Noise Effect on Forecasting

Abstract

The lack of regulation and liquidity in crypto money markets causes higher volatility compared to other financial markets. This situation increases the noise in price change. The high noise and random walk create a problem that cannot be explained by traditional stochastic financial methods. For this reason, a multi-layered deep learning model with an additive attention layer, which uses a single observation in 10-day sequences, was used in this study. Different transformations are used to reduce the noise of the closing values. As a result of the comparisons made between different approaches, it has been revealed that exponential moving averages, to be used as the value to predict, give better results than other conversions and estimation of the original price, since they explain the price better than simple moving averages and reduce the noise of the original price.