Review of deep learning models for crypto price prediction: implementation and evaluation

Paper: arXiv 2405.11431

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.

Complexity vs Empirical Score

• Math Complexity: 6.5/10
• Empirical Rigor: 7.0/10
• Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper employs advanced deep learning architectures (LSTM, CNN, Transformers) requiring knowledge of stochastic optimization and time-series embedding, yet it is heavily grounded in empirical evaluation with specific dataset splits (pre- and post-COVID), volatility analysis, and multivariate comparative benchmarks.

Research Flowchart

  flowchart TD
  A["Research Goal:<br>Review & Evaluate DL Models<br>for Crypto Price Prediction"] --> B{"Data & Input"}
  B --> B1["Pre-COVID-19 Dataset<br>(Early Pandemic Prediction)"]
  B --> B2["COVID-19 Dataset<br>(2023-2024 Prediction)"]
  B --> B3["4 Cryptocurrencies<br>Volatility Analysis"]
  
  B --> C{"Methodology: Deep Learning Models"}
  C --> C1["LSTM Variants"]
  C --> C2["CNN Variants"]
  C --> C3["Transformer Model"]
  
  C --> D{"Evaluation Framework"}
  D --> D1["Univariate Approach<br>Single feature input"]
  D --> D2["Multivariate Approach<br>Multiple feature input"]
  D --> D3["Multi-step Ahead Prediction"]
  
  C1 & C2 & C3 --> E["Computational Process<br>Training & Validation"]
  D1 & D2 & D3 --> E
  
  E --> F["Key Findings / Outcomes"]
  F --> F1["Best Model:<br>ConvLSTM with Multivariate Approach"]
  F --> F2["Multivariate models<br>outperform univariate models<br>across all 4 cryptocurrencies"]
  F --> F3["Significant price volatility<br>observed during COVID-19 period"]

Cited References (192)

1. Community detection in graphs (2010)
2. Finding and evaluating community structure in networks (2004)
3. Visualizing Fuzzy Overlapping Communities in Networks (2013)
4. Near linear time algorithm to detect community structures in large-scale networks (2007)
5. Robust network community detection using balanced propagation (2011)
6. Detecting community structure using label propagation with weighted coherent neighborhood propinquity (2013)
7. Finding community structure in very large networks (2004)
8. Fast unfolding of communities in large networks (2008)

0 of 192 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.