Journal of Forecasting,
Journal Year:
2025,
Volume and Issue:
unknown
Published: Feb. 22, 2025
ABSTRACT
Compared
to
make‐to‐order
production
based
on
customer
order,
make‐to‐stock
forecast
can
effectively
reduce
inventory
level
and
cost.
However,
due
high
randomness
of
spot
markets
many
uncertainties
in
environments,
it
is
hard
the
products
accurately.
In
this
article,
a
hybrid
model
combining
seasonal
autoregressive
integrated
moving
average
(SARIMA)
least
square
support
vector
machines
(LSSVMs)
proposed
potential
demand
steel
products.
First,
SARIMA
multiobjective
differential
evolution
with
improved
mutation
strategies
developed
extract
linear
components
demand.
Then,
sparse
strategy
designed
useful
data
hence
computation
complexity
without
loss
accuracy.
Next,
LSSVMs
combined
single‐objective
are
adopted
nonlinear
Finally,
experimental
results
real‐world
instance
demonstrate
effectiveness
algorithm.
Procedia Computer Science,
Journal Year:
2022,
Volume and Issue:
200, P. 993 - 1003
Published: Jan. 1, 2022
The
application
of
predictive
analytics
(PA)
in
Supply
Chain
Management
(SCM)
has
received
growing
attention
over
the
last
years,
especially
demand
forecasting.
purpose
this
paper
is
to
provide
an
overview
approaches
retail
SCM
and
compare
quality
two
selected
methods.
data
used
comprises
more
than
37
months
actual
sales
from
Austrian
retailer.
Based
on
data,
SARIMA
LSTM
models
were
trained
evaluated.
Both
produced
reasonable
good
results.
In
general,
performed
better
for
products
with
stable
demand,
while
showed
results
seasonal
behavior.
addition,
we
compared
SARIMAX
by
adding
external
factor
promotions
found
that
significantly
promotions.
To
further
improve
forecasting
store
level,
suggest
hybrid
training
SARIMA(X)
similar,
pre-clustered
groups.
Transportation Research Part E Logistics and Transportation Review,
Journal Year:
2022,
Volume and Issue:
164, P. 102725 - 102725
Published: July 6, 2022
Companies
require
a
greater
understanding
of
the
Supply
Chain
(SC)
benefits
that
can
be
gained
from
industry
4.0
(I4.0)
and,
more
specifically,
which
technologies
and
concepts
improve
certain
SC
performance
measures.
A
state-of-the-art
systematic
literature
review
(SLR)
has
been
done
on
supply
chain
measurement
linked
with
various
technologies.
Based
findings
through
content
analysis,
this
paper
presents
framework
for
exploring
usage
I4.0
to
identify
potential
This
includes
dimensions
Procurement
4.0,
Manufacturing
Logistics
Warehousing
4.0.
As
scientific
contribution,
study
validated
proposed
case
studies,
where
existing
studies
are
limited.
Finally,
several
fruitful
future
possible
extensions
have
discussed
based
framework.
Logistics,
Journal Year:
2021,
Volume and Issue:
5(4), P. 66 - 66
Published: Sept. 27, 2021
The
agri-food
sector
is
an
endless
source
of
expansion
for
nourishing
a
vast
population,
but
there
considerable
need
to
develop
high-standard
procedures
through
intelligent
and
innovative
technologies,
such
as
artificial
intelligence
(AI)
big
data.
This
paper
addresses
the
research
concerning
AI
data
analytics
in
food
industry,
including
machine
learning,
neural
networks
(ANNs),
various
algorithms.
Logistics,
supply
chain,
marketing,
production
patterns
are
covered
along
with
sub-sector
applications
techniques.
It
found
that
utilization
techniques
optimization
algorithm
also
leads
significant
process
management.
Thus,
digital
technologies
boon
where
have
enabled
us
achieve
optimum
results
realtime.
Processes,
Journal Year:
2021,
Volume and Issue:
9(7), P. 1157 - 1157
Published: July 2, 2021
Suppliers
are
adjusting
from
the
order-to-order
manufacturing
production
mode
toward
demand
forecasting.
In
meantime,
customers
have
increased
uncertainty
due
to
their
own
considerations,
such
as
end-product
frustration,
which
leads
suppliers’
inaccurate
forecasting
and
inventory
wastes.
Our
research
applies
ARIMA
LSTM
techniques
establish
rolling
forecast
models,
greatly
improve
accuracy
efficiency
of
The
developed
through
historical
data,
evaluated
verified
by
root
mean
squares
average
absolute
error
percentages
in
actual
case
application,
i.e.,
orders
IC
trays
for
semiconductor
plants.
proposed
superior
manufacturer’s
empirical
model
prediction
results,
with
exhibiting
enhanced
performance
terms
short-term
continued
decline
significantly
after
two
months
implementation
application.
