LSTM Prediction of Short-Term Crypto Price Moves from Trade Data

Summary

This paper describes a Long Short-Term Memory model that predicts cryptocurrency price direction over a fixed short-term horizon using trade-by-trade data from a lookback period. Its workflow includes feature design and hyperparameter search, with training based on nearly a year of transaction observations.

The authors report out-of-sample accuracy above 60%, say the performance remains stable across test periods, and describe a trading simulation in which predictions could be monetized. They also report that parameters trained on some instruments retain performance on other cryptocurrencies. The excerpt does not identify the assets, forecast horizon, sample dates, simulation assumptions, or performance after fees and slippage. These reported findings therefore do not establish profitability in live trading or universal transfer across crypto markets.

Key ideas

• The framework uses LSTM networks to forecast short-horizon cryptocurrency price direction from trade-by-trade observations.
• Feature design and hyperparameter search are central parts of the modeling process.
• The paper reports out-of-sample accuracy above 60% and a trading simulation with monetizable predictions.
• It reports transfer to other cryptocurrency instruments, while leaving costs and simulation details unspecified.

Tags

# A Deep Learning Framework for Predicting Digital Asset Price Movement from Trade-by-trade Data


# A Deep Learning Framework for Predicting Digital Asset Price Movement from Trade-by-trade Data









This paper presents a deep learning framework based on Long Short-term Memory Network(LSTM) that predicts price movement of cryptocurrencies from trade-by-trade data. The main focus of this study is on predicting short-term price changes in a fixed time horizon from a looking back period. By carefully designing features and detailed searching for best hyper-parameters, the model is trained to achieve high performance on nearly a year of trade-by-trade data. The optimal model delivers stable high performance(over 60% accuracy) on out-of-sample test periods. In a realistic trading simulation setting, the prediction made by the model could be easily monetized. Moreover, this study shows that the LSTM model could extract universal features from trade-by-trade data, as the learned parameters well maintain their high performance on other cryptocurrency instruments that were not included in training data. This study exceeds existing researches in term of the scale and precision of data used, as well as the high prediction accuracy achieved.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.