TL;DR: A BTC/USDT forecasting experiment that changes the LSTM lookback window and compares the results with SMA, WMA, and EMA baselines.
About This Document
The study uses price data from March through April 2022 and tests several time-parameter settings for a long short-term memory model. It compares mean absolute percentage error against simple, weighted, and exponential moving averages. The authors report their lowest error when the model uses the previous three days of price data.
Why Bitcoin People May Care
Price-prediction papers age fast, which is part of their value as records. This one preserves a specific dataset window, model choice, baseline comparison, and reported 0.0927% MAPE result. It is research evidence, not a trading signal beamed backward from the future.
Document Details
• Title: Cryptocurrency Price Forecasting with Time-Varying LSTM Parameters
• Author / organization: Laor Boongasame, Panida Songram
• Year: 2023
• Document type: Machine-learning research paper
• Pages: 9
Download access
Unlock a direct PDF download of this document. The download is hosted externally. CacheRat provides researched identification and access; purchase does not transfer ownership or expand the document’s existing usage rights.
#pdf #cryptocurrency #price_forecasting #machine_learning #lstm
About This Document
The study uses price data from March through April 2022 and tests several time-parameter settings for a long short-term memory model. It compares mean absolute percentage error against simple, weighted, and exponential moving averages. The authors report their lowest error when the model uses the previous three days of price data.
Why Bitcoin People May Care
Price-prediction papers age fast, which is part of their value as records. This one preserves a specific dataset window, model choice, baseline comparison, and reported 0.0927% MAPE result. It is research evidence, not a trading signal beamed backward from the future.
Document Details
• Title: Cryptocurrency Price Forecasting with Time-Varying LSTM Parameters
• Author / organization: Laor Boongasame, Panida Songram
• Year: 2023
• Document type: Machine-learning research paper
• Pages: 9
Download access
Unlock a direct PDF download of this document. The download is hosted externally. CacheRat provides researched identification and access; purchase does not transfer ownership or expand the document’s existing usage rights.
#pdf #cryptocurrency #price_forecasting #machine_learning #lstm
Sats-powered reveal
Unlock Download
One payment unlocks this reveal. Save your secret to return. No account needed.
Unlock with Secret
Views: 3
Categories: Bitcoin & Blockchain [c26], Bitcoin & Digital Cash [c27], PDFs & Documents [c17]