[论文解读] Review of deep learning models for crypto price prediction: implementation and evaluation

Jingyang Wu, Xinyi Zhang+3 more|arXiv (Cornell University)|May 19, 2024

Currency Recognition and Detection被引用 10

一句话总结

本文评估了加密货币价格预测的深度学习模型，评估了 LSTM、CNN 和 Transformer 的变体，在关键情景中发现卷积LSTM搭配多变量输入最为准确。

ABSTRACT

There has been much interest in accurate cryptocurrency price forecast models by investors and researchers. Deep Learning models are prominent machine learning techniques that have transformed various fields and have shown potential for finance and economics. Although various deep learning models have been explored for cryptocurrency price forecasting, it is not clear which models are suitable due to high market volatility. In this study, we review the literature about deep learning for cryptocurrency price forecasting and evaluate novel deep learning models for cryptocurrency stock price prediction. Our deep learning models include variants of long short-term memory (LSTM) recurrent neural networks, variants of convolutional neural networks (CNNs), and the Transformer model. We evaluate univariate and multivariate approaches for multi-step ahead predicting of cryptocurrencies close-price. We also carry out volatility analysis on the four cryptocurrencies which reveals significant fluctuations in their prices throughout the COVID-19 pandemic. Additionally, we investigate the prediction accuracy of two scenarios identified by different training sets for the models. First, we use the pre-COVID-19 datasets to model cryptocurrency close-price forecasting during the early period of COVID-19. Secondly, we utilise data from the COVID-19 period to predict prices for 2023 to 2024. Our results show that the convolutional LSTM with a multivariate approach provides the best prediction accuracy in two major experimental settings. Our results also indicate that the multivariate deep learning models exhibit better performance in forecasting four different cryptocurrencies when compared to the univariate models.

研究动机与目标

• 综述关于使用深度学习进行加密货币价格预测的文献。
• 评估单变量和多变量深度学习模型在多步前瞻的收盘价预测中的性能。
• 分析训练数据体制（疫情前与疫情期间）对预测精度的影响。
• 评估 COVID-19 期间主要加密货币的波动性特征及其对预测的影响。

提出的方法

• 回顾用于加密货币价格预测的现有深度学习方法（LSTM 变体、CNN 变体、Transformer）。
• 实现并评估用于加密货币多步前瞻收盘价预测的单变量和多变量模型。
• 使用波动性分析来表征 COVID-19 期间的价格波动。
• 比较两种训练集情景：疫情前数据与疫情期间数据在 2023–2024 年预测中的表现。
• 在多变量模型中，包含黄金价格、加密货币的收盘/开盘/最高价，以及相关加密货币价格指数等特征。

实验结果

研究问题

• RQ1 哪些深度学习体系结构（LSTM 变体、CNN、Transformer）在加密货币价格预测中提供最佳准确性？
• RQ2 多变量模型在预测加密货币价格方面是否优于单变量模型？
• RQ3 在疫情前数据与疫情期间数据训练下，模型的性能有何不同？
• RQ4 波动性与外部指标（如黄金价格）在提高预测准确性中的作用是什么？

主要发现

• 卷积LSTM结合多变量输入在两个主要实验设置中带来最佳预测准确度。
• 在对四种不同加密货币的预测中，多变量深度学习模型的表现优于单变量模型。
• 波动性分析揭示COVID-19期间存在显著的价格波动。
• 使用疫情前数据的预测情景与使用疫情期间数据的预测情景存在差异，影响预测性能。
• 研究强调将跨资产指标纳入多变量模型可提高相对于单变量方法的预测准确性。