A cross-institutional database of operational risk external loss events in Chinese banking sector 1986–2023
Scientific Data,
Journal Year:
2024,
Volume and Issue:
11(1)
Published: Aug. 28, 2024
Nowadays
the
collection
of
operational
risk
data
worldwide
highly
relies
on
human
labor,
leading
to
slow
updates,
inconsistency,
and
limited
quantity.
There
remains
a
substantial
shortage
publicly
accessible
databases
for
analysis.
This
study
proposes
new
framework
by
aggregating
text
mining
methods
replace
exhausting
manual
process.
The
news
about
can
be
automatically
collected
from
web
page,
then
its
content
is
analyzed
key
information
extracted.
Finally,
Public-Chinese
Operational
Loss
Data
(P-COLD)
database
financial
institutions
constructed
expanded.
Each
record
contains
12
information,
such
as
occurrence
time,
loss
amount,
business
lines,
offering
more
thorough
description
events.
With
3,723
records
1986
2023,
P-COLD
has
become
one
largest
most
comprehensive
external
in
China.
We
anticipate
will
contribute
advancements
capital
calculations,
dependence
analysis,
institutional
internal
controls.
Language: Английский
Dynamic recommender system for chronic disease-focused online health community
Junruo Gao,
No information about this author
Yuan Zhao,
No information about this author
Dongming Yang
No information about this author
et al.
Expert Systems with Applications,
Journal Year:
2024,
Volume and Issue:
258, P. 125086 - 125086
Published: Aug. 24, 2024
Language: Английский
TriGCN: Graph Convolution Network Based on Tripartite Graph for Personalized Medicine Recommendation System
Huan Zhou,
No information about this author
Sisi Liao,
No information about this author
F. Richard Guo
No information about this author
et al.
Systems,
Journal Year:
2024,
Volume and Issue:
12(10), P. 398 - 398
Published: Sept. 26, 2024
Intelligent
medical
systems
have
great
potential
to
play
an
important
role
in
people’s
daily
lives,
as
they
can
provide
disease
and
medicine
information
immediately
for
both
doctors
patients.
Graph-structured
data
are
attracting
more
attention
the
artificial
intelligence
sector.
Combining
graph-structured
with
a
set,
tripartite
graph
convolutional
network
named
TriGCN
is
proposed.
This
model
able
connect
or
patient,
disease,
nodes,
propagate
from
layer
layer,
update
node
features
at
same
time.
After
this,
calibrated
label
ranking
used
give
personalized
recommendation
lists
The
approach
has
performance,
outperforming
other
machine
learning
methods.
Thus,
this
be
applied
reality
will
contributions
public
health
future.
Language: Английский