Authors :
Mujawar Yahiya; Dhumal Harshwardhan; Thanekar Manav; Ingale Sumit
Volume/Issue :
Volume 8 - 2023, Issue 6 - June
Google Scholar :
https://bit.ly/3TmGbDi
Scribd :
https://tinyurl.com/yse39ndd
DOI :
https://doi.org/10.5281/zenodo.8074498
Abstract :
Predicting stock prices is a complex task that has
garnered significant attention from the machine learning
community in recent years. Although the stock market is
inherently unpredictable, researchers have find out various
techniques to predict stockss price with varying degrees of
success.
In this particular study, our goal is to predict stock
price over a short-term period using candlestick charts.
Candlestick chart are a popular component of technical
analysis, which provides a quick and easy way to interpret
an asset's price movements. By analyzing the patterns
formed by candlesticks, traders can often predict future
direction of prices with a reasonable degree of accuracy.
To build our predictive model, we decided to use an
LSTM model. LSTM, an acronym for long short-term
memory, refers to a specific kind of recurrent neural
network (RNN) that is adept at processing data sequences
with a temporal nature.. LSTM models are particularly
well-suited for time-series forecasting tasks because they
can handle both short-term dependencies and long-term
dependencies.
In our study, we plan to fetch historical data for the
stock we are interested in using Python libraries. Once we
have the data, we will train the LSTM model helps the data
to predict future prices of the stock. By using candlestick
charts in combination with the LSTM model, we hope to
achieve a high degree of accuracy in our stock price
predictions.
Overall, this study aims to demonstrate the
effectiveness of using candlestick charts and LSTM models
in predicting stock prices. By doing so, we hope to
contribute to the growing body of research on stock price
prediction and potentially provide insights that can help
traders and investors make better decisions in stock market.
Predicting stock prices is a complex task that has
garnered significant attention from the machine learning
community in recent years. Although the stock market is
inherently unpredictable, researchers have find out various
techniques to predict stockss price with varying degrees of
success.
In this particular study, our goal is to predict stock
price over a short-term period using candlestick charts.
Candlestick chart are a popular component of technical
analysis, which provides a quick and easy way to interpret
an asset's price movements. By analyzing the patterns
formed by candlesticks, traders can often predict future
direction of prices with a reasonable degree of accuracy.
To build our predictive model, we decided to use an
LSTM model. LSTM, an acronym for long short-term
memory, refers to a specific kind of recurrent neural
network (RNN) that is adept at processing data sequences
with a temporal nature.. LSTM models are particularly
well-suited for time-series forecasting tasks because they
can handle both short-term dependencies and long-term
dependencies.
In our study, we plan to fetch historical data for the
stock we are interested in using Python libraries. Once we
have the data, we will train the LSTM model helps the data
to predict future prices of the stock. By using candlestick
charts in combination with the LSTM model, we hope to
achieve a high degree of accuracy in our stock price
predictions.
Overall, this study aims to demonstrate the
effectiveness of using candlestick charts and LSTM models
in predicting stock prices. By doing so, we hope to
contribute to the growing body of research on stock price
prediction and potentially provide insights that can help
traders and investors make better decisions in stock market.
