Cryptocurrencies have transformed financial markets with their innovative blockchain technology and volatile price movements, presenting both challenges and opportunities for predictive analytics. Ethereum, being one of the leading cryptocurrencies, has experienced significant market fluctuations, making its price prediction an attractive yet complex problem. This paper presents a comprehensive study on the effectiveness of Large Language Models (LLMs) in predicting Ethereum prices for short-term and few-shot forecasting scenarios. The main challenge in training models for time series analysis is the lack of data. We address this by leveraging a novel approach that adapts existing pre-trained LLMs on natural language or images from billions of tokens to the unique characteristics of Ethereum price time series data. Through thorough experimentation and comparison with traditional and contemporary models, our results demonstrate that selectively freezing certain layers of pre-trained LLMs achieves state-of-the-art performance in this domain. This approach consistently surpasses benchmarks across multiple metrics, including Mean Squared Error (MSE), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE), demonstrating its effectiveness and robustness. Our research not only contributes to the existing body of knowledge on LLMs but also provides practical insights in the cryptocurrency prediction domain. The adaptability of pre-trained LLMs to handle the nature of Ethereum prices suggests a promising direction for future research, potentially including the integration of sentiment analysis to further refine forecasting accuracy.

The research delves into the capabilities of a transformer-based neural network for Ethereum cryptocurrency price forecasting. The experiment runs around the hypothesis that cryptocurrency prices are strongly correlated with other cryptocurrencies and the sentiments around the cryptocurrency. The model employs a transformer architecture for several setups from single-feature scenarios to complex configurations incorporating volume, sentiment, and correlated cryptocurrency prices. Despite a smaller dataset and less complex architecture, the transformer model surpasses ANN and MLP counterparts on some parameters. The conclusion presents a hypothesis on the illusion of causality in cryptocurrency price movements driven by sentiments.

In this context, the machine learning algorithms at the cryptocurrency tracking platform PricePredictions, which rely on moving averages (MA), …

The cryptocurrency sector has found itself under increased regulatory pressure in the past weeks, but despite the difficult times, that didn't prevent its representative assets from recording some strong gains, including Ethereum (ETH). Crypto traders and investors are now looking for indicators of further advances or declines with the market's second-largest asset at the start of next month. In this context, the machine learning algorithms at the cryptocurrency tracking platform PricePredictions have projected that Ethereum would be changing hands at the price of $1,747 by March 1, 2023, as per data accessed by Finbold on February 21. Should the predictions of the machine algorithm, which deploys indicators like relative strength index (RSI), Bollinger Bands (BB), moving averages (MA), moving average convergence divergence (MACD), and others, prove correct, this would mean that Ethereum would be trading 3.1% higher from its price at press time. Meanwhile, the sentiment on the 1-week gauges over at the finance and crypto tracking website TradingView is generally positive and suggests'buy' at 12 – as summarized from the oscillators pointing towards'neutral' at 8 and moving averages sitting in the'buy' zone at 10. As things stand, the price of Ethereum currently stands at $1,694, which represents a modest increase of 0.13% over the last 24 hours but, at the same time, a more significant gain of 12.4% across the previous week and a 4.17% growth on its monthly chart.