In this paper, we compare the predictive power of Auto Regressive Integrated Moving Averages (ARIMA) and Multi-Layer Perceptron Artificial Neural Networks (MLP ANN) model to short-term forecast the monthly returns of Bitcoin cryptocurrency. We evaluate the performance of two models using time series with monthly data from January 2018 to December 2021. The key parameters for the final assessment of prognostic models are the values of Root Mean Square Error-RMSE and Forecast Error-FE. The results of the short-term BTC return forecast showed better properties of composite compared to univariate time series forecasting models, i.e., higher prognostic power of the MLP ANN model compared to the selected ARIMA (1,1,3) model (lower RMSE and FE). The results point to further comparative research of prognostic models and the possibility of forming more complex and hybrid structures of neural network models in order to predict economic phenomena as accurately as possible.

The main goal of the research is to predict the future monthly returns of cryptocurrencies using the Vector Error Correction Model (VECM). Time series for the period 2018-2021 consists o f data on monthly returns for the cryptocurrencies Bitcoin, Ethereum and Ripple, as well as monthly returns on gold and the S&P500 stock index. Within the VECM, using the Johansen and Granger tests, short-term cointegration and causality among variables were determined, without the existence o f long-term equilibrium. The resulting model for short-term prediction o f the monthly returns o f the cryptocurrency Bitcoin was evaluated as unbiased and stable with a realistic forecast error o f 0.168 (16.8%).