Bitcoin Price Prediction Using Artificial Neural Network

Bitcoin has recently attracted considerable attention in the fields of economics, cryptography, and computer science due to its inherent nature of combining encryption technology and monetary units. Predicting future index price has always been a problem research area both for the investors who want to get a profit by trading stocks and for the researchers who try to expose the buried information from the complex stock market time series data. In this paper, an artificial neural network model has been developed to estimate the Bitcoin price by using open price, close price, high price, low price and volume are the major parameters have been considered for modeling. The presented model has been evaluated with weighted regression one to compare the performance of neural network model, which it being used in this research. The well known software of MATLAB has been used for analytical process and for models' performance comparison, while the mean square errors have been considered as criteria.Results show that artificial neural network has the better performance with minimum mean square errore to estimate stock price forcast regarding to weighted linear regression.

Keywords:

Artifical neural network , linear regression , stock marke