This paper examines the effectiveness of Artificial Intelligence (AI) in predicting Bitcoin's price movements. To achieve this, we developed two distinct trading strategies and compared their performance against each other and the traditional Buy and Hold (B&H) strategy. Over the period from January 2018 to September 2023, we found that the strategy optimized by ChatGPT 01-Preview, which integrates multiple technical indicators and sentiment analysis into a weighted composite index, delivered an exceptional total return of 944.85 %. The second strategy, that is using Extreme Gradient Boosting (XGBoost) technique achieved a total return of 189.05 %. The AI strategy's excess return of 755.8 % over the XGBoost strategy highlights the significant advantage of AI particularly in utilizing diverse data sources, such as social media, to predict Bitcoin's price trends more effectively than relying solely on economic data. Both trading strategies significantly outperformed the traditional B&H strategy, which returned 73.08 % over the same period. Furthermore, we found that AI has an advantage during periods of high Bitcoin price volatility.

中文翻译：

---

比特币市场的智能预测


本文研究了人工智能 （AI） 在预测比特币价格走势方面的有效性。为了实现这一目标，我们开发了两种不同的交易策略，并将它们的表现与传统的买入并持有 （B&H） 策略进行比较。在 2018 年 1 月至 2023 年 9 月期间，我们发现 ChatGPT 01-Preview 优化的策略将多个技术指标和情绪分析整合到一个加权综合指数中，实现了 944.85% 的出色总回报率。第二种策略，即使用极端梯度提升 （XGBoost） 技术，实现了 189.05% 的总回报率。AI 策略比 XGBoost 策略高出 755.8% 的超额回报率，凸显了 AI 的显着优势，尤其是在利用社交媒体等各种数据源比仅依赖经济数据更有效地预测比特币的价格趋势方面。两种交易策略都明显优于传统的 B&H 策略，后者同期回报率为 73.08%。此外，我们发现人工智能在比特币价格高度波动期间具有优势。