Is this project an undergraduate, graduate, or faculty project?
Graduate
individual
What campus are you from?
Daytona Beach
Authors' Class Standing
Shital Pandey, Graduate Student
Lead Presenter's Name
Shital Pandey
Faculty Mentor Name
Dr. Harihar Khanal
Abstract
Over the last several years, new kinds of currency, such as cryptocurrencies, have been constantly emerging. In terms of market value, cryptocurrency is extremely volatile, with a slew of unknowns that make it difficult to forecast and analyze future pricing. With the ability to predict crypto prices, one can make a prediction for stocks since the popular coin; Bitcoin affects stock prices. Although machine learning has been successful in predicting stock market prices using a variety of time series models, it has been limited in its use in predicting cryptocurrency prices. The reason for this is obvious: cryptocurrency values are influenced by a variety of factors such as technological advancements, internal competitiveness, market pressure to produce, economic troubles, security concerns, political factors, and so on. This research proposes three recurrent neural networks (RNN) algorithms for predicting the values of three different cryptocurrencies: Bitcoin (BTC), Litecoin (LTC), and Ethereum (ETH). The three models, namely gated recurrent unit (GRU), long short-term memory (LSTM), and bi-directional LSTM (bi-LSTM) will be analyzed depending on the mean absolute percentage error (MAPE).
Did this research project receive funding support from the Office of Undergraduate Research.
Yes, Student Internal Grant
Cryptocurrency Price Prediction using Neural Networks and Deep Learning Techniques
Over the last several years, new kinds of currency, such as cryptocurrencies, have been constantly emerging. In terms of market value, cryptocurrency is extremely volatile, with a slew of unknowns that make it difficult to forecast and analyze future pricing. With the ability to predict crypto prices, one can make a prediction for stocks since the popular coin; Bitcoin affects stock prices. Although machine learning has been successful in predicting stock market prices using a variety of time series models, it has been limited in its use in predicting cryptocurrency prices. The reason for this is obvious: cryptocurrency values are influenced by a variety of factors such as technological advancements, internal competitiveness, market pressure to produce, economic troubles, security concerns, political factors, and so on. This research proposes three recurrent neural networks (RNN) algorithms for predicting the values of three different cryptocurrencies: Bitcoin (BTC), Litecoin (LTC), and Ethereum (ETH). The three models, namely gated recurrent unit (GRU), long short-term memory (LSTM), and bi-directional LSTM (bi-LSTM) will be analyzed depending on the mean absolute percentage error (MAPE).