Personalized product recommendation system for e-commerce platforms
Shaik Sameena,
Guntupalli Javali,
Nelavelli Srilakshmi
и другие.
ITM Web of Conferences,
Год журнала:
2025,
Номер
74, С. 03012 - 03012
Опубликована: Янв. 1, 2025
Due
to
rapid
growth
in
e-commerce,
the
interest
for
customized
product
recommendation
systems
has
grown
a
lot
with
high
demands
effective
models.
The
attempt
is
made
explore
development
and
evaluation
of
personalized
model
using
H&M
data
set.
research
highlights
building
up
an
interaction
matrix
between
user
items,
generation
recommendations
suited
tastes
particular
user,
hyperparameter
tuning
better
performance.
Different
techniques
have
been
utilized,
including
KNNBasic,
Non-negative
Matrix
Factorization
(NMF),
CoClustering,
Singular
Value
Decomposition
(SVD).
KNNBasic
had
root
mean
square
error
(RMSE)
0.5022
accuracy
42.00%,
NMF
showed
results
RMSE
0.4999
51.50%.
Co-Clustering
result
as
0.5000
was
50.50%.
Notably,
final
SVD
ranked
very
well
compared
others
0.2261
great
90.40%
this
experiment,
emphasizing
importance
advanced
systems.
In
these
experiments,
not
only
relative
efficacy
different
algorithms
evident
but
also
that
optimization
hyperparameters
genuinely
contributes
increasing
predictive
precision
Язык: Английский
Predictive model for customer satisfaction analytics in E-commerce sector using machine learning and deep learning
International Journal of Information Management Data Insights,
Год журнала:
2024,
Номер
4(2), С. 100295 - 100295
Опубликована: Окт. 7, 2024
Язык: Английский
Intelligent Prediction of Cross-Border E-Commerce Customer Satisfaction Using Deep Learning Embeddings
IEEE Access,
Год журнала:
2024,
Номер
12, С. 173268 - 173278
Опубликована: Янв. 1, 2024
Язык: Английский
Classification of Grapevine Leaf Types with Vision Transformer Architecture
Cumhuriyet Science Journal,
Год журнала:
2024,
Номер
45(4), С. 701 - 706
Опубликована: Дек. 13, 2024
Viticulture
plays
an
important
role
in
agriculture.
Farmers
prefer
grapevine
cultivation
because
not
only
its
fruit
but
also
leaves
are
used
various
fields.
Both
the
use
and
trade
of
within
country
is
source
income.
Grapevine
leaves,
which
grown
almost
all
countries
as
edible,
vary
terms
species.
Determining
cultivating
species
according
to
their
suitability
productivity
important.
In
this
study,
artificial
intelligence
methods
were
classify
leaf
The
dataset
consisting
five
different
classes,
including
100
images
for
each
class,
totalling
500
images,
was
classified
using
ViT,
VGG19
MobileNet
methods.
When
study
help
increase
production
evaluated,
ViT
method
has
best
accuracy
rate
with
94%.
Язык: Английский