Leveraging LSTM for Time-Series Analysis of Cryptocurrency Prices


  • Kanhaiya Naik
  • Krishna Kumar
  • Prashant Bansode
  • Astitva Nikose
  • Naina S. Kokate


Cryptocurrency Price prediction, Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN), Time series analysis, mean absolute error (MAE), Root mean squared error (RMSE).


Cryptocurrency prices are highly volatile and subject to rapid fluctuations, making accurate price prediction a challenging task. In recent years, Long Short-Term Memory (LSTM), a type of Recurrent Neural Network (RNN), has emerged as a promising approach for predicting time series data, such as cryptocurrency prices. In this research paper, we apply LSTM to predict the prices of cryptocurrencies, including Bitcoin and Ethereum. We use historical price and volume data as input features and evaluate the performance of LSTM using metrics such as mean absolute error (MAE) and root mean squared error (RMSE). The results of our study show that LSTM outperforms traditional statistical methods, such as linear regression, in terms of prediction accuracy. Our findings demonstrate the potential of LSTM in predicting cryptocurrency prices and provide insights into the underlying dynamics of the cryptocurrency market.


Download data is not yet available.




How to Cite

Kanhaiya Naik, Krishna Kumar, Prashant Bansode, Astitva Nikose, & Naina S. Kokate. (2023). Leveraging LSTM for Time-Series Analysis of Cryptocurrency Prices. International Journal of Progressive Research in Science and Engineering, 4(02), 35–37. Retrieved from https://journal.ijprse.com/index.php/ijprse/article/view/788




Most read articles by the same author(s)