Spectrum of Decision Making and Applications.,
Journal Year:
2024,
Volume and Issue:
2(1), P. 157 - 164
Published: Nov. 23, 2024
Vendor
Managed
Inventory
(VMI)
is
a
widely
adopted
strategy
in
supply
chain
management,
where
the
vendor
assumes
responsibility
for
maintaining
inventory
levels
at
customer’s
location.
This
paper
presents
model
to
solve
VMI
problem,
focusing
on
optimizing
replenishment
and
reducing
overall
costs.
The
study
employs
heuristic
approach,
breaking
down
problem
into
manageable
phases,
including
clustering
customers,
determining
service
sequence
lists,
delivery
routes.
applied
practical
case
study,
demonstrating
its
effectiveness
minimizing
stockouts
while
efficient
levels.
also
examines
key
factors
like
quantity
optimization,
route
scheduling,
cost
minimization.
model's
demonstrated
by
specific
performance
criteria,
such
as
reduced
stockouts,
improved
levels,
minimized
transportation
findings
indicate
that
suggested
can
significantly
enhance
efficiency,
providing
organizations
with
solid
framework
enhancing
their
procedures.
These
enhancements
are
accomplished
preserving
simplicity
usefulness
without
need
overly
complex
technological
systems.
Frontiers in Pharmacology,
Journal Year:
2024,
Volume and Issue:
15
Published: July 16, 2024
Objectives
To
employ
a
drug
supply
chain
information
system
to
optimize
management
practices,
reducing
costs
and
improving
efficiency
in
financial
asset
management.
Methods
A
digital
artificial
intelligence
+
vendor
managed
inventory
(AI+VMI)-based
for
hospitals
has
been
established.
The
enables
digitalization
intelligentization
of
purchasing
plans,
reconciliations,
consumption
settlements
while
generating
purchase,
sales,
reports
as
well
various
query
reports.
indicators
evaluating
the
effectiveness
before
after
project
implementation
encompass
loss
reporting,
discrepancies,
inter-hospital
medication
retrieval
frequency,
expenditure,
cloud
pharmacy
service
utilization.
Results
successful
this
reduced
hospital
rate
approximately
20%
decreased
average
annual
error
from
0.425‰
0.025‰,
significantly
boosting
by
42.4%.
It
also
minimized
errors
application,
allocation,
distribution
increasing
adverse
reaction
Drug
across
multiple
districts
standardized,
leading
improved
access
medicines
enhanced
patient
satisfaction.
Conclusion
AI+VMI
improves
ensuring
security,
costs,
enhancing
safety
management,
elevating
professional
competence
level
pharmaceutical
personnel.
Processes,
Journal Year:
2025,
Volume and Issue:
13(2), P. 594 - 594
Published: Feb. 19, 2025
Accurate
demand
forecasting
is
crucial
for
modern
supply
chain
management,
forming
the
foundation
inventory
optimization,
cost
control,
and
service
level
improvement.
However,
time
series
data
often
exhibit
high
volatility
diverse
patterns,
further
complicated
by
rapid
expansion
heterogeneity
of
sources.
These
challenges
can
result
in
significant
degradation
predictive
accuracy
when
traditional
models
are
applied
to
complex
datasets.
To
address
these
challenges,
this
study
proposes
an
end-to-end
framework
leveraging
Variational
Mode
Decomposition
(VMD)
attention
mechanisms.
The
first
employs
VMD
decompose
raw
into
multiple
modes
extract
hierarchical
features,
including
trends,
seasonal
short-term
variations.
Subsequently,
mechanism
introduced
dynamically
capture
integrate
sequences
alongside
contextual
information,
enhancing
focus
on
critical
features
improving
performance.
Experimental
results
demonstrate
that
proposed
method
achieves
superior
compared
conventional
approaches,
with
a
37%
reduction
Mean
Absolute
Error
(MAE)
relative
baseline
models.
This
substantial
improvement
provides
actionable
insights
decision-makers,
enabling
more
efficient
production
planning,
overall
optimization.
