• Mrs. Joshi Padma Narasimhachari
• B Sharon Angel
• B.Bindu
• CH.Supriya

The goal of this paper is to determine how well the Bitcoin volume per USD can be predicted. The Bitcoin Price Index contains price information. The work is accomplished to varying degrees of success by employing the Bayesian optimised recurrent neural network (RNN) and the Long Short Term Memory (LSTM) network. LSTM achieves a maximum accuracy of 52% and an RMSE of 8%. The popular ARIMA model for time series is used to compare with in-depth learning models. In-depth offline learning methods outperform ARIMA's poor performance forecast, as expected. Finally, both in-depth learning models are marked on both GPU and CPU, with GPU training time improving CPU implementation by 67.7%. Bitcoin, Deep Learning, GPU, Recurrent Neural Network, Long-Term Memory, ARIMA are index terms.

BITCOIN CRYPTO CURRENCY PREDICTION USING MACHINE LEARNING

"BITCOIN CRYPTO CURRENCY PREDICTION USING MACHINE LEARNING ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 6, page no.c201-c207, June-2021, Available :http://www.jetir.org/papers/JETIR2106299.pdf

"BITCOIN CRYPTO CURRENCY PREDICTION USING MACHINE LEARNING ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 6, page no. ppc201-c207, June-2021, Available at : http://www.jetir.org/papers/JETIR2106299.pdf