Author Information

Shital PandeyFollow

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

Share

COinS
 

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).

 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.