Multi-Modal Data Driven Algorithm for Efficient Trade Market Prediction
Abstract
Financial
market
prediction
is
an
attractive
research
area
for
the
researchers
as
it
helps
participators
to
make
decisions
accordingly.
However,
forecasting
of
financial
not
easy
task
movement
stochastic
in
nature
and
affected
by
several
controllable
uncontrollable
factors.
In
this
research,
S&P
500
index
NASDAQ
predicted
using
five
machine
learning
models
including
support
vector
regression,
random
forest,
linear
k
nearest
neighbour
LSTM.
Three
different
datasets
are
used
daily
closing
price
order
check
sensitivity
towards
Firstly,
historical
data
along
with
macroeconomic
factors
design
a
model.
Second
dataset
sentiment
features
extracted
from
web
news.
Lastly,
hybrid
developed
combining
first
two
datasets.
LSTM
model
outperformed
other
both
markets.
It
also
observed
that
our
most
efficient
one
based
on
gives
minimum
RMSE.
Research Square (Research Square), Год журнала: 2025, Номер unknown
Опубликована: Апрель 24, 2025
Язык: Английский