An Efficient Ensemble Model for Forecasting Time Series Analysis of Crypto Currency Data Using Machine Learning

Time series data are analyzed for predicting the future based on the consistent time period using statistical methods. These analyses are based on the data which are extracted from different sources. Existing method for performing the forecasting process does not fit into the crypto currency data. GARCH and ARIMA models with intelligent mechanisms provide the solution but it is not at the proper level. RNN model takes the data from preexisting intervals and decides the next time series data which is represented as a directed graph. Two types of behavior are considered namely spatial and temporal. The linear model uses the homogeneous data and heterogeneous data analysis is based on the nonlinear model. The nodes and layers are connected based on the input and corresponding activation unit. The memory model is attached to the RNN model for making persistent storage for keeping the processed data for a longer time. The proposed model uses the ensemble method for integrating various RNN models for achieving a high level of accuracy.