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.
1
4
,
No
.
6
,
Dec
em
b
er
2
0
2
5
,
p
p
.
4
8
4
8
~
4
8
6
4
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
14
.i
6
.
p
p
4
8
4
8
-
4
8
6
4
4848
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
A merchan
t
a
na
ly
tics f
ra
me
wo
rk f
o
r re
v
enue
f
o
recas
ting a
nd
financia
l stress
de
tect
io
n
using
t
ra
n
sa
ction da
ta
Ya
ra
H
a
rb,
Wis
s
a
m
B
a
a
k
lin
i,
Na
din
e
Abba
s
,
Se
if
edine K
a
dry
D
e
p
a
r
t
me
n
t
of
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
M
a
t
h
e
ma
t
i
c
s,
Le
b
a
n
e
s
e
A
mer
i
c
a
n
U
n
i
v
e
r
si
t
y
,
B
e
i
r
u
t
,
Le
b
a
n
o
n
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
4
,
2
0
2
5
R
ev
is
ed
Oct
3
0
,
2
0
2
5
Acc
ep
ted
No
v
8
,
2
0
2
5
By
p
ro
c
e
ss
in
g
p
a
y
m
e
n
ts
a
n
d
p
ro
v
id
i
n
g
sp
e
c
ialize
d
fin
a
n
c
ial
se
rv
ice
s,
a
c
q
u
iri
n
g
b
a
n
k
s
a
re
e
ss
e
n
ti
a
l
fo
r
m
e
rc
h
a
n
ts’
o
p
e
ra
ti
o
n
s.
T
o
f
o
re
c
a
st
30
-
d
a
y
re
v
e
n
u
e
traje
c
to
ries
,
i
d
e
n
ti
f
y
se
a
so
n
a
l
d
e
m
a
n
d
p
a
tt
e
rn
s,
a
n
d
i
d
e
n
ti
fy
e
a
rly
in
d
ica
to
rs
o
f
fin
a
n
c
ial
stre
ss
,
t
h
is
p
a
p
e
r
p
re
se
n
ts
a
sc
a
lab
le
m
e
rc
h
a
n
t
a
n
a
ly
ti
c
s
fra
m
e
wo
rk
t
h
a
t
b
e
n
e
fit
s
fro
m
tran
sa
c
ti
o
n
a
l
d
a
ta.
Th
e
f
ra
m
e
wo
rk
c
a
p
tu
re
s
m
u
lt
i
-
lev
e
l
se
a
so
n
a
li
ti
e
s
u
sin
g
P
r
o
p
h
e
t
ti
m
e
se
ries
m
o
d
e
l
,
a
ll
o
wi
n
g
d
y
n
a
m
ic
p
r
o
d
u
c
t
o
ffe
ri
n
g
s
l
i
k
e
re
v
e
n
u
e
-
b
a
se
d
lo
a
n
s.
P
r
o
a
c
ti
v
e
risk
ma
n
a
g
e
m
e
n
t
is
su
p
p
o
rted
o
ffe
ri
n
g
s
li
k
e
re
v
e
n
u
e
-
b
a
se
d
lo
a
n
s.
P
r
o
a
c
ti
v
e
risk
m
a
n
a
g
e
m
e
n
t
is
su
p
p
o
rted
.
b
y
a
n
e
w
stre
ss
-
flag
g
in
g
m
e
c
h
a
n
ism
th
a
t
id
e
n
ti
fies
m
e
rc
h
a
n
ts
a
t
risk
b
a
se
d
o
n
d
e
v
iati
o
n
s
in
re
v
e
n
u
e
tre
n
d
s.
T
h
e
fra
m
e
wo
rk
a
c
h
iev
e
d
a
m
e
d
ian
3
0
-
d
a
y
mean
a
b
so
l
u
te
p
e
rc
e
n
tag
e
e
rro
r
(M
APE
)
of
5
6
.
5
1
%
a
fter
th
e
v
a
li
d
a
ti
o
n
on
a
d
a
tas
e
t
with
1
3
0
,
3
5
0
tra
n
sa
c
ti
o
n
s
fro
m
4
6
0
m
e
rc
h
a
n
ts
in
a
v
o
l
a
ti
le
e
c
o
n
o
m
ic
e
n
v
ir
o
n
m
e
n
t
.
T
h
e
m
o
d
e
l
d
e
m
o
n
stra
ted
sig
n
ifi
c
a
n
t
p
ra
c
ti
c
a
l
u
ti
li
t
y
i
n
id
e
n
ti
fy
i
n
g
fin
a
n
c
ial
d
i
stre
ss
a
n
d
se
g
m
e
n
ti
n
g
m
e
rc
h
a
n
t
b
e
h
a
v
i
o
r,
d
e
sp
it
e
it
s
m
o
d
e
ra
te
p
re
d
icti
v
e
p
re
c
isio
n
,
wh
ich
is
c
o
m
m
o
n
c
h
a
ll
e
n
g
e
i
n
h
i
g
h
-
v
a
rian
c
e
m
e
rc
h
a
n
t
d
a
tas
e
ts.
M
o
d
e
l
o
u
t
p
u
ts
a
re
c
o
n
v
e
rted
i
n
t
o
d
e
c
i
sio
n
-
su
p
p
o
rt
v
isu
a
li
z
a
ti
o
n
s
a
l
o
n
g
wit
h
a
n
in
tera
c
ti
v
e
d
a
sh
b
o
a
rd
.
K
ey
w
o
r
d
s
:
Fin
an
cial
s
tr
ess
d
etec
tio
n
Me
r
ch
an
t a
n
aly
tics
Pro
p
h
et
m
o
d
el
T
im
e
s
er
ies f
o
r
ec
asti
n
g
T
r
an
s
ac
tio
n
d
ata
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
:
Nad
in
e
Ab
b
as
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
Ma
th
e
m
atics,
L
eb
an
e
s
e
Am
er
ican
Un
iv
er
s
ity
B
eir
u
t,
L
eb
an
o
n
E
m
ail:
n
ad
in
e.
ab
b
as@
lau
.
ed
u
.
lb
1.
I
NT
RO
D
UCT
I
O
N
Acq
u
ir
in
g
b
an
k
s
o
f
f
er
v
alu
e
-
a
d
d
ed
s
er
v
ices
s
u
ch
as
cr
ed
it
a
n
d
lo
an
s
,
also
,
th
e
y
wo
r
k
o
n
f
ac
ilit
atin
g
m
er
ch
an
t
tr
a
n
s
ac
tio
n
s
in
th
e
d
y
n
am
ic
f
i
n
an
cial
s
er
v
ices
in
d
u
s
tr
y
.
Of
f
e
r
in
g
s
p
ec
ialized
s
u
p
p
o
r
t,
e
x
p
ec
tin
g
d
em
an
d
s
p
ik
es,
a
n
d
r
e
d
u
cin
g
r
is
k
s
all
d
ep
en
d
o
n
a
n
u
n
d
er
s
ta
n
d
in
g
o
f
m
er
c
h
an
t p
e
r
f
o
r
m
an
c
e
as d
eter
m
in
ed
b
y
r
ev
en
u
e
f
o
r
ec
asti
n
g
an
d
f
in
an
cial
h
ea
lth
ev
alu
atio
n
.
Sin
ce
s
m
all
an
d
m
ed
iu
m
-
s
ized
b
u
s
in
ess
es,
wh
ich
in
clu
d
e
m
an
y
r
etailer
s
,
ac
co
u
n
t
f
o
r
ar
o
u
n
d
5
0
%
o
f
th
e
wo
r
ld
’
s
g
r
o
s
s
d
o
m
esti
c
p
r
o
d
u
ct
(
GDP
)
,
th
eir
f
in
an
cial
s
tab
ilit
y
is
ess
en
tial
to
ec
o
n
o
m
ic
ex
p
an
s
io
n
[
1
]
.
Ad
v
a
n
ce
d
a
n
al
y
tics
s
o
lu
tio
n
s
ar
e
n
ec
ess
ar
y
b
ec
au
s
e
ex
is
tin
g
ap
p
r
o
ac
h
es
f
r
e
q
u
en
tly
m
is
s
th
e
co
m
p
lex
s
ea
s
o
n
al
p
atter
n
s
an
d
u
n
e
x
p
ec
ted
d
is
tr
ess
s
ig
n
als
p
r
esen
t
in
tr
an
s
ac
tio
n
d
ata.
T
h
is
p
ap
er
p
r
o
p
o
s
es
a
m
er
ch
an
t
an
aly
tics
f
r
am
ewo
r
k
f
o
r
r
ev
en
u
e
p
r
e
d
ictio
n
,
s
ea
s
o
n
al
tr
en
d
d
etec
tio
n
,
an
d
f
in
an
cial
s
tr
ess
id
en
tific
atio
n
.
T
h
e
f
r
am
ew
o
r
k
f
o
r
ec
asts
3
0
-
d
ay
r
e
v
en
u
e
b
y
u
s
in
g
th
e
Pr
o
p
h
et
tim
e
s
er
ies
f
o
r
ec
asti
n
g
m
o
d
el,
wh
ich
h
as
p
r
o
v
e
n
s
tr
o
n
g
p
er
f
o
r
m
an
ce
ef
f
ec
tiv
ely
in
f
in
a
n
ci
al
co
n
tex
ts
s
u
ch
as
f
o
r
ec
asti
n
g
b
an
k
ca
p
ital
r
atio
s
[
2
]
.
T
h
is
allo
ws
b
an
k
s
to
p
r
o
v
id
e
d
y
n
a
m
ic
f
in
an
cial
p
r
o
d
u
cts,
lik
e
s
h
o
r
t
-
ter
m
lo
an
s
,
d
u
r
in
g
p
er
i
o
d
s
o
f
h
ig
h
d
em
an
d
.
Sig
n
if
ican
t
r
e
v
en
u
e
d
ec
lin
es
s
et
o
f
f
a
n
ew
s
tr
ess
f
lag
th
at
n
o
tifie
s
b
an
k
s
o
f
v
u
ln
er
a
b
le
m
e
r
ch
an
ts
an
d
en
c
o
u
r
ag
es
ea
r
ly
ac
tio
n
.
T
h
is
s
tu
d
y
is
d
r
iv
en
b
y
th
e
n
e
ed
to
ad
d
r
ess
is
s
u
es
s
u
ch
as
d
ata
s
p
ar
s
ity
,
cu
r
r
en
cy
f
lu
ctu
atio
n
s
,
an
d
co
m
p
u
tat
io
n
al
ef
f
icien
cy
in
tr
an
s
f
o
r
m
i
n
g
r
aw
tr
an
s
ac
tio
n
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
A
merch
a
n
t a
n
a
lytics fr
a
mewo
r
k
fo
r
r
ev
en
u
e
fo
r
ec
a
s
tin
g
a
n
d
fin
a
n
cia
l str
ess
d
etec
tio
n
u
s
in
g
…
(
Ya
r
a
Ha
r
b
)
4849
d
ata
in
to
ac
tio
n
ab
le
in
s
ig
h
ts
.
B
an
k
an
aly
s
ts
ca
n
ac
ce
s
s
th
e
f
r
am
ewo
r
k
’
s
in
ter
ac
tiv
e
d
ash
b
o
ar
d
f
o
r
ex
am
in
in
g
m
er
ch
an
t p
e
r
f
o
r
m
an
ce
,
w
h
ich
was a
p
p
lied
to
a
d
ataset
o
f
1
3
0
,
3
5
0
tr
an
s
ac
tio
n
s
f
r
o
m
4
6
0
m
er
ch
an
ts
.
Ma
n
y
ex
is
tin
g
wo
r
k
s
h
a
v
e
ad
d
r
ess
ed
s
ales
f
o
r
ec
asti
n
g
,
f
in
a
n
cial
d
is
tr
ess
p
r
ed
ictio
n
,
an
d
t
im
e
-
s
er
ies
an
o
m
aly
d
etec
tio
n
u
s
in
g
s
tatis
tical
an
d
m
ac
h
in
e
lea
r
n
in
g
t
ec
h
n
iq
u
es.
E
ar
ly
s
tu
d
ies
f
o
c
u
s
ed
o
n
tr
ad
itio
n
al
ec
o
n
o
m
etr
ic
an
d
au
to
r
e
g
r
ess
iv
e
in
teg
r
ated
m
o
v
i
n
g
av
er
a
g
e
(
AR
I
MA
)
-
b
ased
f
o
r
ec
asti
n
g
f
o
r
r
etail
an
d
b
an
k
in
g
d
ata
[
3
]
–
[
7
]
,
wh
ile
n
ewe
r
s
tu
d
ies
ad
o
p
ted
a
d
v
an
ce
d
m
o
d
els
s
u
ch
as
Pro
p
h
et,
ex
tr
em
e
g
r
ad
ie
n
t
b
o
o
s
tin
g
(
XGBo
o
s
t
)
,
an
d
h
y
b
r
id
d
ee
p
lear
n
in
g
ar
ch
ite
ctu
r
es
to
im
p
r
o
v
e
s
ea
s
o
n
al
tr
en
d
ca
p
tu
r
e
an
d
in
ter
p
r
etab
ilit
y
[
8
]
–
[
1
2
]
.
T
h
e
r
esear
ch
in
[
1
3
]
–
[
1
6
]
ex
p
lo
r
e
d
n
eu
r
al
an
d
t
r
an
s
f
o
r
m
e
r
-
b
ase
d
s
eq
u
en
ce
m
o
d
els,
s
h
o
win
g
en
h
an
ce
d
r
o
b
u
s
tn
ess
to
n
o
n
lin
ea
r
a
n
d
m
u
lti
-
s
ea
s
o
n
al
b
eh
a
v
io
r
in
tr
an
s
ac
tio
n
al
d
atasets
.
I
n
p
ar
allel,
s
ev
er
al
r
esear
ch
er
s
in
v
esti
g
ated
f
in
an
cial
s
tr
ess
d
etec
tio
n
an
d
an
o
m
aly
id
e
n
tific
atio
n
in
ti
m
e
-
s
er
ies
d
ata
u
s
in
g
th
r
esh
o
ld
in
g
,
m
u
ltiv
ar
iate
m
o
d
elin
g
,
an
d
d
ee
p
lear
n
i
n
g
b
ased
m
eth
o
d
s
[
1
7
]
–
[
2
3
]
.
T
h
ese
s
tu
d
ies
u
n
d
er
s
co
r
e
th
e
g
r
o
win
g
c
o
n
v
e
r
g
en
ce
o
f
f
o
r
ec
asti
n
g
ac
c
u
r
ac
y
,
ex
p
lain
ab
ilit
y
,
an
d
r
is
k
a
n
aly
tics
in
f
in
an
cial
an
d
r
etail
d
o
m
ain
s
,
m
o
tiv
atin
g
th
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
.
T
h
is
s
tu
d
y
co
n
tr
ib
u
tes
to
th
e
l
iter
atu
r
e
b
y
ad
a
p
tin
g
tim
e
s
er
ies
f
o
r
ec
asti
n
g
a
n
d
d
is
tr
ess
p
r
ed
ictio
n
t
o
th
e
m
er
ch
an
t
co
n
te
x
t,
a
r
elativ
ely
u
n
d
e
r
ex
p
lo
r
ed
ar
ea
.
T
h
e
m
ain
co
n
tr
ib
u
tio
n
s
o
f
th
is
p
ap
er
ar
e
as
f
o
llo
ws.
First,
th
is
s
tu
d
y
d
ev
elo
p
s
an
a
n
aly
tics
f
r
am
ewo
r
k
t
h
at
in
teg
r
ates
f
o
r
ec
asti
n
g
,
clu
s
ter
in
g
,
a
n
d
s
tr
ess
d
etec
tio
n
in
to
a
u
n
i
f
ied
p
ip
eli
n
e.
Seco
n
d
,
it
v
alid
ates
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
u
s
in
g
r
ea
l
tr
an
s
ac
t
io
n
-
lev
el
d
ata
f
r
o
m
L
eb
an
ese
m
er
ch
an
ts
.
T
h
ir
d
,
it
p
r
esen
ts
an
in
ter
ac
tiv
e
d
ash
b
o
ar
d
th
at
allo
ws
an
aly
s
ts
to
v
is
u
alize
m
er
ch
an
t
b
eh
av
io
r
,
r
is
k
lev
el,
a
n
d
s
tr
ess
s
ig
n
als
in
r
ea
l
tim
e.
T
h
ese
co
n
tr
ib
u
tio
n
s
co
llectiv
el
y
d
em
o
n
s
tr
ate
th
e
f
r
am
ewo
r
k
’
s
p
r
ac
tical
v
alu
e
in
s
u
p
p
o
r
tin
g
d
ata
-
d
r
i
v
en
cr
e
d
it
d
ec
is
io
n
s
an
d
p
r
o
ac
tiv
e
r
i
s
k
m
an
ag
em
en
t
in
ac
q
u
ir
in
g
b
an
k
s
.
T
h
e
p
ap
er
is
o
r
g
an
ized
as
f
o
llo
ws:
s
ec
tio
n
2
r
ev
iews
r
e
lated
wo
r
k
o
n
r
etail
s
ales
f
o
r
ec
asti
n
g
,
f
in
an
cial
d
is
tr
ess
p
r
e
d
ictio
n
,
a
n
d
tim
e
s
er
ies
an
o
m
aly
d
etec
tio
n
.
Sectio
n
3
d
etails
th
e
m
eth
o
d
o
lo
g
y
,
in
clu
d
in
g
d
ata
an
d
m
o
d
elin
g
.
Sectio
n
4
d
is
cu
s
s
es
r
esu
lts
,
wh
ile
s
ec
t
i
o
n
5
co
v
er
s
im
p
lem
en
tatio
n
an
d
u
s
er
in
ter
f
ac
e
.
Sectio
n
6
co
v
er
s
m
o
d
el
b
en
ch
m
ar
k
in
g
a
n
d
ju
s
tific
atio
n
,
an
d
f
in
ally
,
co
n
clu
s
io
n
s
ar
e
d
r
aw
n
in
s
ec
tio
n
7
with
f
u
tu
r
e
d
ir
ec
tio
n
s
.
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
2
.
1
.
Ret
a
il sa
les f
o
re
ca
s
t
ing
T
im
e
s
er
ies
f
o
r
ec
asti
n
g
is
co
m
m
o
n
ly
u
s
ed
to
p
r
e
d
ict
s
ales,
o
p
tim
ize
in
v
en
t
o
r
y
,
a
n
d
s
u
p
p
o
r
t
s
tr
ateg
ic
d
ec
is
io
n
-
m
ak
in
g
.
C
u
r
r
e
n
t
s
tu
d
ies
s
h
o
w
h
o
w
well
s
o
p
h
is
tic
ated
m
o
d
els
h
a
n
d
le
ir
r
eg
u
lar
d
ata
s
tr
u
ctu
r
es
an
d
ca
p
tu
r
e
s
ea
s
o
n
al
p
atter
n
s
.
Pro
p
h
et’
s
ab
ilit
y
to
ac
c
u
r
ately
m
o
d
el
s
ea
s
o
n
al
v
ar
iatio
n
s
a
n
d
h
o
lid
ay
ef
f
ec
ts
was
d
em
o
n
s
tr
ated
b
y
s
ev
er
al
r
es
ea
r
ch
er
s
wh
en
th
e
y
ap
p
lied
Pro
p
h
et
an
d
lig
h
t
g
r
ad
ien
t
b
o
o
s
tin
g
m
ac
h
in
e
(
L
ig
h
tGB
M
)
to
W
alm
ar
t
s
ale
s
d
ata
[
3
]
.
I
n
a
s
im
ilar
o
th
er
r
esear
ch
er
s
u
s
ed
Pro
p
h
et
to
f
o
r
ec
ast
s
u
p
er
m
ar
k
et
s
ales
an
d
p
r
o
v
en
th
at
it
p
er
f
o
r
m
ed
b
etter
th
an
c
o
n
v
e
n
tio
n
al
AR
I
MA
m
o
d
els
d
u
e
to
th
e
p
o
s
s
ib
ilit
y
o
f
h
an
d
lin
g
m
u
ltip
le
s
ea
s
o
n
alities
[
4
]
.
Fo
r
f
u
r
n
itu
r
e
s
ales,
o
th
er
r
esear
ch
er
s
d
ev
elo
p
e
d
a
h
y
b
r
id
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
(
C
NN
)
-
b
id
ir
ec
tio
n
al
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
B
iLST
M
)
m
o
d
el
th
at
o
u
tp
e
r
f
o
r
m
e
d
tr
ad
itio
n
al
m
eth
o
d
s
in
ca
p
t
u
r
in
g
co
m
p
le
x
tem
p
o
r
al
d
e
p
en
d
e
n
cies
[
5
]
.
I
n
th
eir
th
o
r
o
u
g
h
in
v
esti
g
atio
n
o
f
d
ee
p
lear
n
in
g
tech
n
i
q
u
es
f
o
r
tim
e
s
er
ies
f
o
r
ec
asti
n
g
,
o
th
er
r
esear
ch
er
s
em
p
h
asized
th
e
n
ec
ess
ity
o
f
m
o
d
els
th
at
ca
n
m
an
ag
e
n
o
is
y
a
n
d
ir
r
eg
u
lar
d
at
a,
wh
ich
ar
e
t
y
p
ical
in
m
er
ch
a
n
t
tr
an
s
ac
tio
n
e
n
v
ir
o
n
m
en
ts
[
6
]
.
Desp
ite
th
eir
wi
d
esp
r
ea
d
u
s
e,
tr
ad
itio
n
al
m
o
d
els
s
u
ch
as
AR
I
MA
f
r
eq
u
e
n
tly
n
ee
d
t
o
b
e
m
a
n
u
ally
ad
ju
s
ted
f
o
r
tr
en
d
an
d
s
ea
s
o
n
ality
co
m
p
o
n
en
ts
[
7
]
.
Similar
ly
,
r
etail
f
o
r
ec
asti
n
g
h
as
u
s
ed
XGBo
o
s
t
,
a
g
r
ad
ien
t
b
o
o
s
tin
g
f
r
am
ewo
r
k
,
s
in
ce
it
ca
n
h
an
d
le
h
ig
h
-
d
i
m
en
s
io
n
al
d
ata
an
d
m
o
d
el
n
o
n
-
lin
ea
r
r
elatio
n
s
h
i
p
s
;
h
o
wev
er
,
it
r
eq
u
ir
es
ca
r
ef
u
l
f
ea
tu
r
e
en
g
in
ee
r
in
g
[
8
]
.
B
u
ild
in
g
o
n
th
ese
m
eth
o
d
o
l
o
g
ical
ad
v
a
n
ce
s
,
o
t
h
er
r
esear
ch
er
s
d
e
m
o
n
s
tr
ated
th
e
p
r
ac
tical
v
alu
e
o
f
Pro
p
h
et
in
th
e
f
in
a
n
cial
d
o
m
ain
b
y
ap
p
l
y
in
g
it
to
f
o
r
e
ca
s
t
b
an
k
ca
p
ital
r
atio
s
,
s
h
o
win
g
th
at
th
e
m
o
d
el
ca
n
b
e
ef
f
e
ctiv
ely
d
ep
l
o
y
ed
in
lar
g
e
-
s
ca
le,
r
ea
l
-
wo
r
ld
b
a
n
k
in
g
ap
p
licatio
n
s
[
2
]
.
T
h
eir
s
tu
d
y
h
ig
h
lig
h
ts
Pro
p
h
et’
s
f
lex
ib
ilit
y
in
in
co
r
p
o
r
atin
g
ex
o
g
en
o
u
s
r
eg
r
ess
o
r
s
an
d
its
ab
ilit
y
to
s
u
p
p
o
r
t
s
ca
lab
le
d
ep
lo
y
m
en
t
in
r
eg
u
lated
en
v
ir
o
n
m
en
ts
.
Ou
r
m
eth
o
d
in
co
r
p
o
r
ates
tem
p
o
r
al
f
ea
tu
r
e
s
,
s
u
ch
as
th
e
d
ay
o
f
th
e
w
ee
k
,
wh
ich
ar
e
p
ar
t
o
f
f
e
atu
r
e
en
g
in
ee
r
i
n
g
an
d
h
av
e
b
ee
n
em
p
h
asized
as
cr
i
tical
in
[
6
]
.
B
ey
o
n
d
Pro
p
h
et
an
d
class
ical
g
r
ad
ien
t
b
o
o
s
tin
g
m
o
d
els,
r
ec
e
n
t
s
tate
-
of
-
th
e
-
ar
t
d
ee
p
lear
n
in
g
ar
ch
itectu
r
es
h
av
e
s
h
o
wn
g
o
o
d
p
er
f
o
r
m
an
ce
in
r
etail
f
o
r
e
ca
s
tin
g
.
Am
az
o
n
’
s
Dee
p
AR
,
an
au
to
r
eg
r
ess
iv
e
r
ec
u
r
r
en
t
n
etwo
r
k
,
d
em
o
n
s
tr
ated
s
tr
o
n
g
p
r
o
b
ab
ilis
tic
f
o
r
ec
a
s
tin
g
ca
p
ab
ilit
ies
b
y
ca
p
tu
r
in
g
co
m
p
le
x
tem
p
o
r
al
d
ep
en
d
en
cies
in
wate
r
d
em
an
d
s
ce
n
ar
io
s
,
wh
ich
ar
e
d
ir
ec
tly
tr
an
s
f
er
ab
le
to
r
etail
s
ales
f
o
r
ec
asti
n
g
[
9
]
.
Similar
ly
,
th
e
tem
p
o
r
al
f
u
s
io
n
tr
an
s
f
o
r
m
er
(
T
FT)
in
tr
o
d
u
ce
d
atten
ti
o
n
m
ec
h
an
is
m
s
an
d
g
atin
g
lay
e
r
s
th
at
allo
w
in
t
er
p
r
etab
le
m
u
lti
-
h
o
r
izo
n
f
o
r
e
ca
s
ts
,
s
ig
n
if
ican
tly
im
p
r
o
v
in
g
th
e
h
an
d
lin
g
o
f
h
eter
o
g
en
e
o
u
s
r
etail
d
atasets
[
1
0
]
.
I
n
p
ar
allel,
h
y
b
r
id
ar
c
h
i
tectu
r
es
s
u
ch
as
C
NN
-
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
h
av
e
b
ee
n
ap
p
lied
in
wate
r
r
eso
u
r
ce
m
an
ag
em
e
n
t,
wh
er
e
co
n
v
o
lu
tio
n
al
lay
er
s
ca
p
tu
r
e
lo
ca
l
tem
p
o
r
a
l
p
atter
n
s
an
d
L
STM
la
y
er
s
m
o
d
el
lo
n
g
-
ter
m
d
e
p
en
d
e
n
cies,
h
ig
h
lig
h
tin
g
th
eir
ad
ap
tab
ilit
y
f
o
r
c
o
m
p
lex
r
etail
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.
1
4
,
No
.
6
,
Dec
em
b
er
2
0
2
5
:
4
8
4
8
-
4
8
6
4
4850
en
v
ir
o
n
m
en
ts
[
1
1
]
.
T
h
ese
m
o
d
els
r
ep
r
esen
t
a
n
ew
wav
e
o
f
f
o
r
ec
asti
n
g
tech
n
iq
u
es
t
h
at
in
teg
r
ate
d
ee
p
s
eq
u
en
ce
m
o
d
elin
g
,
in
te
r
p
r
eta
b
ilit
y
,
an
d
s
ca
lab
ilit
y
.
T
r
an
s
f
o
r
m
e
r
-
b
ased
m
o
d
els,
wh
ich
u
s
e
atten
tio
n
m
ec
h
an
is
m
s
to
ca
p
tu
r
e
lo
n
g
-
r
an
g
e
d
ep
en
d
en
cies
in
s
eq
u
en
tial
d
ata,
h
av
e
b
ee
n
a
d
o
p
ted
r
ec
e
n
tly
[
1
2
]
.
A
d
etaile
d
r
ev
iew
o
f
t
r
an
s
f
o
r
m
e
r
ap
p
lic
atio
n
s
in
tim
e
s
er
ies
an
aly
s
is
is
g
iv
en
b
y
o
th
er
r
esear
ch
er
s
wh
ich
em
p
h
asized
h
o
w
well
th
ey
wo
r
k
f
o
r
f
o
r
ec
ast
in
g
task
s
[
1
3
]
.
I
n
a
s
im
ilar
,
o
th
er
r
esear
ch
er
s
ex
a
m
in
e
t
r
an
s
f
o
r
m
e
r
-
b
ased
lo
n
g
-
ter
m
f
o
r
ec
asti
n
g
an
d
talk
ab
o
u
t
ad
v
an
ce
m
e
n
ts
in
co
m
p
lex
p
atter
n
m
o
d
elin
g
[
1
4
]
.
W
h
en
e
v
alu
atin
g
t
r
an
s
f
o
r
m
er
m
o
d
els
f
o
r
r
etail
d
em
a
n
d
f
o
r
ec
asti
n
g
,
d
if
f
er
en
t
r
esear
ch
er
s
f
o
u
n
d
th
at
th
ey
s
ig
n
if
ican
tly
o
u
tp
er
f
o
r
m
ed
m
o
r
e
c
o
n
v
e
n
tio
n
al
tech
n
iq
u
es
lik
e
AR
I
MA
[
1
5
]
.
I
n
o
r
d
er
to
f
u
r
th
er
a
d
v
an
ce
th
e
f
ield
,
o
th
er
r
esear
ch
er
s
p
r
o
p
o
s
ed
a
t
r
an
s
f
o
r
m
e
r
-
b
ased
ar
c
h
itectu
r
e
lev
er
ag
in
g
atten
tio
n
with
p
ar
allel
p
r
o
ce
s
s
in
g
to
h
a
n
d
le
lo
n
g
s
eq
u
e
n
ce
s
m
o
r
e
ef
f
icien
tly
[
1
6
]
.
2
.
2
.
P
r
o
ph
et
wit
h t
hresh
o
ld
v
s
.
m
ultiv
a
ria
t
e
f
o
re
c
a
s
t
ing
A
w
i
d
e
l
y
u
s
e
d
a
p
p
r
o
a
c
h
i
n
r
e
t
a
i
l
f
o
r
e
c
a
s
t
i
n
g
c
o
m
b
i
n
e
s
P
r
o
p
h
e
t
w
i
t
h
s
i
m
p
l
e
r
e
s
i
d
u
a
l
t
h
r
e
s
h
o
l
d
i
n
g
t
o
i
d
e
n
t
i
f
y
a
n
o
m
a
l
i
e
s
.
T
h
i
s
a
p
p
r
o
a
c
h
i
s
v
a
l
u
e
d
f
o
r
i
t
s
t
r
a
n
s
p
a
r
e
n
c
y
,
e
a
s
e
o
f
i
m
p
l
e
m
e
n
t
a
t
i
o
n
,
a
n
d
s
u
i
t
a
b
i
l
i
t
y
f
o
r
s
m
a
l
l
-
s
c
a
l
e
d
e
p
l
o
y
m
e
n
t
s
.
H
o
w
e
v
e
r
,
i
t
s
r
e
l
i
a
n
c
e
o
n
s
i
m
p
l
e
s
i
g
n
a
l
s
a
n
d
h
e
u
r
i
s
t
i
c
c
u
t
o
f
f
s
l
i
m
i
t
s
i
t
s
e
f
f
e
c
t
i
v
e
n
e
s
s
i
n
c
a
p
t
u
r
i
n
g
c
r
o
s
s
-
s
e
r
i
e
s
d
e
p
e
n
d
e
n
c
i
e
s
o
r
a
d
a
p
t
i
n
g
t
o
s
t
r
u
c
t
u
r
a
l
c
h
a
n
g
e
s
i
n
t
h
e
d
a
t
a
.
R
e
c
e
n
t
s
t
u
d
i
e
s
h
a
v
e
e
x
p
l
o
r
e
d
t
h
r
e
s
h
o
l
d
-
b
a
s
e
d
a
p
p
r
o
a
c
h
e
s
f
o
r
s
t
r
e
s
s
o
r
a
n
o
m
a
l
y
f
l
a
g
g
i
n
g
i
n
t
i
m
e
-
s
e
r
i
e
s
d
a
t
a
,
e
m
p
h
a
s
i
z
i
n
g
t
h
e
i
r
s
i
m
p
l
i
c
i
t
y
a
n
d
a
d
a
p
t
a
b
i
l
i
t
y
a
c
r
o
s
s
d
o
m
a
i
n
s
.
F
o
r
i
n
s
t
a
n
c
e
,
d
y
n
a
m
i
c
t
h
r
e
s
h
o
l
d
i
n
g
m
e
t
h
o
d
s
a
u
t
o
m
a
t
i
c
a
l
l
y
a
d
j
u
s
t
d
e
t
e
c
t
i
o
n
b
o
u
n
d
a
r
i
e
s
b
a
s
e
d
o
n
l
o
c
a
l
d
a
t
a
d
i
s
t
r
i
b
u
t
i
o
n
s
,
e
n
a
b
l
i
n
g
r
e
l
i
a
b
l
e
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
a
b
n
o
r
m
a
l
p
a
t
t
e
r
n
s
w
h
i
l
e
r
e
d
u
c
i
n
g
f
a
l
s
e
p
o
s
i
t
i
v
e
s
a
n
d
m
i
s
s
e
d
d
e
t
e
c
t
i
o
n
s
[
1
7
]
.
I
n
c
o
n
t
r
a
s
t
,
m
o
d
e
r
n
m
u
l
t
i
v
a
r
i
a
t
e
d
e
e
p
l
e
a
r
n
i
n
g
m
e
t
h
o
d
s
s
u
c
h
a
s
D
e
e
p
A
R
,
T
F
T
,
a
n
d
h
y
b
r
i
d
C
N
N
-
L
S
T
M
a
r
c
h
i
t
e
c
t
u
r
e
s
h
a
v
e
s
h
o
w
n
s
u
p
e
r
i
o
r
c
a
p
a
b
i
l
i
t
i
e
s
i
n
c
o
m
p
l
e
x
f
o
r
e
c
a
s
t
i
n
g
e
n
v
i
r
o
n
m
e
n
t
s
[
9
]
–
[
1
2
]
.
T
h
e
s
e
m
o
d
e
l
s
c
o
m
b
i
n
e
c
o
v
a
r
i
a
t
e
s
a
n
d
r
e
l
a
t
e
d
t
i
m
e
s
e
r
i
e
s
,
g
e
n
e
r
a
t
e
c
o
n
s
i
s
t
e
n
t
p
r
o
b
a
b
i
l
i
s
t
i
c
f
o
r
e
c
a
s
t
s
,
a
n
d
c
a
n
b
e
c
o
u
p
l
e
d
w
i
t
h
r
o
b
u
s
t
a
n
o
m
a
l
y
d
e
t
e
c
t
i
o
n
f
r
a
m
e
w
o
r
k
s
.
E
m
p
i
r
i
c
a
l
s
t
u
d
i
e
s
h
i
g
h
l
i
g
h
t
t
h
e
i
r
s
t
r
e
n
g
t
h
s
i
n
r
e
d
u
c
i
n
g
f
a
l
s
e
a
l
e
r
t
s
,
i
m
p
r
o
v
i
n
g
s
e
n
s
i
t
i
v
i
t
y
t
o
s
t
r
u
c
t
u
r
a
l
c
h
a
n
g
e
s
,
a
n
d
p
r
o
v
i
d
i
n
g
g
r
e
a
t
e
r
s
c
a
l
a
b
i
l
i
t
y
f
o
r
l
a
r
g
e
r
e
t
a
i
l
p
o
r
t
f
o
l
i
o
s
.
I
n
s
u
m
m
a
r
y
,
P
r
o
p
h
e
t
w
i
t
h
t
h
r
e
s
h
o
l
d
i
n
g
r
e
m
a
i
n
s
a
n
a
p
p
r
o
p
r
i
a
t
e
c
h
o
i
c
e
f
o
r
r
a
p
i
d
,
i
n
t
e
r
p
r
e
t
a
b
l
e
m
o
n
i
t
o
r
i
n
g
,
w
h
i
l
e
m
u
l
t
i
v
a
r
i
a
t
e
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
s
r
e
p
r
e
s
e
n
t
t
h
e
s
t
a
t
e
o
f
t
h
e
a
r
t
f
o
r
d
a
t
a
-
r
i
c
h
,
h
i
g
h
-
d
i
m
e
n
s
i
o
n
a
l
r
e
t
a
i
l
f
o
r
e
c
a
s
t
i
n
g
t
a
s
k
s
w
h
e
r
e
a
c
c
u
r
a
c
y
a
n
d
e
a
r
l
y
a
n
o
m
a
l
y
d
e
t
e
c
t
i
o
n
a
r
e
e
s
s
e
n
t
i
a
l
.
2.
3
.
F
ina
ncia
l dis
t
re
s
s
predi
ct
io
n
Fo
r
b
u
s
in
ess
es
an
d
f
in
an
cial
i
n
s
titu
tio
n
s
to
s
tay
s
af
e,
f
in
an
c
ial
d
is
tr
ess
p
r
ed
ictio
n
is
ess
en
tial.
New
d
ev
elo
p
m
e
n
ts
in
m
ac
h
in
e
lear
n
in
g
p
r
o
v
id
e
b
etter
p
r
e
d
ictiv
e
ac
cu
r
ac
y
th
an
ex
is
tin
g
ap
p
r
o
a
ch
es,
wh
ich
m
ain
ly
r
ely
o
n
f
in
an
cial
r
atio
s
.
I
n
o
r
d
er
to
im
p
r
o
v
e
th
e
d
etec
tio
n
o
f
f
in
an
cial
d
is
tr
ess
,
esp
ec
iall
y
in
th
e
p
r
esen
ce
o
f
u
n
ce
r
tain
ty
,
s
ev
er
al
r
esear
ch
er
s
p
r
esen
ted
a
h
y
b
r
id
m
o
d
e
l
th
at
co
m
b
in
es
m
ac
h
in
e
lea
r
n
in
g
an
d
n
etwo
r
k
an
aly
s
is
[
7
]
.
A
m
ac
h
in
e
lear
n
in
g
-
b
ased
ea
r
ly
war
n
in
g
s
y
s
tem
f
o
r
f
in
an
cial
cr
is
es
was
p
r
esen
ted
,
em
p
h
asizin
g
th
e
v
alu
e
o
f
r
ea
l
-
tim
e
m
o
n
ito
r
in
g
,
a
c
o
n
ce
p
t
t
h
at
clo
s
ely
r
e
s
em
b
les
o
u
r
u
s
e
o
f
th
e
s
tr
ess
f
lag
[
1
8
]
.
B
y
u
s
in
g
m
ac
h
in
e
lear
n
in
g
in
b
an
k
in
g
an
aly
tics
,
r
ec
en
t
r
esear
ch
ad
v
an
ce
s
th
is
ar
ea
ev
en
m
o
r
e
.
Oth
er
r
esear
ch
er
s
em
p
lo
y
ed
a
b
an
k
in
g
r
is
k
in
d
ex
to
ev
alu
ate
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
s
f
o
r
f
o
r
ec
asti
n
g
cr
is
es
in
th
e
I
n
d
ia
n
b
an
k
in
g
s
ec
to
r
[
1
9
]
.
A
d
if
f
e
r
e
n
t r
esear
ch
er
co
n
d
u
cted
a
q
u
al
itativ
e
s
u
r
v
ey
o
f
b
an
k
b
o
ar
d
m
em
b
er
s
to
ex
am
in
e
th
e
ad
o
p
tio
n
o
f
AI
a
n
d
m
a
ch
in
e
lear
n
in
g
in
b
an
k
in
g
s
y
s
tem
s
,
h
ig
h
lig
h
tin
g
r
e
al
-
wo
r
ld
im
p
lem
en
tatio
n
ch
allen
g
es
[
2
0
]
.
Oth
er
r
esear
c
h
er
s
m
ap
p
e
d
a
d
ec
ad
e
o
f
d
e
v
elo
p
m
en
ts
in
th
e
ap
p
licatio
n
o
f
m
ac
h
i
n
e
lear
n
in
g
to
b
an
k
i
n
g
r
is
k
m
a
n
ag
em
e
n
t,
p
r
o
v
id
i
n
g
in
s
ig
h
ts
in
to
its
ev
o
lv
in
g
r
o
le
in
f
in
a
n
cial
s
tab
ilit
y
[
2
1
]
.
2.
4
.
T
im
e
s
er
ies a
no
ma
ly
de
t
ec
t
io
n
Fin
d
in
g
u
n
u
s
u
al
p
atter
n
s
in
tim
e
s
er
ies
d
ata
th
at
co
u
ld
i
n
d
icate
o
p
e
r
atio
n
al
is
s
u
es
o
r
f
in
an
cial
d
is
tr
ess
r
eq
u
ir
es
an
o
m
aly
d
et
ec
tio
n
.
A
d
etailed
an
aly
s
is
o
f
an
o
m
aly
d
etec
tio
n
m
eth
o
d
o
l
o
g
ies
was
p
r
esen
ted
b
y
s
ev
er
al
r
esear
ch
er
s
,
w
h
o
d
iv
id
ed
th
em
in
to
t
h
r
ee
ca
t
eg
o
r
ies:
s
tatis
tical,
m
ac
h
in
e
lear
n
in
g
,
an
d
d
ee
p
lear
n
in
g
-
b
ased
tech
n
iq
u
es
[
2
2
]
.
Sev
er
al
r
esear
ch
er
s
s
p
ec
if
ic
ally
ex
p
lo
r
ed
an
o
m
al
y
d
etec
ti
o
n
in
f
in
a
n
cial
tim
e
s
er
ies,
u
s
in
g
tech
n
iq
u
es
s
u
ch
as
p
r
in
cip
al
co
m
p
o
n
en
t
a
n
aly
s
is
an
d
n
eu
r
al
n
etwo
r
k
s
to
d
etec
t
f
r
au
d
u
len
t
o
r
cr
is
is
-
r
elate
d
p
atter
n
s
[
2
3
]
.
R
ec
en
t
ad
v
an
ce
m
en
ts
in
f
in
a
n
cial
an
o
m
aly
d
etec
tio
n
in
clu
d
e
g
r
ap
h
-
b
ased
a
n
d
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
es.
Oth
er
r
esear
ch
er
s
r
ev
iewe
d
an
o
m
aly
d
etec
tio
n
m
eth
o
d
s
in
d
ig
ital
f
in
an
cial
s
y
s
tem
s
,
em
p
h
asizin
g
m
ac
h
in
e
lear
n
in
g
’
s
r
o
le
in
id
en
tif
y
in
g
p
r
o
b
lem
s
[
2
4
]
.
Oth
er
s
p
r
o
p
o
s
ed
g
r
ap
h
-
b
ase
d
an
o
m
aly
d
etec
tio
n
f
o
r
an
ti
-
m
o
n
ey
lau
n
d
er
in
g
,
lev
e
r
ag
in
g
t
r
an
s
ac
tio
n
n
etwo
r
k
s
[
2
5
]
.
Dif
f
er
en
t
r
esear
ch
er
s
d
ev
elo
p
e
d
a
m
ac
h
in
e
lear
n
in
g
m
o
d
el
f
o
r
o
n
lin
e
p
ay
m
en
t
f
r
au
d
,
in
teg
r
atin
g
a
n
o
m
aly
d
etec
tio
n
with
r
is
k
m
an
ag
em
en
t
[
2
6
]
.
Oth
er
s
in
tr
o
d
u
ce
d
a
v
a
r
iatio
n
al
au
to
e
n
co
d
er
(
VAE
)
-
t
r
an
s
f
o
r
m
er
m
o
d
el
f
o
r
a
n
o
m
aly
d
etec
tio
n
in
d
ec
en
tr
alize
d
f
in
a
n
ce
,
s
h
o
wca
s
in
g
d
ee
p
lear
n
in
g
’
s
p
o
ten
tial
in
em
er
g
in
g
f
in
a
n
cial
s
y
s
tem
s
[
2
7
]
.
T
h
e
u
s
ed
s
tr
ess
-
f
lag
g
in
g
m
ec
h
an
is
m
ca
n
b
e
in
ter
p
r
ete
d
as
a
tar
g
ete
d
an
o
m
aly
d
etec
tio
n
m
eth
o
d
,
wh
er
e
s
ig
n
if
ican
t
c
h
an
g
es
f
r
o
m
f
o
r
ec
asted
r
ev
e
n
u
e
p
atter
n
s
tr
ig
g
er
ale
r
ts
.
T
h
ese
aler
t
s
ar
e
co
n
ce
p
tu
ally
g
r
o
u
n
d
ed
in
th
e
a
n
o
m
aly
d
ete
ctio
n
f
r
a
m
ewo
r
k
s
d
is
cu
s
s
ed
in
th
e
liter
atu
r
e
an
d
s
er
v
e
as
ac
t
io
n
ab
le
s
ig
n
als
f
o
r
ac
q
u
ir
in
g
b
an
k
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
A
merch
a
n
t a
n
a
lytics fr
a
mewo
r
k
fo
r
r
ev
en
u
e
fo
r
ec
a
s
tin
g
a
n
d
fin
a
n
cia
l str
ess
d
etec
tio
n
u
s
in
g
…
(
Ya
r
a
Ha
r
b
)
4851
3.
M
E
T
H
O
DO
L
O
G
Y
3
.
1
.
O
bje
c
t
iv
e
T
h
e
m
ain
g
o
al
o
f
th
e
p
r
o
p
o
s
ed
m
er
ch
an
t
a
n
aly
tics
ap
p
r
o
a
ch
is
to
p
r
o
v
id
e
a
cq
u
ir
in
g
b
a
n
k
s
with
a
30
-
d
a
y
f
o
r
war
d
v
iew
o
f
ea
ch
m
er
ch
a
n
t’
s
ex
p
ec
ted
r
ev
en
u
e.
B
ey
o
n
d
f
o
r
ec
asti
n
g
,
t
h
e
m
o
d
el
i
d
en
tifie
s
m
er
ch
an
ts
at
f
in
an
cial
s
tr
ess
r
is
k
,
en
ab
lin
g
ea
r
ly
d
etec
tio
n
o
f
p
o
ten
tial
p
r
o
b
lem
s
o
r
in
s
tab
il
ity
.
Fu
r
th
er
m
o
r
e,
it
co
m
b
in
es
m
er
ch
a
n
ts
in
to
s
im
ilar
b
eh
av
io
r
al
g
r
o
u
p
s
,
allo
wi
n
g
b
an
k
s
to
d
esig
n
tailo
r
e
d
i
n
ter
v
en
tio
n
s
,
c
r
ed
it
s
tr
ateg
ies,
an
d
f
in
an
cial
p
r
o
d
u
cts th
at
ad
d
r
ess
th
e
s
p
ec
if
ic
n
e
ed
s
an
d
r
is
k
p
r
o
f
iles
o
f
ea
c
h
g
r
o
u
p
.
3
.
2
.
Da
t
a
T
h
e
d
ataset
co
n
s
is
ts
o
f
m
er
c
h
an
t
tr
an
s
ac
tio
n
r
ec
o
r
d
s
,
in
cl
u
d
in
g
tr
a
n
s
ac
tio
n
d
ate,
a
m
o
u
n
t,
m
er
ch
a
n
t
n
am
e,
ca
r
d
b
an
k
id
e
n
tific
atio
n
n
u
m
b
er
(
B
I
N
)
,
ap
p
r
o
v
al
s
t
atu
s
,
an
d
cu
r
r
en
c
y
.
Fig
u
r
e
1
s
h
o
ws
a
s
am
p
le
o
f
th
ese
r
ec
o
r
d
s
,
wh
er
e
ea
c
h
r
o
w
is
a
tr
an
s
ac
tio
n
en
tr
y
with
its
ass
o
ciate
d
ap
p
r
o
v
al
s
tatu
s
an
d
am
o
u
n
t
in
L
eb
an
ese
Po
u
n
d
s
.
T
h
e
d
ata
s
o
u
r
ce
d
f
r
o
m
a
b
an
k
s
p
an
at
least
o
n
e
y
ea
r
to
ca
p
tu
r
e
s
ea
s
o
n
al
p
atter
n
s
a
n
d
co
n
tain
s
1
3
0
,
3
5
0
tr
an
s
ac
tio
n
s
.
Af
ter
p
r
e
p
r
o
ce
s
s
in
g
,
t
h
ese
wer
e
co
m
b
in
e
d
in
to
1
3
,
7
7
7
d
aily
m
er
ch
a
n
t
-
d
ate
r
ec
o
r
d
s
ac
r
o
s
s
4
6
0
m
er
c
h
an
ts
,
o
f
wh
ich
1
1
2
,
0
4
8
tr
an
s
ac
tio
n
s
wer
e
ap
p
r
o
v
ed
.
E
x
ter
n
al
co
v
ar
iates
f
iv
e
r
eg
r
e
s
s
o
r
s
ca
p
tu
r
e
tr
an
s
ac
tio
n
al,
b
eh
av
io
r
al,
an
d
m
ac
r
o
-
ec
o
n
o
m
ic
d
r
iv
er
s
:
i
)
d
ec
li
n
e
r
at
e
:
d
ail
y
p
r
o
p
o
r
ti
o
n
o
f
d
ec
l
in
e
d
a
u
t
h
o
r
i
za
t
io
n
s
(
p
ay
m
e
n
t
-
ap
p
r
o
v
al
h
ea
lt
h
)
,
ii
)
t
x
n
co
u
n
t
:
to
tal
n
u
m
b
e
r
o
f
tr
a
n
s
ac
ti
o
n
s
p
er
d
ay
(
a
cti
v
i
ty
in
te
n
s
it
y
)
,
iii
)
c
u
s
to
m
e
r
c
o
u
n
t
:
c
o
u
n
t
o
f
u
n
i
q
u
e
ca
r
d
-
b
i
n
s
p
e
r
d
a
y
(
f
o
o
t
-
t
r
a
f
f
ic
p
r
o
x
y
)
,
iv
)
cu
r
r
e
n
c
y
v
o
la
tili
ty
:
a
b
s
o
l
u
te
d
ail
y
%
c
h
a
n
g
e
i
n
th
e
USD
/LBP
FX
r
ate
(
m
a
cr
o
-
u
n
ce
r
t
ai
n
t
y
)
;
an
d
v
)
is
p
r
o
m
o
tio
n
:
b
in
ar
y
f
lag
f
o
r
p
r
o
m
o
tio
n
a
l
o
r
h
o
lid
ay
p
e
r
io
d
s
(
e.
g
.
,
B
lac
k
Frid
ay
a
n
d
E
id
)
.
T
h
ese
f
ea
tu
r
es
ar
e
m
er
g
e
d
i
n
to
th
e
m
er
c
h
an
t
-
d
a
y
p
an
el
an
d
p
ass
ed
to
Pro
p
h
et
v
ia
“
m
o
d
el.
ad
d
r
eg
r
ess
o
r
(
.
.
.
,
m
o
d
e=
"
m
u
ltip
licativ
e"
)
”,
allo
win
g
ea
ch
f
ac
to
r
to
in
cr
ea
s
e
o
r
r
ed
u
ce
th
e
b
aselin
e
s
ea
s
o
n
al
s
ig
n
al.
Fo
r
th
e
30
-
d
a
y
f
o
r
ec
ast
h
o
r
izo
n
,
ea
c
h
r
eg
r
ess
o
r
is
ca
r
r
ie
d
f
o
r
war
d
with
its
m
o
s
t
r
ec
en
t
v
alu
e
,
p
r
ev
en
tin
g
m
is
s
in
g
co
v
ar
iates in
th
e
f
u
tu
r
e
f
r
am
e.
Fig
u
r
e
1
.
Sam
p
le
s
tr
u
ct
u
r
e
o
f
t
h
e
tr
an
s
ac
tio
n
d
ataset
3
.
3
.
Da
t
a
prepro
ce
s
s
ing
a
nd
f
ea
t
ure
eng
ineering
Pre
p
r
o
ce
s
s
in
g
en
s
u
r
es d
ata
q
u
ality
an
d
p
r
e
p
ar
es it f
o
r
m
o
d
el
in
g
:
‒
C
u
r
r
en
cy
co
n
v
er
s
io
n
:
tr
an
s
ac
tio
n
am
o
u
n
ts
(
L
B
P)
wer
e
co
n
v
er
ted
to
USD
b
y
f
etch
in
g
a
liv
e
ex
ch
an
g
e
r
ate
b
ec
au
s
e
th
e
L
B
P to
USD
r
ate
is
n
o
t stab
le
in
L
eb
an
o
n
d
u
e
to
th
e
ec
o
n
o
m
ic
c
r
is
is
[
2
8
]
.
‒
Data
clea
n
in
g
an
d
v
alid
atio
n
: c
o
lu
m
n
s
wer
e
s
tan
d
ar
d
ized
(
tr
im
m
ed
an
d
r
en
am
e
d
)
an
d
ch
a
n
g
ed
to
p
r
o
p
e
r
ty
p
es
(
n
u
m
er
ic
f
o
r
am
o
u
n
ts
a
n
d
ca
r
d
b
in
s
;
d
atetim
e
f
o
r
tr
an
s
ac
tio
n
d
ates)
.
R
o
ws
with
m
i
s
s
in
g
o
r
in
v
alid
v
alu
es
in
an
y
o
f
th
e
cr
itical
f
ield
s
(
am
o
u
n
t,
ca
r
d
b
in
,
m
er
ch
an
t
n
am
e,
an
d
tr
an
s
ac
tio
n
d
ate)
wer
e
d
r
o
p
p
ed
.
A
b
in
ar
y
d
ec
lin
e
f
lag
(
is
d
ec
lin
e)
is
en
co
d
e
d
f
r
o
m
a
p
p
r
o
v
al
s
tatu
s
f
o
r
d
o
wn
s
tr
ea
m
an
aly
tics
.
‒
Ou
tlier
tr
ea
tm
en
t
an
d
f
ea
tu
r
e
en
g
in
ee
r
i
n
g
:
tr
a
n
s
ac
tio
n
am
o
u
n
ts
wer
e
m
in
o
r
ized
at
th
e
1
s
t
an
d
9
9
th
p
er
ce
n
tiles
to
m
itig
ate
ex
tr
e
m
e
o
u
tlier
s
.
C
alen
d
ar
f
ea
tu
r
es
wer
e
d
er
iv
ed
f
r
o
m
th
e
tr
an
s
ac
tio
n
d
ate:
d
ay
-
of
-
wee
k
,
m
o
n
th
,
y
ea
r
,
ca
p
tu
r
in
g
s
ea
s
o
n
al
,
an
d
tem
p
o
r
al
p
atter
n
s
.
‒
Daily
ag
g
r
eg
atio
n
a
n
d
r
o
llin
g
m
etr
ics:
f
o
r
ea
ch
m
e
r
ch
an
t
an
d
d
ate,
co
m
p
u
te
to
tal
r
e
v
en
u
e
in
USD,
tr
an
s
ac
tio
n
co
u
n
t,
a
n
d
n
u
m
b
er
o
f
d
ec
lin
es.
C
alcu
late
7
-
an
d
3
0
-
d
a
y
r
o
llin
g
a
v
er
ag
es
o
f
d
ai
ly
r
ev
en
u
e
t
o
ca
p
tu
r
e
s
h
o
r
t
-
ter
m
tr
en
d
s
.
T
h
e
r
esu
ltin
g
d
aily
d
ata
f
r
am
e
s
u
p
p
o
r
ts
tim
e
s
er
ies
f
o
r
ec
asti
n
g
,
with
r
o
llin
g
av
er
ag
es (
7
-
an
d
3
0
-
d
ay
)
ad
d
e
d
to
s
m
o
o
th
tr
en
d
s
.
3
.
4
.
M
er
cha
nt
clus
t
er
ing
K
-
m
ea
n
s
clu
s
ter
in
g
was
ap
p
li
ed
to
s
eg
m
en
t
m
er
ch
an
ts
b
as
ed
o
n
tr
a
n
s
ac
tio
n
al
b
eh
a
v
io
r
s
,
p
r
ec
is
ely
to
tal
r
ev
en
u
e,
c
u
s
to
m
er
c
o
u
n
ts
,
an
d
tr
an
s
ac
tio
n
f
r
eq
u
en
cy
.
T
h
e
o
p
tim
al
n
u
m
b
er
o
f
clu
s
ter
s
(
k
)
was
d
eter
m
in
ed
also
th
r
o
u
g
h
s
ilh
o
u
ette
s
co
r
e
m
ax
im
izatio
n
o
v
er
a
r
an
g
e
o
f
2
-
6
clu
s
ter
s
.
T
h
e
ch
o
s
en
m
eth
o
d
en
s
u
r
es f
ast co
m
p
u
tatio
n
an
d
ex
p
lain
ab
le
r
esu
lts
.
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.
1
4
,
No
.
6
,
Dec
em
b
er
2
0
2
5
:
4
8
4
8
-
4
8
6
4
4852
3.
5
.
P
r
o
ph
et
m
o
del:
t
heo
re
t
i
ca
l per
s
pect
iv
e
Pro
p
h
et
is
b
ased
o
n
a
g
en
er
a
lized
ad
d
itiv
e
m
o
d
el
(
GAM
)
f
r
am
ewo
r
k
,
wh
er
e
tim
e
s
er
ies
d
ata
ar
e
d
ec
o
m
p
o
s
ed
in
to
in
ter
p
r
eta
b
le
co
m
p
o
n
en
ts
:
tr
en
d
,
s
ea
s
o
n
a
lity
,
h
o
lid
ay
ef
f
ec
ts
,
a
n
d
n
o
is
e
[
2
]
.
I
t
m
o
d
els
th
e
tim
e
s
er
ies as
in
(
1
)
.
(
)
=
(
)
+
(
)
+
ℎ
(
)
+
(
1
)
W
h
er
e
g
(
t)
d
en
o
tes
th
e
l
o
n
g
-
ter
m
tr
en
d
(
eith
er
lin
ea
r
o
r
lo
g
is
tic
with
ch
an
g
ep
o
in
ts
)
,
s
(
t)
r
ep
r
esen
ts
s
ea
s
o
n
al
p
atter
n
s
u
s
in
g
a
Fo
u
r
ier
s
er
i
es,
h
(
t)
ac
co
u
n
ts
f
o
r
h
o
lid
ay
ef
f
ec
ts
,
an
d
εt
d
en
o
tes
th
e
er
r
o
r
ter
m
.
Un
li
k
e
tr
ad
itio
n
al
m
o
d
els
s
u
ch
as
AR
I
MA
,
Pro
p
h
et
a
u
to
m
atica
lly
d
etec
ts
ch
a
n
g
ep
o
in
ts
an
d
h
an
d
les
m
u
ltip
le
s
ea
s
o
n
alities
,
m
ak
in
g
it
esp
ec
ially
s
u
ited
f
o
r
ir
r
e
g
u
lar
,
h
ig
h
-
v
ar
ian
ce
d
ata
co
m
m
o
n
in
b
u
s
in
ess
an
d
tr
an
s
ac
tio
n
en
v
ir
o
n
m
en
ts
.
Par
am
eter
s
ar
e
esti
m
ated
u
s
in
g
m
ax
im
u
m
a
p
o
s
ter
io
r
i
(
MA
P
)
tech
n
iq
u
es,
with
s
u
p
p
o
r
t
f
o
r
u
s
er
-
d
ef
in
ed
d
is
tr
ib
u
tio
n
s
a
n
d
e
x
ter
n
al
r
eg
r
es
s
o
r
s
.
Pro
p
h
et’
s
i
n
ter
p
r
eta
b
ilit
y
,
s
ca
lab
ilit
y
,
a
n
d
r
o
b
u
s
tn
ess
to
m
is
s
in
g
d
ata
a
n
d
o
u
tlier
s
h
a
v
e
m
a
d
e
it
a
s
tr
o
n
g
ca
n
d
i
d
ate
f
o
r
b
u
s
in
ess
f
o
r
ec
asti
n
g
task
s
,
in
clu
d
in
g
r
ev
en
u
e
p
r
e
d
ictio
n
a
n
d
r
is
k
ass
ess
m
en
t in
b
an
k
in
g
an
d
r
etail
d
o
m
ain
s
.
3.
6
.
Rev
enue
f
o
re
ca
s
t
ing
Face
b
o
o
k
’
s
Pro
p
h
et
m
o
d
el
w
as
u
s
ed
f
o
r
m
er
ch
a
n
t
-
lev
el
r
ev
en
u
e
f
o
r
ec
asti
n
g
d
u
e
t
o
its
ab
ilit
y
to
ef
f
ec
tiv
ely
h
a
n
d
le
m
u
ltip
le
s
ea
s
o
n
alities
an
d
ch
an
g
e
p
o
i
n
ts
with
m
in
im
al
p
ar
a
m
eter
tu
n
in
g
.
Pro
p
h
et’
s
co
r
e
ex
p
ec
tatio
n
s
in
clu
d
e
a
n
ad
d
itiv
e
(
o
r
m
u
ltip
licativ
e)
d
e
co
m
p
o
s
itio
n
o
f
tr
en
d
,
s
ea
s
o
n
ality
,
an
d
n
o
is
e,
in
d
ep
en
d
en
ce
o
f
e
r
r
o
r
s
,
an
d
a
s
tab
le
f
u
tu
r
e
r
esem
b
lin
g
h
i
s
to
r
ical
p
atter
n
s
.
E
ac
h
m
er
c
h
an
t’
s
d
aily
r
e
v
en
u
e
tim
e
s
er
ies
g
o
th
r
o
u
g
h
f
o
r
ec
asti
n
g
with
Pro
p
h
et,
co
n
f
ig
u
r
ed
with
y
ea
r
ly
an
d
wee
k
ly
s
ea
s
o
n
alities
,
m
u
ltip
licativ
e
s
ea
s
o
n
ality
m
o
d
e,
an
d
au
to
m
atic
ch
a
n
g
e
p
o
in
t
d
etec
tio
n
(
m
ax
im
u
m
s
et
to
m
in
(
2
0
,
⌊
N/3
⌋
)
,
wh
er
e
N
is
d
ata
p
o
in
ts
)
.
3.
7
.
F
ina
ncia
l st
re
s
s
det
ec
t
io
n
A
f
in
an
cial
s
tr
ess
d
etec
tio
n
al
g
o
r
ith
m
was
in
tr
o
d
u
ce
d
to
f
la
g
m
er
ch
an
ts
at
r
is
k
.
T
h
e
r
is
k
is
d
ef
in
ed
b
y
a
s
ig
n
if
ican
t
r
ec
en
t
d
r
o
p
i
n
r
ev
en
u
e
,
as
d
etailed
in
Alg
o
r
ith
m
1
.
T
h
is
f
lag
ac
ts
as
an
aler
t
m
ec
h
an
is
m
f
o
r
b
an
k
s
to
tak
e
p
r
ev
e
n
tiv
e
m
ea
s
u
r
es.
Alg
o
r
ith
m
1
.
Fin
an
cial
s
tr
ess
d
etec
tio
n
1.
last
7
←
m
ea
n
r
ev
en
u
e
o
v
e
r
th
e
last
7
d
ay
s
2.
last
9
0
←
m
ea
n
r
ev
e
n
u
e
o
v
er
t
h
e
last
9
0
d
ay
s
3.
if
last
7
an
d
last
9
0
ar
e
b
o
th
d
ef
in
ed
th
en
4.
if
last
7
<0
.
7
×
last
9
0
th
e
n
5.
s
tr
ess
f
lag
←
tr
u
e
6.
else
7.
s
tr
ess
f
lag
←
f
alse
8.
en
d
if
9.
else
10.
s
tr
ess
f
lag
←
NaN
11.
en
d
if
4.
RE
SUL
T
S
AND
DIS
CUS
SI
O
N
T
h
is
s
ec
tio
n
d
is
cu
s
s
es
o
u
tco
m
es
b
ased
o
n
th
e
m
o
d
el
an
d
co
d
e
o
u
tp
u
t.
I
t
in
clu
d
es
a
ca
s
e
s
t
u
d
y
o
n
th
e
m
er
ch
an
t “
Fah
ed
s
u
p
er
v
alu
e
”
.
Ad
d
itio
n
ally
,
it
p
r
o
v
i
d
es a
n
e
x
p
lan
atio
n
o
f
th
e
d
ash
b
o
a
r
d
.
4
.
1
.
O
v
er
a
ll
m
er
cha
nt
la
nd
s
ca
pe
T
o
g
ain
an
o
v
er
v
iew
o
f
m
er
ch
an
t
p
er
f
o
r
m
a
n
ce
an
d
r
is
k
,
all
m
er
ch
an
ts
wer
e
f
ir
s
t
v
is
u
alize
d
co
llectiv
ely
.
Fig
u
r
e
2
d
em
o
n
s
tr
ates
th
e
m
er
c
h
an
t
r
is
k
lan
d
s
ca
p
e,
wh
er
e
ea
ch
m
er
c
h
an
t
is
r
ep
r
esen
ted
b
y
a
b
u
b
b
le,
p
o
s
itio
n
ed
ac
co
r
d
in
g
to
r
ev
en
u
e
v
o
latilit
y
o
n
th
e
x
-
ax
is
(
co
ef
f
icien
t
o
f
v
ar
iatio
n
)
an
d
tr
a
n
s
ac
tio
n
d
ec
lin
e
r
ate
o
n
th
e
y
-
a
x
is
(
r
atio
o
f
d
ec
lin
ed
t
o
to
tal
tr
a
n
s
ac
tio
n
s
)
,
with
b
u
b
b
le
s
ize
p
r
o
p
o
r
ti
o
n
al
to
to
tal
h
is
to
r
ical
r
ev
en
u
e
in
USD.
T
h
e
r
esu
lts
s
h
o
wed
th
at
m
o
s
t
m
er
ch
an
ts
ar
e
co
n
ce
n
tr
ated
i
n
th
e
lo
w
-
v
o
latilit
y
(
u
n
d
er
1
.
0
)
a
n
d
lo
w
-
d
ec
lin
e
(
u
n
d
er
5
%)
r
e
g
io
n
,
r
e
f
lectin
g
s
tab
le
o
p
er
atin
g
p
e
r
f
o
r
m
an
ce
.
I
n
co
n
tr
ast,
a
s
m
all
g
r
o
u
p
o
f
o
u
tlier
s
ex
h
ib
ited
b
o
th
h
ig
h
v
o
latilit
y
an
d
h
ig
h
d
ec
lin
e
r
ates,
in
d
icatin
g
m
er
ch
an
ts
with
m
o
r
e
u
n
p
r
e
d
ictab
le
r
ev
e
n
u
e
p
atter
n
s
an
d
in
cr
ea
s
ed
f
in
an
cial
r
is
k
.
As
f
o
r
th
e
clu
s
ter
in
g
,
th
is
s
tu
d
y
s
eg
m
en
ted
th
e
m
e
r
ch
an
ts
i
n
to
two
g
r
o
u
p
s
b
ased
o
n
to
ta
l
r
ev
en
u
e,
tr
an
s
ac
tio
n
co
u
n
t,
an
d
u
n
iq
u
e
cu
s
to
m
er
co
u
n
t.
Fig
u
r
e
3
s
h
o
ws
th
e
d
is
tr
ib
u
tio
n
o
f
m
er
ch
an
t
r
ev
en
u
es
ac
r
o
s
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
A
merch
a
n
t a
n
a
lytics fr
a
mewo
r
k
fo
r
r
ev
en
u
e
fo
r
ec
a
s
tin
g
a
n
d
fin
a
n
cia
l str
ess
d
etec
tio
n
u
s
in
g
…
(
Ya
r
a
Ha
r
b
)
4853
clu
s
ter
s
o
b
tain
ed
u
s
in
g
k
-
m
ea
n
s
,
wh
er
e
lo
g
s
ca
le
was
u
s
ed
to
h
ig
h
lig
h
t
th
e
m
ag
n
itu
d
e
d
if
f
er
en
ce
s
b
etwe
en
th
ese
clu
s
ter
s
,
d
em
o
n
s
tr
atin
g
h
o
w
s
eg
m
en
tatio
n
s
ep
ar
ates
lo
w
-
an
d
h
ig
h
-
p
er
f
o
r
m
i
n
g
g
r
o
u
p
s
.
Fig
u
r
e
3
r
ev
ea
ls
th
at
clu
s
ter
1
(
≈
1
0
cu
s
to
m
er
s
)
co
n
tain
s
lo
wer
r
ev
en
u
e
m
er
ch
an
ts
with
a
wid
e
s
p
r
ea
d
o
f
o
u
tlier
s
,
wh
er
ea
s
clu
s
ter
2
(
≈
9
7
cu
s
to
m
er
s
)
ca
p
t
u
r
es th
e
to
p
-
p
er
f
o
r
m
in
g
m
er
ch
an
ts
with
u
n
if
o
r
m
l
y
h
ig
h
h
is
to
r
ical
r
ev
en
u
e
.
Fig
u
r
e
2
.
Me
r
c
h
an
t r
is
k
lan
d
s
ca
p
e
b
ased
o
n
v
o
latilit
y
an
d
d
e
clin
e
r
ate
Fig
u
r
e
3
.
R
ev
en
u
e
d
is
tr
ib
u
tio
n
p
er
cu
s
to
m
er
clu
s
ter
(
lo
g
s
ca
le)
ac
r
o
s
s
lo
w
-
an
d
h
ig
h
-
in
co
m
e
g
r
o
u
p
s
4
.
2
.
I
nte
ra
ct
i
v
e
m
er
cha
nt
e
x
plo
re
r
An
in
ter
ac
tiv
e
wid
g
et
was
b
u
ilt,
wh
ich
allo
ws
th
e
u
s
er
to
s
elec
t
a
ca
r
d
b
in
an
d
d
is
p
lay
th
e
to
p
-
N
m
er
ch
an
ts
f
r
o
m
it
illu
s
tr
ated
in
Fig
u
r
e
4
.
User
s
ca
n
u
s
e
th
is
in
ter
ac
tiv
e
d
ash
b
o
a
r
d
t
o
s
elec
t
a
ca
r
d
b
in
(
e.
g
.
,
4
0
0
3
9
0
)
a
n
d
d
is
p
lay
th
e
to
p
-
N
m
er
ch
a
n
ts
ass
o
ciate
d
with
it.
Fo
r
ex
am
p
le,
u
p
o
n
s
elec
tin
g
ca
r
d
b
in
4
0
0
3
9
0
an
d
to
p
5
,
th
e
d
r
o
p
d
o
wn
lis
ts
th
e
5
h
ig
h
est
-
v
o
l
u
m
e
m
er
ch
an
ts
ass
o
ciate
d
with
th
at
ca
r
d
b
in
.
T
h
is
f
u
n
ctio
n
ality
en
ab
les
tar
g
eted
ex
p
lo
r
atio
n
o
f
p
o
r
tf
o
lio
c
o
m
p
o
s
itio
n
an
d
f
ac
ilit
ates
d
ee
p
e
r
u
n
d
er
s
tan
d
in
g
o
f
m
er
ch
an
t p
e
r
f
o
r
m
an
ce
.
Fig
u
r
e
4
.
I
n
ter
ac
tiv
e
m
e
r
ch
an
t
ex
p
lo
r
e
r
in
ter
f
ac
e
b
ased
o
n
ca
r
d
b
in
a
n
d
to
p
-
n
m
er
ch
a
n
ts
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.
1
4
,
No
.
6
,
Dec
em
b
er
2
0
2
5
:
4
8
4
8
-
4
8
6
4
4854
4
.
3
.
Ca
s
e
s
t
ud
y
:
F
a
hed
s
up
er
v
a
lue
T
h
e
f
u
l
l
p
i
p
e
l
in
e
w
a
s
s
h
o
wn
u
s
i
n
g
t
h
e
m
er
ch
a
n
t
“
F
ah
e
d
s
u
p
e
r
v
a
l
u
e
”
(
o
n
e
o
f
th
e
to
p
5
f
o
r
ca
r
d
b
i
n
4
0
0
3
9
0
)
.
F
i
g
u
r
e
5
p
r
e
s
en
t
s
t
h
e
3
0
-
d
a
y
P
r
o
p
h
e
t
f
o
r
ec
a
s
t
f
o
r
F
a
h
e
d
S
u
p
e
r
V
al
u
e.
T
h
e
m
o
d
e
l
ca
p
tu
r
e
s
b
o
t
h
w
e
e
k
ly
f
l
u
c
tu
a
t
i
o
n
s
a
n
d
a
g
en
e
r
a
l
i
n
cr
e
a
s
i
n
g
r
ev
en
u
e
t
r
e
n
d
,
s
h
o
w
in
g
i
t
s
ab
i
l
i
t
y
to
d
e
te
c
t
s
h
o
r
t
-
te
r
m
c
y
c
l
e
s
a
l
o
n
g
s
i
d
e
lo
n
g
e
r
-
t
e
r
m
g
r
o
w
th
d
y
n
am
i
c
s
.
F
i
g
u
r
e
s
6
to
8
p
r
e
s
e
n
t
t
h
e
d
e
c
o
m
p
o
s
i
t
i
o
n
o
f
t
h
e
t
im
e
s
e
r
i
e
s
f
o
r
F
ah
e
d
s
u
p
er
v
a
lu
e
u
s
in
g
P
r
o
p
h
e
t
.
T
h
e
p
r
o
p
o
s
ed
s
t
u
d
y
m
a
i
n
ly
e
v
a
lu
a
t
e
s
t
h
e
w
e
e
k
ly
t
r
e
n
d
c
o
m
p
o
n
en
t
i
n
F
i
g
u
r
e
6
an
d
t
h
e
m
o
n
th
l
y
an
d
y
e
ar
l
y
s
e
a
s
o
n
a
l
i
t
y
i
n
F
i
g
u
r
e
s
7
a
n
d
8
,
r
e
s
p
e
c
t
i
v
e
ly
.
F
i
g
u
r
e
6
s
h
o
w
s
th
e
w
e
e
k
l
y
s
e
a
s
o
n
a
l
i
ty
,
c
a
p
tu
r
in
g
th
e
t
y
p
i
c
a
l
f
lu
c
t
u
a
t
io
n
s
i
n
r
e
v
en
u
e
b
a
s
e
d
o
n
t
h
e
d
a
y
o
f
t
h
e
we
e
k
.
T
h
e
p
lo
t
i
n
d
i
c
a
te
s
th
a
t
th
e
r
ev
en
u
e
i
s
g
e
n
e
r
a
l
ly
l
o
w
er
o
n
S
u
n
d
a
y
s
a
n
d
T
u
e
s
d
a
y
s
,
w
h
i
l
e
S
a
tu
r
d
a
y
s
e
x
h
ib
i
t
th
e
h
ig
h
e
s
t
p
o
s
i
t
i
v
e
v
ar
i
a
t
i
o
n
f
r
o
m
t
h
e
av
e
r
ag
e
,
p
o
te
n
t
i
a
l
ly
in
d
i
c
a
t
in
g
p
e
ak
s
h
o
p
p
in
g
a
c
t
i
v
it
y
o
n
w
e
e
k
e
n
d
s
.
F
ig
u
r
e
7
d
i
s
p
l
a
y
s
th
e
t
r
en
d
co
m
p
o
n
e
n
t,
w
h
i
c
h
r
e
f
l
ec
t
s
t
h
e
o
v
e
r
a
l
l
lo
n
g
-
t
er
m
g
r
o
w
th
i
n
r
e
v
en
u
e.
A
s
s
e
e
n
,
t
h
er
e
i
s
a
s
t
e
a
d
y
u
p
w
a
r
d
t
r
a
j
e
c
t
o
r
y
f
r
o
m
J
an
u
ar
y
t
o
N
o
v
e
m
b
e
r
2
0
2
4
,
s
u
g
g
e
s
t
i
n
g
a
c
o
n
s
i
s
t
e
n
t
i
n
cr
e
a
s
e
in
d
a
i
l
y
r
e
v
en
u
e
o
v
er
t
im
e
.
F
i
g
u
r
e
8
s
h
o
w
s
th
e
y
e
ar
l
y
s
e
a
s
o
n
a
l
i
ty
,
w
h
i
c
h
r
ev
e
a
l
s
r
ep
e
a
t
in
g
p
a
t
ter
n
s
th
r
o
u
g
h
o
u
t
t
h
e
y
e
a
r
.
R
e
v
en
u
e
ap
p
e
a
r
s
t
o
i
n
c
r
e
a
s
e
a
t
th
e
b
eg
in
n
in
g
an
d
e
n
d
o
f
th
e
y
e
a
r
,
a
n
d
e
x
p
e
r
ien
c
e
s
n
o
t
a
b
l
e
d
r
o
p
s
a
r
o
u
n
d
M
ar
c
h
a
n
d
e
ar
l
y
s
u
m
m
e
r
.
T
h
e
s
e
s
e
a
s
o
n
a
l
p
a
t
t
er
n
s
m
a
y
a
l
i
g
n
w
i
t
h
l
o
ca
l
e
co
n
o
m
i
c
o
r
c
u
l
tu
r
a
l
f
a
c
t
o
r
s
i
n
f
l
u
en
c
in
g
c
o
n
s
u
m
er
b
e
h
av
i
o
r
.
Fig
u
r
e
5
.
T
h
ir
ty
-
d
ay
P
r
o
p
h
et
r
ev
en
u
e
f
o
r
ec
ast f
o
r
Fah
ed
s
u
p
er
v
alu
e
Fig
u
r
e
6
.
W
ee
k
ly
in
c
o
m
e
s
ea
s
o
n
ality
f
o
r
Fah
ed
s
u
p
e
r
v
alu
e
Fig
u
r
e
7
.
Mo
n
th
ly
in
c
o
m
e
s
ea
s
o
n
ality
f
o
r
Fah
e
d
s
u
p
er
v
alu
e
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
A
merch
a
n
t a
n
a
lytics fr
a
mewo
r
k
fo
r
r
ev
en
u
e
fo
r
ec
a
s
tin
g
a
n
d
fin
a
n
cia
l str
ess
d
etec
tio
n
u
s
in
g
…
(
Ya
r
a
Ha
r
b
)
4855
Fig
u
r
e
8
.
Yea
r
ly
in
co
m
e
s
ea
s
o
n
ality
f
o
r
Fah
e
d
s
u
p
er
v
alu
e
Fig
u
r
e
9
p
r
o
v
id
es
a
h
ea
tm
ap
v
is
u
aliza
tio
n
o
f
Fah
ed
s
u
p
er
v
alu
e’
s
tr
an
s
ac
tio
n
v
o
lu
m
e,
co
m
p
o
s
ed
o
f
d
ay
o
f
th
e
wee
k
(
r
o
ws)
an
d
m
o
n
th
o
f
th
e
y
ea
r
(
c
o
lu
m
n
s
)
.
E
ac
h
ce
ll
in
d
icate
s
th
e
to
tal
n
u
m
b
er
o
f
tr
a
n
s
ac
tio
n
s
o
n
a
s
p
ec
if
ic
d
ay
an
d
m
o
n
t
h
co
m
b
in
atio
n
,
with
d
a
r
k
er
s
h
ad
es
r
ep
r
esen
tin
g
h
ig
h
er
tr
an
s
ac
tio
n
v
o
l
u
m
es.
T
h
is
v
is
u
aliza
tio
n
r
ev
ea
ls
clea
r
s
ea
s
o
n
ality
p
atter
n
s
,
s
u
ch
as
h
eig
h
ten
e
d
ac
tiv
ity
o
n
Satu
r
d
ay
s
an
d
Mo
n
d
ay
s
,
esp
ec
ially
in
Ma
y
,
J
u
n
e,
an
d
J
u
ly
.
T
h
e
d
a
r
k
est
ce
lls
,
s
u
ch
as
Satu
r
d
ay
in
J
u
n
e
(
3
1
2
tr
an
s
ac
tio
n
s
)
an
d
T
u
esd
ay
in
J
u
ly
(
2
8
6
tr
an
s
ac
tio
n
s
)
,
h
ig
h
lig
h
t
p
ea
k
s
h
o
p
p
in
g
p
er
io
d
s
wh
ich
c
o
u
ld
r
elate
to
s
ea
s
o
n
al
d
em
an
d
o
r
p
r
o
m
o
tio
n
al
ca
m
p
aig
n
s
.
On
th
e
o
th
er
h
an
d
,
lo
wer
v
alu
es
,
s
u
ch
as
Mo
n
d
ay
s
an
d
T
u
e
s
d
ay
s
in
Feb
r
u
ar
y
(
8
4
an
d
1
0
0
tr
an
s
ac
tio
n
s
)
,
m
ay
r
ef
lect
o
f
f
-
p
ea
k
r
etail
ac
tiv
ity
.
T
h
is
h
ea
tm
ap
h
elp
s
id
en
tify
h
ig
h
-
tr
af
f
ic
p
er
io
d
s
,
en
a
b
lin
g
b
etter
s
taf
f
in
g
,
in
v
e
n
to
r
y
p
lan
n
in
g
,
an
d
p
r
o
m
o
tio
n
al
tar
g
etin
g
.
Fig
u
r
e
9
.
Hea
tm
ap
o
f
d
aily
tr
a
n
s
ac
tio
n
v
o
lu
m
e
b
y
d
ay
o
f
we
ek
an
d
m
o
n
th
f
o
r
Fah
ed
Su
p
e
r
Valu
e
4
.
4
.
E
x
ec
utiv
e
s
um
m
a
ry
:
F
a
hed
s
u
per
v
a
lue
Fin
ally
,
th
e
d
ec
is
io
n
-
m
a
k
in
g
s
u
m
m
ar
y
s
y
n
th
esizes
all
k
ey
m
etr
ics
f
o
r
Fah
e
d
s
u
p
er
v
alu
e
:
Fah
ed
s
u
p
er
v
alu
e
r
ec
o
r
d
e
d
$
2
3
9
,
7
4
8
.
8
3
in
to
tal
r
ev
e
n
u
e
a
n
d
$
1
,
0
9
6
.
0
6
in
a
v
er
ag
e
d
aily
r
ev
en
u
e
o
v
e
r
2
1
9
b
u
s
in
ess
d
ay
s
,
p
r
o
ce
s
s
in
g
1
2
,
6
7
9
tr
an
s
ac
tio
n
s
f
r
o
m
1
1
4
u
n
iq
u
e
cu
s
to
m
er
s
.
I
t
was
ass
ig
n
ed
to
clu
s
ter
2
(
≈
9
7
c
u
s
to
m
er
s
)
.
T
h
e
3
0
-
d
a
y
r
ev
en
u
e
f
o
r
ec
ast
was
$
3
7
,
5
5
1
(
9
5
%
C
I
:
$
1
5
,
7
2
1
–
$
5
6
,
2
2
9
)
,
with
a
m
ea
n
ab
s
o
lu
te
p
er
ce
n
tag
e
er
r
o
r
(
M
APE
)
o
f
5
6
.
5
1
%,
in
d
icatin
g
m
o
d
er
ate
p
r
ed
ictiv
e
ac
c
u
r
ac
y
.
T
h
e
s
tr
ess
f
lag
was
n
o
,
s
u
g
g
esti
n
g
t
h
at
r
ec
en
t
s
h
o
r
t
-
ter
m
p
er
f
o
r
m
a
n
ce
r
em
ain
s
with
in
7
0
%
o
f
th
e
9
0
-
d
a
y
b
as
elin
e.
C
o
llectiv
ely
,
th
ese
f
ig
u
r
es
a
n
d
t
h
e
ac
co
m
p
a
n
y
in
g
n
ar
r
ativ
e
d
em
o
n
s
tr
ate
t
h
e
u
tili
ty
o
f
o
u
r
en
d
-
to
-
en
d
p
i
p
elin
e
f
o
r
m
e
r
ch
an
t
s
eg
m
en
tatio
n
,
f
o
r
ec
asti
n
g
,
an
d
r
is
k
ass
ess
m
en
t.
5.
D
A
S
H
B
O
AR
D
F
O
R
R
E
S
UL
T
S
V
I
S
U
AL
I
Z
AT
I
O
N
T
h
is
s
ec
tio
n
p
r
esen
ts
th
e
k
ey
co
m
p
o
n
en
ts
o
f
th
e
m
er
c
h
a
n
t
an
aly
tics
d
ash
b
o
ar
d
.
I
t
in
clu
d
es
th
e
p
o
r
tf
o
lio
o
v
e
r
v
iew,
r
is
k
ass
ess
m
en
t,
an
d
clu
s
ter
in
g
.
Ad
d
i
tio
n
ally
,
it
co
v
er
s
th
e
to
p
m
er
ch
an
ts
'
s
u
m
m
ar
y
,
tr
en
d
s
,
an
d
f
o
r
ec
ast.
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.
1
4
,
No
.
6
,
Dec
em
b
er
2
0
2
5
:
4
8
4
8
-
4
8
6
4
4856
5
.
1
.
P
o
rt
f
o
lio
o
v
er
v
iew
da
s
hb
o
a
rd
Fig
u
r
e
1
0
s
u
m
m
ar
izes
h
ig
h
-
lev
el
k
ey
p
er
f
o
r
m
an
ce
in
d
icato
r
s
(
KPI
s
)
ac
r
o
s
s
all
m
er
ch
an
ts
.
Me
r
ch
an
ts
wh
o
s
e
7
-
d
ay
a
v
er
ag
e
r
ev
en
u
e
f
alls
u
n
d
er
7
0
%
o
f
th
eir
9
0
-
d
ay
b
aselin
e
ar
e
f
lag
g
ed
as
s
tr
ess
ed
.
A
s
p
ik
e
in
s
tr
ess
ed
m
er
ch
an
ts
m
ay
in
d
icate
elev
ated
o
p
er
atio
n
al
r
is
k
o
r
p
o
te
n
tial
an
o
m
alo
u
s
b
e
h
av
io
r
(
e.
g
.
,
f
r
a
u
d
)
war
r
a
n
tin
g
f
u
r
th
er
in
v
esti
g
atio
n
.
T
h
e
lef
t
-
h
a
n
d
p
an
el
o
f
f
e
r
s
in
ter
ac
tiv
e
f
ilter
s
f
o
r
d
ate
r
an
g
e,
cu
s
to
m
er
clu
s
ter
,
m
i
n
im
u
m
tr
an
s
ac
tio
n
d
a
y
s
,
an
d
m
in
im
u
m
to
tal
r
ev
e
n
u
e.
T
h
e
h
ea
d
er
d
is
p
lay
s
f
o
u
r
k
e
y
m
etr
ics:
to
tal
h
is
to
r
ical
r
ev
en
u
e
(
USD)
,
u
n
iq
u
e
c
u
s
to
m
er
co
u
n
t,
ac
tiv
ity
r
ate
(
p
er
ce
n
ta
g
e
o
f
d
ay
s
with
at
least
o
n
e
tr
a
n
s
ac
tio
n
)
,
an
d
an
o
v
er
a
ll
r
is
k
s
co
r
e.
T
h
e
f
o
llo
win
g
t
wo
ch
ar
ts
s
h
o
w
th
e
d
aily
r
ev
e
n
u
e
tim
e
s
er
ies
an
d
th
e
d
ay
-
of
-
wee
k
t
r
an
s
ac
tio
n
v
o
lu
m
e
p
atter
n
to
r
e
v
ea
l tr
en
d
s
an
d
s
ea
s
o
n
al
ef
f
ec
ts
.
Fig
u
r
e
10.
Po
r
tf
o
lio
o
v
er
v
iew
d
ash
b
o
ar
d
p
r
esen
tin
g
g
en
e
r
al
d
etails
o
f
m
er
ch
an
ts
5
.
2
.
Ris
k
a
s
s
ess
m
ent
a
nd
clu
s
t
er
ing
da
s
hb
o
a
rd
Fig
u
r
e
1
1
c
o
m
b
in
es
two
p
o
r
tf
o
lio
-
lev
el
r
is
k
p
e
r
s
p
ec
tiv
es.
T
h
e
lef
t
p
a
n
el
s
h
o
ws
a
b
u
b
b
le
ch
ar
t
m
ap
p
in
g
v
o
latilit
y
ag
ai
n
s
t
d
ec
lin
e
r
ate,
wh
er
e
b
u
b
b
le
s
ize
r
e
p
r
esen
ts
r
ev
en
u
e
an
d
co
lo
r
en
co
d
es
a
co
m
p
o
s
ite
r
is
k
s
co
r
e.
T
h
e
r
ig
h
t
p
a
n
el
illu
s
tr
ates
th
e
d
is
tr
ib
u
tio
n
o
f
m
er
c
h
an
ts
b
y
cu
s
to
m
er
clu
s
ter
.
T
o
g
eth
er
,
th
ese
v
iews
lin
k
r
is
k
ex
p
o
s
u
r
e
to
m
er
ch
an
t
s
eg
m
en
tatio
n
.
Fig
u
r
e
1
1
.
Po
r
tf
o
lio
r
is
k
ass
es
s
m
en
t a
n
d
clu
s
ter
in
g
illu
s
tr
ati
n
g
v
o
latilit
y
an
d
d
ec
lin
e
r
elatio
n
s
h
ip
,
an
d
m
er
ch
an
t d
is
tr
ib
u
tio
n
b
y
cu
s
to
m
er
clu
s
ter
5
.
3
.
T
o
p
m
er
cha
nt
’
s
s
um
m
a
ry
da
s
hb
o
a
rd
Fig
u
r
e
1
2
p
r
esen
ts
lead
er
b
o
ar
d
s
f
o
r
two
cr
itical
m
etr
ics:
h
is
to
r
ical
r
ev
en
u
e
a
n
d
s
tr
ess
s
co
r
e.
T
h
e
lef
t
p
an
el
s
h
o
ws
t
h
e
to
p
5
m
e
r
ch
a
n
ts
b
y
r
ev
e
n
u
e,
o
f
f
er
in
g
a
cle
ar
s
n
ap
s
h
o
t
o
f
wh
ich
m
er
c
h
a
n
ts
co
n
tr
ib
u
te
m
o
s
t
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
A
merch
a
n
t a
n
a
lytics fr
a
mewo
r
k
fo
r
r
ev
en
u
e
fo
r
ec
a
s
tin
g
a
n
d
fin
a
n
cia
l str
ess
d
etec
tio
n
u
s
in
g
…
(
Ya
r
a
Ha
r
b
)
4857
s
ig
n
if
ican
tly
to
o
v
e
r
all
p
o
r
tf
o
l
io
p
er
f
o
r
m
a
n
ce
.
T
h
ese
h
i
g
h
-
v
alu
e
clien
ts
ar
e
im
p
o
r
tan
t
t
o
m
ain
tain
g
r
o
wth
an
d
s
h
o
u
ld
b
e
p
r
io
r
itized
f
o
r
r
et
en
tio
n
s
tr
ateg
ies
an
d
tailo
r
e
d
s
er
v
ices.
T
h
e
r
ig
h
t
p
an
el
r
an
k
s
th
e
to
p
f
iv
e
m
er
ch
an
ts
b
y
s
tr
ess
s
co
r
e,
a
c
o
m
p
o
s
ite
in
d
icato
r
t
h
at
r
e
f
lects
elev
ated
r
is
k
lev
els
d
u
e
t
o
v
o
latile
tr
an
s
ac
tio
n
b
eh
av
io
r
,
h
ig
h
d
ec
lin
e
r
ates,
o
r
r
ev
en
u
e
d
r
o
p
s
.
T
h
ese
m
er
ch
an
ts
m
ay
r
eq
u
ir
e
im
m
e
d
iate
atten
tio
n
,
f
u
r
th
er
in
v
esti
g
atio
n
,
o
r
in
ter
v
e
n
tio
n
to
m
itig
ate
a
p
o
s
s
ib
le
f
in
an
cial
r
is
k
.
B
y
co
m
p
ar
i
n
g
h
i
g
h
-
r
ev
en
u
e
m
er
c
h
an
ts
with
h
ig
h
-
s
tr
ess
o
n
es,
th
is
s
u
m
m
ar
y
h
elp
s
s
tak
eh
o
l
d
er
s
d
if
f
er
en
tiate
b
etwe
en
m
er
ch
a
n
ts
th
at
ar
e
v
alu
ab
le
an
d
s
tab
le
v
er
s
u
s
th
e
o
n
es
wh
o
ar
e
p
o
ten
tially
u
n
s
af
e
d
esp
it
e
h
ig
h
tr
a
n
s
ac
tio
n
v
o
lu
m
es.
T
h
is
d
is
tin
ctio
n
is
ess
en
tial
f
o
r
d
esig
n
in
g
b
alan
c
ed
s
tr
ateg
ies
th
at
n
o
t
o
n
ly
m
a
x
im
ize
r
ev
en
u
e
,
b
u
t
also
co
n
t
r
o
l
r
is
k
,
m
ak
in
g
th
e
tab
le
a
r
eq
u
ir
ed
t
o
o
l
f
o
r
p
o
r
tf
o
lio
m
an
ag
e
r
s
an
d
an
al
y
s
ts
.
Fig
u
r
e
1
2
.
T
o
p
-
m
er
ch
a
n
t le
ad
er
b
o
ar
d
s
b
y
h
is
to
r
ical
r
e
v
en
u
e
an
d
s
tr
ess
s
co
r
e
5
.
4
.
M
er
cha
nt
det
a
iled a
na
l
y
s
is
da
s
h
bo
a
rd
Fig
u
r
e
1
3
s
h
o
ws
th
e
o
p
tio
n
to
b
e
ab
le
to
s
elec
t
an
y
m
er
c
h
a
n
t
f
o
r
a
d
etailed
an
aly
s
is
.
T
h
e
lef
t
-
h
an
d
p
an
el
o
f
f
er
s
f
ilter
s
f
o
r
d
ate
r
an
g
e,
cu
s
to
m
er
clu
s
ter
,
m
in
im
u
m
tr
an
s
ac
tio
n
d
ay
s
,
an
d
m
in
im
u
m
r
ev
e
n
u
e.
T
h
e
h
ea
d
er
s
h
o
ws
to
tal
r
ev
en
u
e,
u
n
iq
u
e
cu
s
to
m
er
co
u
n
t,
ac
tiv
ity
r
ate,
an
d
r
is
k
s
co
r
e.
T
h
e
2
ch
ar
ts
p
r
esen
t
th
e
d
aily
r
ev
en
u
e
tim
e
s
er
ies an
d
t
h
e
d
ay
-
of
-
wee
k
tr
an
s
ac
tio
n
v
o
lu
m
e
p
atter
n
f
o
r
th
e
ch
o
s
en
m
er
ch
an
t.
Fig
u
r
e
1
3
.
Me
r
ch
an
t i
n
ter
f
ac
e
s
u
m
m
ar
izin
g
k
e
y
m
etr
ics s
u
ch
as d
aily
r
ev
en
u
e,
ac
tiv
ity
,
a
n
d
r
is
k
s
co
r
e
5
.
5
.
T
re
nd
s
a
nd
f
o
re
ca
s
t
da
s
hb
o
a
rd
Fig
u
r
e
1
4
s
h
o
ws
th
e
tr
en
d
s
an
d
f
o
r
ec
ast
p
an
el.
T
h
e
lef
t
ch
ar
t
o
v
er
lay
s
r
aw
d
aily
r
ev
en
u
e
with
7
-
an
d
30
-
d
a
y
r
o
llin
g
av
e
r
ag
es,
m
itig
atin
g
s
h
o
r
t
-
ter
m
v
o
latilit
y
an
d
clar
if
y
in
g
tr
en
d
d
y
n
a
m
ics.
T
h
e
r
ig
h
t
ch
ar
t
s
h
o
ws
th
e
3
0
-
d
ay
Pro
p
h
et
f
o
r
ec
ast
w
ith
ac
cu
r
ac
y
m
et
r
ics
(
MA
PE,
r
o
o
t
m
ea
n
s
q
u
ar
e
er
r
o
r
(
R
MSE
)
)
a
n
d
s
tr
ess
-
f
lag
s
tatu
s
,
in
teg
r
atin
g
h
is
to
r
ical
co
n
tex
t w
ith
p
r
ed
ictiv
e
o
u
tp
u
ts
.
Evaluation Warning : The document was created with Spire.PDF for Python.