Description
TL;DR: A hybrid deep-learning forecasting model compared with recurrent alternatives using error metrics on two financial time series.
About This Document
Mohamed El Mahjouby and coauthors train a SimpleRNN–LSTM model on Bitcoin and EUR/USD data enriched with technical indicators. They compare the hybrid with SimpleRNN, LSTM, and GRU approaches using four reported evaluation measures and present the resulting forecasts and performance differences.
Why Bitcoin People May Care
Model fit on a selected historical dataset is not reliable evidence of future profit. Results can depend on time window, preprocessing, indicator leakage, hyperparameters, and market regime. This paper is a 2025 machine-learning study, not a live signal service, trading strategy, or investment recommendation.
What You Receive
Purchase reveals the verified preserved PDF location for this document.
Document Details
- Title: RNN–LSTM Forecasting for Bitcoin and EUR/USD
- Author / organization: Mohamed El Mahjouby, Khalid El Fahssi, Mohamed Taj Bennani, Mohamed Lamrini, and Mohamed El Far
- Year: 2025
- Language: English
- Document type: Financial machine-learning research paper
- Pages: 10
CacheRat provides researched source-location and document-identification information. CacheRat does not claim ownership of the underlying third-party documentation.
