The objective of the project is to leverage deep learning models to predict the future prices of cryptocurrency. Recurrect neural networks(RNNs) have demonstrated strong learning techniques in time-series data prediction, due to the ability to remember and extract temporal features of data. Another most well-known and successful statistical model for time-series prediction is ARIMA (Auto Regressive Integrated Moving Average). In this project, we create a hybrid framework of Bidirectional LSTM and ARIMA for cryptocurrency price prediction.