
u
al
a
p
p
r
o
a
ch
is
ad
o
p
ted
to
co
llect
th
e
n
ec
ess
ar
y
d
ata
f
o
r
th
e
i
d
en
tifie
d
v
ar
iab
les.
T
h
e
f
ir
s
t
m
eth
o
d
in
v
o
l
v
es
g
ath
er
i
n
g
d
at
a
f
r
o
m
C
SV
f
iles
,
wh
ich
p
r
o
v
id
es
s
tr
u
ctu
r
ed
an
d
r
ea
d
ily
av
ailab
le
in
f
o
r
m
atio
n
f
o
r
an
aly
s
is
.
T
h
e
s
ec
o
n
d
m
et
h
o
d
u
tili
ze
s
web
s
cr
ap
in
g
tech
n
iq
u
es,
im
p
lem
en
te
d
th
r
o
u
g
h
Py
th
o
n
lib
r
a
r
ies
s
u
ch
as
b
ea
u
tifu
l
s
o
u
p
an
d
r
eq
u
ests
,
to
ex
tr
ac
t
d
ata
f
r
o
m
o
n
lin
e
s
o
u
r
ce
s
.
B
y
em
p
lo
y
i
n
g
th
ese
m
eth
o
d
s
,
th
e
s
tu
d
y
en
s
u
r
es th
e
av
ailab
il
ity
o
f
h
ig
h
-
q
u
ality
d
ata
f
o
r
s
u
b
s
eq
u
en
t p
r
e
p
r
o
ce
s
s
in
g
an
d
an
a
ly
s
is
.
2
.
3
.
Da
t
a
pre
-
pro
ce
s
s
ing
T
o
m
ain
tain
th
e
q
u
ality
an
d
c
o
n
s
is
ten
cy
o
f
th
e
co
llected
d
ata,
a
th
o
r
o
u
g
h
d
ata
clea
n
in
g
p
r
o
ce
s
s
is
co
n
d
u
cte
d
.
T
h
is
p
r
o
ce
s
s
id
en
tifie
s
an
d
co
r
r
ec
ts
an
y
an
o
m
ali
es,
m
is
s
in
g
v
alu
es,
o
r
er
r
o
r
s
in
th
e
d
ata
to
e
n
s
u
r
e
its
r
elia
b
ilit
y
f
o
r
f
u
r
th
er
an
aly
s
is
.
Ad
d
itio
n
ally
,
s
ep
ar
ate
d
at
a
s
er
ies
ar
e
m
e
r
g
ed
in
to
a
s
in
g
le
u
n
if
ie
d
d
ataset,
with
tim
estam
p
s
alig
n
ed
to
cr
ea
te
a
co
n
s
is
ten
t
tim
e
s
er
ies
f
o
r
m
at.
T
h
e
Py
th
o
n
lib
r
a
r
y
Pa
n
d
as
is
u
s
ed
f
o
r
th
is
in
teg
r
atio
n
,
e
n
ab
lin
g
ef
f
icien
t
h
an
d
lin
g
a
n
d
m
a
n
ip
u
latio
n
o
f
th
e
d
ata.
B
y
p
er
f
o
r
m
in
g
th
e
s
e
s
tep
s
,
th
e
s
tu
d
y
en
s
u
r
es th
at
th
e
d
ataset
is
b
o
th
ac
cu
r
ate
an
d
r
ea
d
y
f
o
r
s
u
b
s
eq
u
en
t a
n
aly
tical
p
r
o
ce
d
u
r
es.
2
.
4
.
F
e
a
t
ure
eng
ineering
Featu
r
e
en
g
in
ee
r
in
g
is
th
e
p
r
a
ctice
o
f
ex
tr
ac
tin
g
a
d
d
itio
n
al
f
ea
tu
r
es
f
r
o
m
an
ex
is
tin
g
d
ataset
in
o
r
d
e
r
to
im
p
r
o
v
e
th
e
p
r
ed
ictiv
e
m
o
d
elin
g
p
r
o
ce
s
s
.
T
ec
h
n
ical
in
d
icato
r
s
s
u
ch
as
th
e
r
elativ
e
s
t
r
en
g
th
in
d
e
x
(
R
SI)
,
B
o
llin
g
er
B
an
d
s
(
B
B
an
d
s
)
,
an
d
s
im
p
le
m
o
v
in
g
av
er
a
g
e
(
S
MA
)
ar
e
co
m
p
u
te
d
in
th
is
s
tu
d
y
b
y
th
e
h
elp
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
F
o
r
ec
a
s
tin
g
b
itco
in
p
r
ice
flu
ct
u
a
tio
n
s
:
a
time
s
eries
a
n
a
lysi
s
a
p
p
r
o
a
ch
f
o
r
p
r
ed
ictive
…
(
A
min
e
B
a
ts
i
)
1967
Pan
d
as
-
T
a
lib
r
a
r
y
.
B
y
i
n
co
r
p
o
r
atin
g
R
SI,
B
B
an
d
s
,
an
d
SMA
in
to
th
e
s
tu
d
y
we
en
s
u
r
e
a
co
m
p
r
e
h
en
s
iv
e
an
aly
s
is
o
f
m
ar
k
et
c
o
n
d
itio
n
s
,
co
m
b
in
in
g
m
o
m
en
tu
m
,
v
o
latilit
y
,
an
d
tr
e
n
d
in
d
icato
r
s
to
en
h
a
n
ce
th
e
p
r
ed
ictiv
e
p
e
r
f
o
r
m
an
ce
o
f
th
e
B
itco
in
p
r
ice
f
o
r
ec
asti
n
g
m
o
d
el.
2
.
5
.
F
e
a
t
ure
s
elec
t
io
n
Featu
r
e
s
elec
tio
n
is
a
s
ig
n
if
ican
t
p
h
ase
in
r
e
f
in
in
g
t
h
e
d
ata
s
et
an
d
o
p
tim
izin
g
m
o
d
el
p
er
f
o
r
m
an
ce
,
f
o
r
id
en
tify
in
g
an
d
p
r
eser
v
e
th
e
m
o
s
t
s
ig
n
if
ican
t
attr
ib
u
tes,
we
em
p
lo
y
two
f
ilter
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
:
co
r
r
elatio
n
-
b
ased
an
d
m
u
tu
al
in
f
o
r
m
atio
n
-
b
ased
to
e
v
alu
ate
f
ea
tu
r
es
b
ased
o
n
t
h
eir
s
tatis
tical
p
r
o
p
er
ties
o
r
th
eir
r
elatio
n
s
h
ip
s
with
th
e
tar
g
et
v
ar
iab
le,
in
d
ep
e
n
d
en
t
o
f
an
y
s
p
ec
if
ic
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
.
T
h
e
co
r
r
elatio
n
-
b
ased
m
eth
o
d
to
m
in
im
izes
m
u
ltico
llin
ea
r
ity
an
d
p
o
ten
tially
i
n
cr
ea
s
es
m
o
d
el
in
ter
p
r
etab
ilit
y
b
y
r
em
o
v
in
g
p
air
s
o
f
f
ea
t
u
r
es with
a
h
ig
h
co
r
r
elatio
n
co
e
f
f
ic
ien
t,
s
p
ec
if
ically
th
o
s
e
ab
o
v
e
a
th
r
esh
o
ld
o
f
0
.
8
5
.
T
h
e
m
u
tu
al
in
f
o
r
m
atio
n
m
e
th
o
d
,
im
p
lem
en
te
d
u
s
in
g
Scik
it
-
lear
n
’
s
‘
m
u
tu
al_
in
f
o
_
r
e
g
r
ess
io
n
’
in
v
o
lv
es
ca
lcu
latin
g
th
e
s
co
r
e
b
etwe
en
ea
ch
f
ea
tu
r
e
an
d
th
e
tar
g
et
v
ar
iab
le,
th
en
s
elec
tin
g
th
e
f
ea
tu
r
es
with
th
e
h
i
g
h
est
m
u
tu
al
in
f
o
r
m
atio
n
s
co
r
es
to
en
s
u
r
e
th
at
o
n
ly
th
e
m
o
s
t
in
f
o
r
m
ativ
e
f
ea
tu
r
es
ar
e
in
clu
d
ed
,
wh
ich
ca
n
s
ig
n
if
ican
tly
en
h
a
n
ce
th
e
m
o
d
el
’
s
ab
ilit
y
to
m
ak
e
ac
cu
r
ate
p
r
ed
ictio
n
s
.
2
.
6
.
Da
t
a
no
r
m
a
liza
t
i
o
n a
nd
s
pli
t
t
ing
Af
ter
,
clea
n
in
g
d
ata
an
d
h
a
n
d
l
in
g
m
is
s
in
g
v
alu
es
a
m
in
im
u
m
an
d
m
ax
im
u
m
s
ca
ler
(
Min
Ma
x
Scaler
)
h
as
b
ee
n
ap
p
lied
f
o
r
ea
ch
d
at
aset.
T
h
u
s
,
all
th
e
v
a
r
iab
les
a
r
e
u
n
i
f
ied
b
etwe
en
0
an
d
1
,
t
h
e
s
ca
lin
g
f
o
r
m
u
la
p
r
esen
ted
in
(
1
)
.
As
illu
s
tr
ated
in
Fig
u
r
e
2
,
th
e
d
ataset
will
b
e
p
ar
titi
o
n
ed
in
t
o
tr
ain
in
g
an
d
test
s
et
s
,
with
8
5
%
(
3
0
2
5
d
ay
s
)
d
esig
n
ated
f
o
r
tr
a
in
in
g
f
r
o
m
Ap
r
il
3
0
,
2
0
1
3
,
to
Au
g
u
s
t
1
0
,
2
0
2
1
,
an
d
1
5
%
(
5
3
4
d
ay
s
)
allo
ca
t
e
d
f
o
r
test
in
g
s
p
an
n
i
n
g
Au
g
u
s
t 1
1
,
2
0
2
1
,
to
J
an
u
ar
y
2
6
,
2
0
2
3
.
=
−
−
(
1
)
2
.
7
.
T
ra
ini
ng
a
nd
ev
a
lua
t
io
n
T
r
ain
in
g
was
co
n
d
u
cted
f
o
r
e
ac
h
m
o
d
el
o
n
th
e
o
r
ig
in
al
d
ataset
as
well
a
s
th
e
two
d
er
iv
e
d
d
atasets
cr
ea
ted
th
r
o
u
g
h
f
ea
tu
r
e
s
elec
tio
n
.
W
e
b
eg
an
with
m
ac
h
in
e
lear
n
in
g
m
o
d
els,
in
clu
d
in
g
XGBo
o
s
t,
L
R
,
SV
R
an
d
FB
Pro
p
h
et.
Ad
d
itio
n
ally
,
we
d
ev
elo
p
ed
a
d
ee
p
lear
n
in
g
m
o
d
el
u
s
in
g
T
en
s
o
r
Flo
w
b
ased
o
n
R
NN
v
ar
ian
ts
,
s
p
ec
if
ically
B
i
-
GR
U,
Fig
u
r
e
3
s
h
o
ws
o
u
r
p
r
o
p
o
s
ed
m
o
d
el
ar
c
h
itectu
r
e.
T
h
en
we
ass
es
s
th
e
m
o
d
els’
p
er
f
o
r
m
an
ce
u
s
in
g
m
ea
n
ab
s
o
lu
te
er
r
o
r
(
MA
E
)
,
m
ea
n
s
q
u
ar
e
er
r
o
r
(
MSE
)
,
m
ea
n
a
b
s
o
lu
te
p
er
ce
n
tag
e
e
r
r
o
r
(
MA
PE)
,
an
d
R
2
s
co
r
e.
T
h
es
e
m
etr
ics
o
f
f
er
a
th
o
r
o
u
g
h
ev
alu
atio
n
o
f
th
e
m
o
d
el’
s
p
r
e
d
i
ctiv
e
p
r
ec
is
io
n
an
d
r
esil
ien
ce
.
T
h
e
f
o
r
m
u
las
f
o
r
co
m
p
u
tin
g
th
ese
m
etr
ics
ar
e
p
r
o
v
id
ed
in
(
2
)
th
r
o
u
g
h
(
4
)
.
T
h
e
s
p
ec
if
ic
co
n
f
ig
u
r
atio
n
s
f
o
r
ea
ch
m
o
d
el
ar
e
o
u
tlin
ed
i
n
T
ab
le
2
.
Fig
u
r
e
2
.
T
r
ain
in
g
a
n
d
test
in
g
s
p
lits
Fig
u
r
e
3
.
B
i
-
GR
U
m
o
d
el
ar
ch
i
tectu
r
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
3
,
Ma
r
ch
20
2
5
:
1
96
4
-
1
97
5
1968
T
ab
le
2
.
Mo
d
el
lib
r
ar
ies an
d
c
o
n
f
ig
u
r
atio
n
s
M
o
d
e
l
Li
b
r
a
r
y
C
o
n
f
i
g
u
r
a
t
i
o
n
LR
S
c
i
k
i
t
-
l
e
a
r
n
D
e
f
a
u
l
t
p
a
r
a
me
t
e
r
s
S
V
R
S
c
i
k
i
t
-
l
e
a
r
n
C=
1
0
,
e
p
s
i
l
o
n
=
0
.
0
1
,
k
e
r
n
e
l
=
‘
l
i
n
e
a
r
’
X
G
B
o
o
st
x
g
b
o
o
s
t
b
o
o
s
t
e
r
=
‘
g
b
l
i
n
e
a
r
’
,
n
_
e
s
t
i
m
a
t
o
r
s=
10
,
0
0
0
,
o
b
j
e
c
t
i
v
e
=
‘
r
e
g
:
s
q
u
a
r
e
d
e
r
r
o
r
’
F
b
P
r
o
p
h
e
t
p
r
o
p
h
e
t
W
e
a
d
d
e
d
a
r
e
g
r
e
ss
o
r
f
o
r
e
v
e
r
y
f
e
a
t
u
r
e
i
n
t
h
e
d
a
t
a
s
e
t
Bi
-
G
R
U
Te
n
s
o
r
F
l
o
w
l
o
ss
=
‘
me
a
n
_
s
q
u
a
r
e
d
_
e
r
r
o
r
’
,
o
p
t
i
mi
z
e
r
=
‘
a
d
a
m
’
,
met
r
i
c
s
=
‘
ma
e
’
,
l
o
o
k
_
b
a
c
k
=
7
,
e
p
o
c
h
s
=
1
0
0
,
b
a
t
c
h
_
s
i
z
e
=
1
2
8
,
a
n
d
a
l
i
n
e
a
r
a
c
t
i
v
a
t
i
o
n
f
o
r
d
e
n
se
l
a
y
e
r
s
=
1
∑
|
−
|
=
1
(
2
)
=
1
∑
|
−
|
=
1
(
3
)
=
1
∑
(
−
)
2
=
1
(
4
)
2
=
1
−
∑
(
−
)
2
=
1
∑
(
−
)
2
=
1
(
5
)
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
Af
ter
in
itiatin
g
th
e
s
tu
d
y
b
y
c
o
llectin
g
an
d
p
r
e
-
p
r
o
ce
s
s
in
g
t
h
e
d
ata
an
d
co
n
s
o
lid
atin
g
it
in
to
a
s
in
g
le
d
ataset,
we
p
r
o
ce
ed
with
f
ea
tu
r
e
e
n
g
in
ee
r
i
n
g
b
y
ca
lcu
latin
g
s
ev
er
al
tech
n
ical
i
n
d
icato
r
s
.
T
h
ese
in
cl
u
d
e
th
e
SMA
o
v
er
2
0
p
er
io
d
s
,
th
e
R
SI
o
v
er
1
4
p
er
io
d
s
,
an
d
th
e
B
B
an
d
s
o
v
er
2
0
p
er
io
d
s
.
T
h
is
en
h
an
ce
s
th
e
d
ataset
b
y
in
co
r
p
o
r
atin
g
v
alu
ab
le
m
a
r
k
et
in
d
icato
r
s
th
at
ca
n
ai
d
in
p
r
ed
ictin
g
B
itco
in
p
r
ices.
Fo
llo
win
g
th
is
,
we
ap
p
ly
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
es
co
r
r
el
atio
n
an
d
m
u
tu
al
in
f
o
r
m
atio
n
,
s
co
r
es
ar
e
p
r
o
v
id
e
d
in
Fig
u
r
es
4
an
d
5
r
esp
ec
tiv
ely
.
As
a
r
esu
lt,
two
ad
d
itio
n
al
d
atasets
ar
e
d
er
iv
e
d
f
r
o
m
th
e
o
r
i
g
in
al
d
ataset,
ea
ch
co
n
tain
in
g
a
u
n
iq
u
e
s
et
o
f
s
elec
ted
f
ea
tu
r
es.
T
ab
le
3
o
u
tlin
es
th
e
s
p
ec
if
ic
f
ea
tu
r
es
ch
o
s
en
f
o
r
ea
ch
o
f
th
e
r
esu
ltan
t
d
atasets
,
h
ig
h
lig
h
tin
g
th
e
d
if
f
er
en
ce
s
a
n
d
th
e
r
atio
n
ale
b
eh
in
d
th
e
s
elec
tio
n
in
ea
ch
ca
s
e.
T
h
e
m
u
t
u
al
in
f
o
r
m
atio
n
tech
n
iq
u
e
s
elec
ted
f
ea
tu
r
es
s
u
ch
as
o
p
en
,
v
o
lu
m
e,
ch
a
n
g
e,
B
T
C
d
o
m
in
an
ce
,
an
d
C
OVI
D
-
19
n
ew
ca
s
es
am
o
n
g
o
th
e
r
s
,
in
d
icatin
g
th
ese
v
a
r
iab
les
s
tr
o
n
g
i
n
d
iv
id
u
al
co
n
tr
ib
u
t
io
n
s
to
p
r
ice
p
r
ed
ictio
n
.
I
n
co
n
t
r
ast,
th
e
m
eth
o
d
o
f
r
em
o
v
i
n
g
h
ig
h
ly
co
r
r
e
lated
f
ea
tu
r
es r
esu
lted
in
th
e
s
elec
tio
n
o
f
d
if
f
e
r
en
t
v
ar
iab
les
lik
e
h
ig
h
,
lo
w,
E
th
er
eu
m
d
o
m
in
an
ce
,
an
d
t
o
tal
m
ar
k
et
ca
p
italizatio
n
h
ig
h
lig
h
tin
g
th
e
im
p
o
r
tan
ce
o
f
m
in
im
izin
g
r
ed
u
n
d
a
n
cy
a
n
d
m
u
ltico
llin
ea
r
ity
.
Fig
u
r
e
4
.
C
o
r
r
elatio
n
m
atr
ix
s
co
r
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
F
o
r
ec
a
s
tin
g
b
itco
in
p
r
ice
flu
ct
u
a
tio
n
s
:
a
time
s
eries
a
n
a
lysi
s
a
p
p
r
o
a
ch
f
o
r
p
r
ed
ictive
…
(
A
min
e
B
a
ts
i
)
1969
Fig
u
r
e
5
.
Mu
t
u
al
in
f
o
r
m
atio
n
s
co
r
e
T
ab
le
3
.
Featu
r
es e
x
tr
ac
te
d
in
ea
ch
ch
ild
d
ataset
S
e
l
e
c
t
e
d
f
e
a
t
u
r
e
s
u
si
n
g
c
o
r
r
e
l
a
t
i
o
n
(
1
8
f
e
a
t
u
r
e
s)
S
e
l
e
c
t
e
d
f
e
a
t
u
r
e
s
u
si
n
g
m
u
t
u
a
l
i
n
f
o
r
m
a
t
i
o
n
(
1
9
f
e
a
t
u
r
e
s)
O
p
e
n
,
v
o
l
u
me
,
c
h
a
n
g
e
,
B
TC
d
o
mi
n
a
n
c
e
,
C
O
V
1
9
ne
w
c
a
ses
,
C
O
V
1
9
n
e
w
d
e
a
t
h
s,
W
TI
o
i
l
p
r
i
c
e
,
G
o
o
g
l
e
t
r
e
n
d
,
t
w
e
e
t
t
r
e
n
d
,
g
o
l
d
p
r
i
c
e
,
EPU
,
T
M
U
,
TEU
,
G
P
R
C
,
nu
m
b
e
r
o
f
t
r
a
n
s
a
c
t
i
o
n
s i
n
b
l
o
c
k
c
h
a
i
n
,
A
V
G
t
r
a
n
s
a
c
t
i
o
n
f
e
e
,
s
e
n
t
c
o
i
n
s
i
n
U
S
D
,
n
u
mb
e
r
o
f
B
TC
i
n
c
i
r
c
u
l
a
t
i
o
n
O
p
e
n
,
h
i
g
h
,
l
o
w
,
e
t
h
e
r
e
u
m
d
o
mi
n
a
n
c
e
,
t
o
t
a
l
mar
k
e
t
c
a
p
i
t
a
l
i
z
a
t
i
o
n
,
t
o
t
a
l
mark
e
t
c
a
p
i
t
a
l
i
z
a
t
i
o
n
w
i
t
h
o
u
t
B
T
C
,
a
c
t
i
v
e
c
r
y
p
t
o
c
u
r
r
e
n
c
i
e
s
,
C
O
V
1
9
n
e
w
d
e
a
t
h
s
,
C
P
I
,
t
w
e
e
t
t
r
e
n
d
,
A
V
G
mi
n
i
n
g
d
i
f
f
i
c
u
l
t
y
,
A
V
G
h
a
s
h
r
a
t
e
,
A
V
G
t
r
a
n
sac
t
i
o
n
v
a
l
u
e
,
mi
n
e
r
’
s
r
e
v
e
n
u
e
,
S
M
A
,
B
B
L,
B
B
M
,
B
B
U
,
b
i
t
c
o
i
n
mar
k
e
t
c
a
p
i
t
a
l
i
z
a
t
i
o
n
T
h
e
p
er
f
o
r
m
an
ce
ev
al
u
atio
n
o
f
B
itco
in
p
r
ice
p
r
ed
ictio
n
m
o
d
els
o
n
th
e
o
r
ig
in
al
d
ataset,
as
d
etailed
in
T
ab
le
4
a
n
d
illu
s
tr
ated
i
n
Fig
u
r
e
6
,
in
clu
d
es
th
e
f
o
llo
win
g
m
o
d
els:
B
i
-
GR
U,
LR
,
X
GB
o
o
s
t,
SVR
,
an
d
FB
Pro
p
h
et,
h
ig
h
lig
h
ts
n
o
tab
le
v
ar
iatio
n
s
in
p
er
f
o
r
m
an
ce
.
Star
tin
g
with
B
i
-
GR
U,
th
e
m
o
d
el
ac
h
iev
es
a
h
ig
h
R
2
s
co
r
e
o
f
0
.
9
8
5
0
b
u
t
s
li
g
h
tly
h
ig
h
er
MA
E
(
0
.
0
1
9
)
an
d
MSE
(
0
.
0
0
0
6
)
,
in
d
icatin
g
m
o
d
er
ate
er
r
o
r
s
.
Fig
u
r
e
6
(
a
)
s
h
o
ws
g
o
o
d
alig
n
m
en
t
b
etwe
en
p
r
e
d
icted
an
d
a
ctu
al
p
r
ices,
th
o
u
g
h
m
i
n
o
r
d
e
v
iatio
n
s
ar
e
v
is
ib
le.
LR
p
er
f
o
r
m
s
well
with
an
R
2
s
co
r
e
o
f
0
.
9
8
9
4
,
MA
E
o
f
0
.
0
2
1
,
an
d
MSE
o
f
0
.
0
0
0
6
,
with
Fi
g
u
r
e
6
(
b
)
d
is
p
lay
in
g
clo
s
e
o
v
er
lap
s
o
f
p
r
ed
icted
an
d
ac
tu
al
p
r
ices,
s
u
g
g
esti
n
g
r
eliab
le
p
r
e
d
ictio
n
s
.
X
GB
o
o
s
t
em
er
g
es
as
th
e
m
o
s
t
ac
cu
r
ate
m
o
d
el,
ac
h
i
ev
in
g
th
e
h
ig
h
est
R
2
s
co
r
e
o
f
0
.
9
8
9
9
an
d
th
e
lo
west
er
r
o
r
s
(
MA
E
o
f
0
.
0
2
0
a
n
d
MA
PE
o
f
3
.
3
3
%).
F
ig
u
r
e
6
(
c)
illu
s
tr
ates
m
in
im
al
d
i
s
cr
ep
an
cies
b
etwe
en
p
r
ed
icted
an
d
ac
tu
al
p
r
ices,
in
d
icatin
g
ex
ce
p
tio
n
al
p
er
f
o
r
m
an
ce
.
SVR
also
d
eliv
er
s
s
tr
o
n
g
r
esu
lts
,
with
an
R
2
s
co
r
e
o
f
0
.
9
8
8
4
an
d
MA
P
E
o
f
3
.
8
3
%,
as
r
ef
lecte
d
in
th
e
Fig
u
r
e
6
(
d
)
clo
s
ely
m
atch
ed
p
r
ice
lin
es,
th
o
u
g
h
with
s
lig
h
tly
lar
g
er
er
r
o
r
s
co
m
p
ar
ed
to
XGBo
o
s
t.
Fin
ally
,
FB
p
r
o
p
h
et
ac
h
iev
es
r
ea
s
o
n
ab
le
ac
cu
r
ac
y
with
an
R
2
s
co
r
e
o
f
0
.
9
8
4
3
b
u
t
ex
h
ib
its
h
ig
h
er
MA
PE
(
5
.
1
4
%),
as
F
ig
u
r
e
6
(
e)
s
h
o
ws
m
o
r
e
p
r
o
n
o
u
n
ce
d
d
ev
iatio
n
s
b
etwe
en
p
r
ed
icted
an
d
ac
tu
al
v
alu
es,
esp
ec
ially
d
u
r
in
g
p
er
io
d
s
o
f
h
ig
h
v
o
latilit
y
.
Ov
er
all,
th
e
m
o
d
els,
p
ar
t
icu
lar
ly
XGBo
o
s
t,
s
h
o
wca
s
e
p
r
o
m
is
in
g
r
esu
lts
in
f
o
r
ec
asti
n
g
B
itco
in
p
r
ices,
e
m
p
h
asizin
g
th
e
ef
f
ec
tiv
en
ess
o
f
m
ac
h
in
e
l
ea
r
n
in
g
ap
p
r
o
ac
h
es in
th
is
co
n
tex
t.
T
ab
le
4
.
p
e
r
f
o
r
m
an
ce
m
et
r
ics o
n
m
o
t
h
er
d
ataset
M
o
d
e
l
M
A
E
M
S
E
M
A
P
E
R
2
s
c
o
r
e
Bi
-
G
R
U
0
.
0
1
9
0
.
0
0
0
6
4
.
0
9
%
0
.
9
8
5
0
X
G
B
o
o
st
0
.
0
2
0
0
.
0
0
0
7
3
.
3
3
%
0
.
9
8
9
9
S
V
R
0
.
0
2
2
0
.
0
0
0
8
3
.
8
3
%
0
.
9
8
8
4
LR
0
.
0
2
1
0
.
0
0
0
7
3
.
5
4
%
0
.
9
8
9
4
F
B
p
r
o
p
h
e
t
0
.
0
2
1
0
.
0
0
0
6
5
.
1
4
%
0
.
9
8
4
3
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
3
,
Ma
r
ch
20
2
5
:
1
96
4
-
1
97
5
1970
(
a)
(
b
)
(
c)
(
d
)
(
e)
Fig
u
r
e
6
.
Mo
d
el
s
r
esu
lts
o
n
m
o
th
er
d
ataset
;
(
a)
B
i
-
GR
U
,
(
b
)
L
R
,
(
c)
XGBo
o
s
t
,
(
d
)
SVR
,
an
d
(
e)
FB
Pro
p
h
et
T
h
e
ev
alu
atio
n
o
f
B
itco
in
p
r
i
ce
p
r
ed
ictio
n
m
o
d
els
af
ter
ap
p
ly
in
g
a
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
e
th
at
r
em
o
v
es
h
ig
h
ly
co
r
r
elate
d
v
ar
iab
les
r
ev
ea
ls
im
p
r
o
v
e
d
p
e
r
f
o
r
m
an
ce
,
as
s
u
m
m
a
r
ized
in
T
a
b
le
5
an
d
illu
s
tr
ated
in
Fig
u
r
e
7
c
o
m
p
r
is
es
th
e
m
o
d
els
B
i
-
GR
U,
LR
,
XG
B
o
o
s
t,
SVR
,
an
d
FB
Pro
p
h
et.
Star
tin
g
with
B
i
-
GR
U,
th
e
m
o
d
el
d
eliv
er
s
s
tr
o
n
g
r
esu
lts
with
an
R
2
s
co
r
e
o
f
0
.
9
8
7
2
,
MA
E
o
f
0
.
0
1
7
,
an
d
MA
PE
o
f
3
.
4
6
%.
F
ig
u
r
e
7
(
a)
d
em
o
n
s
tr
ates
g
o
o
d
alig
n
m
e
n
t
b
etwe
en
p
r
ed
icted
an
d
ac
tu
a
l
p
r
ices,
th
o
u
g
h
m
in
o
r
d
is
cr
e
p
an
cies
ar
e
v
is
ib
le,
esp
ec
ially
d
u
r
in
g
v
o
latile
p
e
r
i
o
d
s
.
L
R
p
er
f
o
r
m
s
e
x
ce
p
tio
n
ally
well,
ac
h
iev
i
n
g
t
h
e
h
i
g
h
est
R
2
s
co
r
e
o
f
0
.
9
9
2
0
,
MA
E
o
f
0
.
0
1
6
,
an
d
th
e
lo
wes
t
MA
PE
o
f
2
.
5
2
%.
F
ig
u
r
e
7
(
b
)
r
ev
ea
ls
n
ea
r
-
p
e
r
f
ec
t
o
v
er
lap
b
etwe
en
p
r
ed
icted
an
d
ac
tu
al
p
r
ices,
h
i
g
h
lig
h
tin
g
its
r
eliab
ilit
y
.
XGBo
o
s
t
m
a
tch
es
L
R
in
p
er
f
o
r
m
a
n
ce
,
als
o
ac
h
iev
in
g
an
R
2
s
co
r
e
o
f
0
.
9
9
2
0
,
MA
E
o
f
0
.
0
1
6
,
an
d
a
s
lig
h
tly
h
i
g
h
er
MA
PE
o
f
2
.
5
3
%.
F
ig
u
r
e
7
(
d
)
co
n
f
ir
m
s
ex
ce
p
tio
n
al
p
r
ed
ictiv
e
ac
cu
r
ac
y
with
m
in
im
al
d
ev
iatio
n
s
.
SVR
f
o
llo
w
s
clo
s
ely
with
an
R
2
s
co
r
e
o
f
0
.
9
9
0
8
,
MA
E
o
f
0
.
0
2
0
,
an
d
MA
PE
o
f
3
.
5
0
%.
W
h
ile
F
ig
u
r
e
7
(
c)
r
ef
lects
r
o
b
u
s
t
alig
n
m
en
t,
it
s
h
o
ws
s
lig
h
tl
y
lar
g
er
d
ev
iatio
n
s
co
m
p
ar
ed
to
XGBo
o
s
t
an
d
L
R
,
p
ar
ticu
lar
ly
d
u
r
in
g
h
ig
h
p
r
ice
f
lu
ctu
atio
n
s
.
Fin
ally
,
FB
p
r
o
p
h
et
ac
h
iev
es
th
e
lo
west
MA
E
(
0
.
0
1
5
)
a
n
d
MSE
(
0
.
0
0
0
4
)
,
alo
n
g
with
an
R
2
s
co
r
e
o
f
0
.
9
9
0
3
a
n
d
a
MA
PE
o
f
3
.
1
4
%
.
F
ig
u
r
e
7
(
e)
illu
s
tr
ates
s
tr
o
n
g
a
lig
n
m
en
t
b
etwe
en
p
r
ed
ictio
n
s
an
d
ac
tu
al
v
alu
es,
th
o
u
g
h
s
o
m
e
d
is
cr
ep
an
cies
ar
e
o
b
s
er
v
ed
d
u
r
i
n
g
v
o
latile
p
er
i
o
d
s
.
T
h
e
r
em
o
v
al
o
f
h
ig
h
l
y
c
o
r
r
elate
d
f
ea
t
u
r
es
ap
p
ea
r
s
to
en
h
an
ce
all
m
o
d
els
’
p
er
f
o
r
m
an
ce
,
as
r
e
f
lecte
d
in
r
ed
u
ce
d
e
r
r
o
r
s
an
d
co
n
s
is
ten
tly
h
ig
h
p
r
ed
ictiv
e
r
eliab
ilit
y
ac
r
o
s
s
th
e
b
o
ar
d
,
em
p
h
asizin
g
th
e
e
f
f
ec
tiv
en
ess
o
f
f
ea
tu
r
e
s
elec
tio
n
in
r
ef
i
n
in
g
B
itco
in
p
r
ice
f
o
r
ec
asti
n
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
F
o
r
ec
a
s
tin
g
b
itco
in
p
r
ice
flu
ct
u
a
tio
n
s
:
a
time
s
eries
a
n
a
lysi
s
a
p
p
r
o
a
ch
f
o
r
p
r
ed
ictive
…
(
A
min
e
B
a
ts
i
)
1971
T
ab
le
1
.
Per
f
o
r
m
an
ce
m
etr
ics o
n
co
r
r
elatio
n
d
ata
s
et
M
o
d
e
l
M
A
E
M
S
E
M
A
P
E
R
2
s
c
o
r
e
Bi
-
G
R
U
0
.
0
1
7
0
.
0
0
0
5
3
.
4
6
%
0
.
9
8
7
2
X
G
B
o
o
st
0
.
0
1
6
0
.
0
0
0
6
2
.
5
3
%
0
.
9
9
2
0
S
V
R
0
.
0
2
0
0
.
0
0
0
7
3
.
5
0
%
0
.
9
9
0
8
LR
0
.
0
1
6
0
.
0
0
0
6
2
.
5
2
%
0
.
9
9
2
0
F
B
p
r
o
p
h
e
t
0
.
0
1
5
0
.
0
0
0
4
3
.
1
4
%
0
.
9
9
0
3
Fig
u
r
e
7
.
Mo
d
el
r
esu
lts
o
n
c
o
r
r
elatio
n
d
ataset
;
(
a)
B
i
-
GR
U
,
(
b
)
L
R
,
(
c)
XGBo
o
s
t
,
(
d
)
SVR
,
an
d
(
e)
FB
Pro
p
h
et
T
h
e
an
aly
s
is
o
f
B
itco
in
p
r
ice
p
r
ed
ictio
n
m
o
d
els
u
s
in
g
m
u
tu
al
in
f
o
r
m
ati
o
n
as
a
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
e
p
r
o
v
i
d
es
v
alu
ab
le
i
n
s
ig
h
ts
,
as
illu
s
tr
ated
in
T
ab
le
6
an
d
Fig
u
r
e
8
co
n
s
is
ts
o
f
th
e
m
o
d
els
B
i
-
GR
U,
LR
,
XGBo
o
s
t,
SV
R
,
an
d
FB
Pro
p
h
et.
B
eg
in
n
i
n
g
with
B
i
-
GR
U,
th
e
m
o
d
el
ac
h
iev
es
an
R2
s
co
r
e
o
f
0
.
9
8
2
1
,
MA
E
o
f
0
.
0
2
0
,
an
d
MA
PE
o
f
4
.
1
2
%.
F
ig
u
r
e
8
(
a)
h
ig
h
lig
h
ts
g
o
o
d
alig
n
m
e
n
t
b
etwe
en
p
r
ed
icted
an
d
ac
tu
al
p
r
ices,
th
o
u
g
h
s
o
m
e
d
ev
iatio
n
s
ar
e
v
is
ib
le
d
u
r
in
g
v
o
latile
p
er
io
d
s
.
L
R
p
e
r
f
o
r
m
s
ex
ce
p
tio
n
ally
well
with
th
e
h
ig
h
est
R2
s
co
r
e
o
f
0
.
9
9
1
9
,
MA
E
o
f
0
.
0
1
6
,
an
d
t
h
e
lo
west
MA
PE
o
f
2
.
4
5
%.
F
ig
u
r
e
8
(
b
)
s
h
o
ws
n
ea
r
-
p
e
r
f
ec
t
o
v
er
l
ap
b
etwe
en
p
r
ed
icte
d
an
d
ac
tu
al
p
r
ices,
em
p
h
asizin
g
its
p
r
ed
ictiv
e
ac
cu
r
ac
y
.
XGBo
o
s
t
clo
s
ely
m
atch
es
(
a)
(
b
)
(
c)
(
d
)
(
e)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
3
,
Ma
r
ch
20
2
5
:
1
96
4
-
1
97
5
1972
L
R
,
ac
h
iev
in
g
an
R2
s
co
r
e
o
f
0
.
9
9
1
8
,
MA
E
o
f
0
.
0
1
6
,
an
d
a
s
lig
h
tly
h
ig
h
er
MA
PE
o
f
2
.
4
7
%.
F
ig
u
r
e
8
(
c)
co
n
f
ir
m
s
th
e
m
o
d
el
’
s
ex
ce
p
tio
n
al
p
r
ec
is
io
n
,
with
m
in
im
a
l
d
ev
iatio
n
s
.
SVR
also
d
eliv
er
s
s
tr
o
n
g
p
er
f
o
r
m
an
ce
,
with
an
R2
s
co
r
e
o
f
0
.
9
9
1
0
,
MA
E
o
f
0
.
0
1
7
,
an
d
MA
PE
o
f
2
.
5
3
%.
F
ig
u
r
e
8
(
d
)
r
ef
lect
s
r
o
b
u
s
t
alig
n
m
en
t
b
etwe
en
ac
tu
al
an
d
p
r
ed
icted
p
r
ices,
th
o
u
g
h
it
s
h
o
ws
s
lig
h
tly
lar
g
er
er
r
o
r
s
co
m
p
a
r
ed
to
L
R
an
d
XGBo
o
s
t.
F
in
ally
,
FB
p
r
o
p
h
et
ac
h
iev
es
an
R2
s
co
r
e
o
f
0
.
9
8
4
6
,
MA
E
o
f
0
.
0
2
0
,
a
n
d
MA
PE
o
f
5
.
2
0
%.
F
ig
u
r
e
8
(
e
)
d
em
o
n
s
tr
ates
r
ea
s
o
n
ab
le
alig
n
m
en
t
b
u
t
s
h
o
ws
m
o
r
e
p
r
o
n
o
u
n
ce
d
d
ev
iatio
n
s
,
esp
ec
ially
d
u
r
i
n
g
p
er
io
d
s
o
f
h
ig
h
v
o
latilit
y
.
Mu
tu
al
in
f
o
r
m
atio
n
as
a
f
ea
tu
r
e
s
elec
tio
n
m
et
h
o
d
p
r
o
v
es
b
e
n
ef
icial,
e
n
h
an
cin
g
th
e
p
r
e
d
ictiv
e
ac
cu
r
ac
y
o
f
all
m
o
d
els an
d
r
ea
f
f
ir
m
in
g
its
v
alu
e
in
o
p
tim
izin
g
B
itco
in
p
r
ice
f
o
r
ec
asti
n
g
.
T
ab
le
6
.
Per
f
o
r
m
an
ce
m
etr
ics o
n
m
u
t
u
al
in
f
o
r
m
atio
n
d
ataset
M
o
d
e
l
M
A
E
M
S
E
M
A
P
E
R
2
s
c
o
r
e
Bi
-
G
R
U
0
.
0
2
0
0
.
0
0
0
8
4
.
1
2
%
0
.
9
8
2
1
X
G
B
o
o
st
0
.
0
1
6
0
.
0
0
0
6
2
.
4
7
%
0
.
9
9
1
8
S
V
R
0
.
0
1
7
0
.
0
0
0
6
2
.
5
3
%
0
.
9
9
1
0
LR
0
.
0
1
6
0
.
0
0
0
6
2
.
4
5
%
0
.
9
9
1
9
F
B
p
r
o
p
h
e
t
0
.
0
2
0
0
.
0
0
0
6
5
.
2
0
%
0
.
9
8
4
6
(
a)
(
b
)
(
c)
(
d
)
(
e)
Fig
u
r
e
8
.
Mo
d
el
r
esu
lts
o
n
m
u
tu
al
in
f
o
r
m
atio
n
d
ataset
;
(
a)
B
i
-
GR
U
,
(
b
)
L
R
,
(
c)
XGBo
o
s
t
,
(
d
)
SVR
,
an
d
(
e)
FB
Pro
p
h
et
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
F
o
r
ec
a
s
tin
g
b
itco
in
p
r
ice
flu
ct
u
a
tio
n
s
:
a
time
s
eries
a
n
a
lysi
s
a
p
p
r
o
a
ch
f
o
r
p
r
ed
ictive
…
(
A
min
e
B
a
ts
i
)
1973
T
h
is
s
tu
d
y
in
v
esti
g
ated
th
e
p
r
ed
ictiv
e
p
er
f
o
r
m
an
ce
o
f
m
ac
h
in
e
lear
n
in
g
m
o
d
els,
p
a
r
ticu
lar
ly
th
eir
ef
f
ec
tiv
en
ess
in
f
o
r
ec
asti
n
g
B
itco
in
p
r
ices.
W
h
ile
p
r
ev
io
u
s
r
esear
ch
h
as
d
em
o
n
s
tr
ated
th
e
p
o
ten
tial
o
f
m
ac
h
in
e
lear
n
i
n
g
m
o
d
els
in
th
e
cr
y
p
to
c
u
r
r
e
n
cy
d
o
m
ain
,
th
e
y
h
av
e
o
f
ten
o
v
e
r
lo
o
k
e
d
th
e
i
m
p
ac
t
o
f
in
teg
r
atin
g
m
u
ltip
le
ec
o
n
o
m
ic
an
d
g
eo
p
o
liti
ca
l
f
ac
to
r
s
,
s
u
ch
as
E
PU,
T
MU
,
T
E
U
,
an
d
GPR
C
.
Ad
d
itio
n
ally
,
th
er
e
h
as
b
ee
n
lim
ited
f
o
cu
s
o
n
h
o
w
t
h
e
r
em
o
v
al
o
f
h
ig
h
ly
co
r
r
elate
d
v
ar
iab
les
with
in
f
ea
tu
r
e
s
ets
m
ig
h
t
en
h
an
c
e
m
o
d
el
ac
cu
r
ac
y
.
Ou
r
f
in
d
in
g
s
in
d
icate
th
at
th
e
XGBo
o
s
t
m
o
d
el
co
n
s
is
ten
tly
o
u
tp
er
f
o
r
m
ed
o
th
er
m
o
d
els
in
p
r
ed
ictin
g
B
itco
in
p
r
ices,
as
r
ef
lecte
d
b
y
its
lo
wer
MA
E
an
d
MSE
ac
r
o
s
s
v
ar
io
u
s
d
atasets
an
d
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
es.
C
o
n
s
o
lid
atin
g
k
e
y
ec
o
n
o
m
ic
in
d
icato
r
s
in
to
a
s
i
n
g
le
d
ataset,
c
o
u
p
led
with
t
h
e
r
em
o
v
a
l
o
f
h
i
g
h
ly
co
r
r
elate
d
f
ea
tu
r
es,
s
ig
n
if
ican
t
ly
im
p
r
o
v
e
d
th
e
m
o
d
el
’
s
p
r
ed
ictiv
e
ac
cu
r
ac
y
.
I
n
ter
esti
n
g
l
y
,
wh
ile
th
e
B
i
-
GR
U
m
o
d
el
ex
h
ib
ited
s
lig
h
tly
h
ig
h
er
MA
E
an
d
MSE
v
alu
es
th
a
n
XGBo
o
s
t,
it
s
till
ac
h
iev
ed
a
s
tr
o
n
g
R
2
s
co
r
e,
d
em
o
n
s
tr
atin
g
its
p
o
te
n
tial f
o
r
c
ap
tu
r
in
g
tem
p
o
r
al
d
ep
e
n
d
en
cies in
v
o
latile
B
itco
in
d
ata.
W
h
en
co
m
p
a
r
in
g
o
u
r
r
esu
lts
to
p
r
io
r
s
tu
d
ies,
it
b
ec
o
m
e
s
clea
r
th
at
m
ac
h
in
e
lear
n
in
g
m
o
d
els
co
n
tin
u
e
to
b
e
h
ig
h
ly
ef
f
ec
tiv
e
in
p
r
ed
ictin
g
cr
y
p
to
cu
r
r
en
cy
p
r
ices.
L
ik
e
ea
r
lier
r
esear
c
h
,
o
u
r
s
tu
d
y
co
n
f
i
r
m
s
th
at
in
co
r
p
o
r
atin
g
m
u
ltip
le
f
ac
to
r
s
in
to
th
e
f
ea
tu
r
e
s
elec
tio
n
p
r
o
ce
s
s
ca
n
s
u
b
s
tan
tially
im
p
r
o
v
e
m
o
d
el
p
er
f
o
r
m
an
ce
.
Ho
wev
er
,
a
k
ey
d
is
tin
ctio
n
in
o
u
r
wo
r
k
is
th
e
em
p
h
asis
o
n
r
em
o
v
in
g
h
ig
h
ly
co
r
r
elate
d
f
ea
tu
r
es,
wh
ich
,
u
n
lik
e
i
n
s
o
m
e
p
r
e
v
io
u
s
s
tu
d
ies,
p
r
o
v
e
d
to
s
ig
n
if
i
ca
n
tly
en
h
an
ce
th
e
ac
cu
r
ac
y
o
f
th
e
p
r
e
d
ictio
n
s
.
T
h
is
s
u
g
g
ests
th
at
ca
r
ef
u
l
f
e
atu
r
e
s
elec
tio
n
is
p
ar
ticu
lar
ly
im
p
o
r
tan
t
w
h
en
d
ea
lin
g
wit
h
co
m
p
le
x
,
v
o
latile
m
ar
k
ets lik
e
cr
y
p
t
o
cu
r
r
e
n
cies.
On
e
lim
itatio
n
o
f
o
u
r
s
tu
d
y
is
th
e
r
elian
ce
o
n
h
is
to
r
i
ca
l
d
ata,
wh
ich
m
ay
n
o
t
f
u
lly
ac
co
u
n
t
f
o
r
f
u
tu
r
e
m
ar
k
et
an
o
m
alies
o
r
s
u
d
d
en
s
h
if
ts
in
m
ar
k
et
co
n
d
itio
n
s
.
T
h
is
co
u
ld
lim
it
th
e
m
o
d
el’
s
ef
f
ec
tiv
en
ess
in
r
ea
l
-
tim
e
s
ce
n
ar
io
s
,
wh
er
e
m
ar
k
et
d
y
n
am
ics
ar
e
co
n
s
tan
tly
ev
o
lv
in
g
.
Fu
r
th
e
r
m
o
r
e,
u
n
e
x
p
ec
t
ed
f
in
d
in
g
s
s
u
ch
as
th
e
h
ig
h
p
er
f
o
r
m
a
n
ce
o
f
th
e
B
i
-
GR
U
m
o
d
el,
d
esp
ite
its
r
elativ
ely
h
ig
h
er
MA
E
a
n
d
MSE
co
m
p
ar
e
d
to
XGBo
o
s
t,
war
r
an
t
f
u
r
th
er
in
v
esti
g
atio
n
.
T
h
ese
r
esu
lts
in
d
ic
ate
th
at
d
ee
p
lear
n
in
g
m
o
d
els
lik
e
B
i
-
G
R
U
m
ay
h
av
e
p
o
ten
tial in
ca
p
tu
r
in
g
p
atter
n
s
o
v
er
tim
e
in
B
itco
in
p
r
ic
e
m
o
v
em
e
n
ts
.
L
o
o
k
in
g
f
o
r
war
d
,
f
u
tu
r
e
r
es
ea
r
ch
co
u
ld
f
o
cu
s
o
n
in
co
r
p
o
r
atin
g
r
ea
l
-
tim
e
d
ata
to
ev
alu
ate
th
e
m
o
d
el’
s
ab
ilit
y
t
o
r
esp
o
n
d
to
m
ar
k
et
s
h
o
c
k
s
an
d
ex
ter
n
al
ev
en
ts
.
Ad
d
itio
n
ally
,
ex
p
l
o
r
in
g
m
o
r
e
a
d
v
an
ce
d
d
ee
p
lear
n
in
g
m
o
d
els,
s
u
ch
as
B
i
-
GR
U
,
m
ay
p
r
o
v
id
e
d
ee
p
er
i
n
s
ig
h
ts
in
to
ca
p
tu
r
in
g
tem
p
o
r
al
d
ep
en
d
e
n
cies
in
v
o
latile
m
ar
k
ets.
T
h
e
in
teg
r
ati
o
n
o
f
r
ea
l
-
tim
e
m
ar
k
et
d
ata
a
n
d
th
e
ex
p
l
o
r
atio
n
o
f
s
u
d
d
e
n
m
ar
k
et
f
lu
ctu
atio
n
s
ar
e
cr
u
cial
s
tep
s
f
o
r
a
d
v
an
ci
n
g
p
r
ed
ictiv
e
m
o
d
elin
g
i
n
cr
y
p
to
cu
r
r
en
c
y
m
ar
k
ets
.
I
n
s
u
m
m
ar
y
,
o
u
r
s
tu
d
y
d
em
o
n
s
tr
ates
th
at
th
e
XG
B
o
o
s
t
m
o
d
el
ex
ce
ls
in
p
r
ed
ictin
g
B
itco
in
p
r
ices,
p
ar
ticu
lar
ly
wh
e
n
r
o
b
u
s
t
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
es
ar
e
ap
p
lied
.
T
h
e
r
em
o
v
al
o
f
h
ig
h
l
y
co
r
r
elate
d
f
ea
t
u
r
es,
alo
n
g
with
t
h
e
in
teg
r
atio
n
o
f
d
iv
er
s
e
m
ar
k
et
i
n
d
i
ca
to
r
s
,
s
ig
n
i
f
ican
tly
im
p
r
o
v
es
m
o
d
el
p
e
r
f
o
r
m
an
ce
.
Ho
we
v
er
,
th
e
in
teg
r
atio
n
o
f
r
ea
l
-
tim
e
d
ata
an
d
an
u
n
d
er
s
tan
d
in
g
o
f
m
o
d
el
r
esp
o
n
s
es
to
m
ar
k
et
s
h
o
ck
s
ar
e
im
p
o
r
ta
n
t
ar
ea
s
f
o
r
f
u
tu
r
e
r
esear
c
h
.
4.
CO
NCLU
SI
O
N
I
n
co
n
clu
s
io
n
,
th
is
s
tu
d
y
ex
p
lo
r
ed
th
e
ef
f
ec
tiv
en
ess
o
f
v
ar
io
u
s
f
ac
to
r
s
in
p
r
e
d
ictin
g
B
itco
in
p
r
ices.
T
o
ac
h
iev
e
t
h
is
,
we
d
ev
elo
p
ed
a
u
n
iq
u
e
d
ataset
co
m
p
r
is
in
g
n
ea
r
l
y
4
0
f
ea
tu
r
es
f
r
o
m
d
if
f
er
en
t
d
o
m
ain
s
.
Usi
n
g
f
ilter
m
eth
o
d
s
f
o
r
f
ea
t
u
r
e
s
elec
tio
n
,
we
d
er
iv
e
d
two
a
d
d
itio
n
al
d
atasets
f
r
o
m
th
e
o
r
ig
in
al
o
n
e.
W
e
th
en
ap
p
lied
s
ev
er
al
m
ac
h
in
e
lear
n
in
g
m
o
d
els,
in
clu
d
in
g
XGBo
o
s
t,
SVR
,
L
R
,
an
d
F
B
Pro
p
h
et,
as
well
as
a
d
ee
p
lear
n
in
g
m
o
d
el
b
ased
o
n
B
i
-
GR
U,
to
an
aly
ze
th
eir
ca
p
a
b
ilit
y
to
ca
p
tu
r
e
p
r
ice
m
o
v
em
e
n
t
p
atter
n
s
.
Ou
r
r
esu
lts
d
em
o
n
s
tr
ated
th
at
XGBo
o
s
t
an
d
LR
co
n
s
is
ten
tly
o
u
tp
er
f
o
r
m
ed
o
th
er
m
o
d
els,
s
h
o
win
g
th
e
lo
west
er
r
o
r
v
alu
es
ac
r
o
s
s
all
d
ataset
s
.
T
h
is
in
d
i
ca
tes
th
eir
s
u
p
er
io
r
ab
ilit
y
to
p
r
ed
ict
B
itco
in
p
r
ices
ac
cu
r
ately
.
Ad
d
itio
n
ally
,
we
f
o
u
n
d
th
at
u
tili
zin
g
C
o
r
r
elatio
n
an
d
Mu
tu
al
I
n
f
o
r
m
at
io
n
as
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
es
ef
f
ec
tiv
ely
r
ed
u
ce
d
th
e
er
r
o
r
r
ates
o
f
th
e
m
o
d
els.
T
h
is
h
ig
h
lig
h
ts
th
e
im
p
o
r
tan
ce
o
f
f
ea
t
u
r
e
s
elec
tio
n
in
e
n
h
an
ci
n
g
m
o
d
el
p
er
f
o
r
m
an
ce
.
Fu
tu
r
e
r
esear
ch
co
u
ld
b
e
n
ef
it
f
r
o
m
ex
p
lo
r
in
g
s
p
ec
ialized
tim
e
s
er
ies
f
o
r
ec
asti
n
g
m
o
d
els,
s
u
ch
as
T
im
esNet,
N
B
E
AT
S
,
an
d
N
-
HI
T
S,
to
f
u
r
th
er
im
p
r
o
v
e
p
r
ed
ictio
n
ac
cu
r
ac
y
.
T
h
ese
m
o
d
els
ar
e
s
p
ec
if
ically
d
esig
n
ed
to
h
an
d
le
tim
e
s
er
ies
d
ata
an
d
co
u
ld
p
r
o
v
id
e
d
ee
p
e
r
in
s
ig
h
ts
in
to
th
e
p
atter
n
s
an
d
tr
en
d
s
u
n
d
er
ly
in
g
B
itco
in
p
r
ice
m
o
v
em
en
ts
.
Mo
r
eo
v
er
,
in
teg
r
a
tin
g
m
o
r
e
ad
v
an
ce
d
m
ac
h
in
e
lear
n
in
g
an
d
d
ee
p
lear
n
in
g
tech
n
iq
u
es,
as
well
as
co
n
s
id
er
in
g
ad
d
itio
n
al
ex
ter
n
al
f
ac
t
o
r
s
an
d
th
e
in
teg
r
atio
n
o
f
r
e
al
-
tim
e
d
ata
,
co
u
l
d
f
u
r
th
er
r
ef
in
e
th
e
p
r
e
d
ictiv
e
m
o
d
els an
d
co
n
tr
ib
u
te
t
o
th
e
g
r
o
win
g
f
ield
o
f
cr
y
p
to
cu
r
r
en
cy
m
ar
k
et
p
r
e
d
ictio
n
.
RE
F
E
R
E
NC
E
S
[
1
]
S
.
N
a
k
a
mo
t
o
a
n
d
A
.
P
.
E
.
C
.
S
y
s
t
e
m,
“
B
i
t
c
o
i
n
:
a
p
e
e
r
-
to
-
p
e
e
r
e
l
e
c
t
r
o
n
i
c
c
a
s
h
sy
st
e
m,
”
p
p
.
1
–
9
,
2
0
0
8
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
g
i
t
.
d
h
i
mm
e
l
.
c
o
m
/
b
i
t
c
o
i
n
-
w
h
i
t
e
p
a
p
e
r
/
[
2
]
E.
Za
g
h
l
o
u
l
,
T.
Li
,
M
.
W
.
M
u
t
k
a
,
a
n
d
J
.
R
e
n
,
“
B
i
t
c
o
i
n
a
n
d
b
l
o
c
k
c
h
a
i
n
:
se
c
u
r
i
t
y
a
n
d
p
r
i
v
a
c
y
,
”
I
EE
E
I
n
t
e
rn
e
t
o
f
T
h
i
n
g
s
J
o
u
r
n
a
l
,
v
o
l
.
7
,
n
o
.
1
0
,
p
p
.
1
0
2
8
8
–
1
0
3
1
3
,
O
c
t
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
JI
O
T.
2
0
2
0
.
3
0
0
4
2
7
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.