Thanks to visit codestin.com
Credit goes to www.scribd.com

0% found this document useful (0 votes)
22 views3 pages

Literature Review

Uploaded by

sabujmmanna123
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
22 views3 pages

Literature Review

Uploaded by

sabujmmanna123
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

Paper Abstract summary Main findings Outcome measured

Deep learning and technical analysis are - The LSTM deep learning technique is 1. Stock market forecasting using deep learning
widely used for stock market forecasting, widely used for stock market forecasting models 2. Predictor techniques (with a focus on
Stock Market Forecasting Using
but profitability and risk management are using technical analysis. - Only 35.3% of LSTM) 3. Trading strategies 4. Profitability metrics
Deep Learning and Technical
often overlooked. studies analyzed profitability, and only 5. Risk management
Analysis: A Systematic Review
two studies implemented risk
A. W. Li +1
management, indicating limitations in
IEEE Access
the existing literature. - There are still
2020 ·
interesting open areas for further
59 citations
research and development in this field.
DOI

Deep learning and sentiment analysis can - Deep learning and sentiment analysis Not mentioned (the abstract does not explicitly state
be used to predict and analyze stock can be used to predict and analyze stock any specific outcome that was measured in this
Stock Market Analysis Using
market behavior. market behavior. - The study used LSTM study)
Deep Learning
models and sentiment analysis on
Aruna Gopinath +2
historical stock data and news events to
IARJSET
predict and analyze the stock market. -
2020 ·
The aim of the study was to understand
1 citation
and implement deep learning and
DOI
sentiment analysis methods for stock
market prediction.

Deep learning models, especially Graph - Graph Neural Networks and The primary outcome measured in this study is the
Neural Networks and Transformers, have Transformer models have potential to accuracy and predictive performance of stock
Deep Learning techniques for
shown potential for more accurate stock accurately interpret dynamic and non- market forecasting using various deep learning
stock market forecasting: Recent
market forecasting compared to linear patterns in financial time series techniques, including Artificial Neural Networks,
trends and challenges
traditional methods. data. - Incorporating correlations Convolutional Neural Networks, Sequence-to-
Manali Patel +2
between stock indices, investor Sequence models, Generative Adversarial
International Conferences on
sentiment, and historical data can Networks, Graph Neural Networks, and
Software Engineering and
improve the accuracy of stock market Transformers.
Information Management
forecasting. - The paper identified
2023 ·
benchmark datasets for stock market
1 citation
forecasting based on market
DOI
capitalization.
A deep learning model using LSTM can - The deep LSTM model developed in The primary outcome measured in this study is the
accurately predict stock market prices. this study achieved the highest accuracy prediction of the next day's stock market close price.
Stock Market Prediction Using a
compared to other related models for
Deep Learning Approach
predicting stock market time series. -
Thitimanan Damrongsakmethee
The effectiveness of the deep LSTM
+1
model was evaluated using performance
European Conference on
metrics such as mean square error
Artificial Intelligence
(MSE), root mean square error (RMSE),
2020 ·
mean absolute percentage error (MAPE),
14 citations
and model accuracy.
DOI
Paper Abstract summary Main findings Outcome measured
Stacked LSTM deep learning models - A stacked LSTM architecture The primary outcome measured in this study was
outperform other neural network demonstrated the highest forecasting the forecasting performance of different deep
Stock Market Forecast Using
architectures for short-term and long- performance for both short-term and learning models, including LSTM and GRU
Multivariate Analysis with
term stock market forecasting. long-term stock market predictions. architectures, in predicting stock market trends
Bidirectional and Stacked
using the S&P500 index as the target.
(LSTM, GRU)
Khaled A. Althelaya +2
National Conference on
Communications
2018 ·
57 citations
DOI
Deep learning techniques are extensively- The paper reviews the literature on Not mentioned (the abstract does not mention any
explored to predict stock market using various machine learning and data specific outcomes or endpoints that were measured
Analysis of Stock Market
movements using historical data, analysis techniques, including deep in the study)
Prediction Models Using Deep
technical indicators, and sentiment learning, to predict stock market
Learning
analysis. movements. - The paper argues that the
H. Singh
stock market is too nonlinear to be
Bioscience Biotechnology
predicted using traditional fundamental
Research Communications
and technical analysis methods, and that
2021 ·
more advanced techniques like machine
8 citations
learning are needed. - The paper
DOI
summarizes and categorizes research on
stock market prediction using machine
learning techniques published since
2011, and discusses the challenges and
future scope in this area.
Deep learning algorithms, particularly - The Convolutional Neural Network The primary outcome measured in this study was
Convolutional Neural Networks, can be (CNN) model outperformed the Artificial the accuracy of stock market price prediction using
Stock market prediction using
used to accurately predict stock market Neural Network (ANN) model, deep learning algorithms, specifically the Artificial
deep learning algorithms
prices. achieving an accuracy of 98.92% in Neural Network (ANN) and Convolutional Neural
S. Mukherjee +4
predicting stock market prices. - The Network (CNN) models.
CAAI Transactions on
CNN model used a novel approach of
Intelligence Technology
generating 2-D histograms from the
2021 ·
dataset, which had not been previously
50 citations
used for stock market prediction. - The
PDFDOI
models were able to achieve a decent
accuracy of 91% in predicting stock
market behavior during the COVID-19
pandemic, which caused a sudden
downfall in the stock market.
Paper Abstract summary Main findings Outcome measured
Deep learning models, especially - Deep learning models, including MLP, Not mentioned (the paper does not explicitly state a
Convolutional Neural Networks, RNN, LSTM, and CNN, consistently primary outcome or endpoint that was measured)
Deep Learning Models for Stock
outperform traditional linear models in outperformed the traditional linear
Market Forecasting: A
stock market forecasting. model, ARIMA, in forecasting stock
Comprehensive Comparative
prices across both the NSE and NYSE. -
Analysis
The CNN architecture demonstrated
Md Salim Chowdhury +10
exceptional performance in capturing
Journal of business and
nonlinear trends and recognizing
management studies
seasonal patterns within the stock market
2024 ·
data. - The deep learning models were
8 citations
able to adapt to dynamic market
PDFDOI
conditions and discern intricate patterns
within the financial time series data.

You might also like