Combining Data Filtration and Regression Learning for Enhancing the Forecasting of Cryptocurrencies

Abstract-The cryptocurrency market is highly volatile and unpredictable, making traditional financial models less effective for price forecasting. Unlike stock markets, which are influenced by earnings reports and economic indicators, cryptocurrency prices are driven by a combination of market sentiment, technological developments, regulatory changes, and supply-demand dynamics. Due to the complexity and non-linearity of these factors, machine learning (ML) has emerged as a powerful tool for predicting crypto prices with greater accuracy. The proposed work employs the steepest descent based scaled back propagation algorithm along with the data pre-processing using the discrete wavelet transform (DWT) for crypto price prediction. It has been shown that the proposed system attains lesser MAPE% error compared to previously existing techniques making it a more accurate forecasting model.