隨著人工智慧加速發展，許多人想利用AI來預測市場趨勢，而數位貨幣價格以比特幣、乙太幣為首又在去年(2017年)狂飆數十甚至數百倍，媒體、社交網站上討論熱度越來越熱，人們自然得希望能用AI的方式預測虛擬幣市場。
本研究以推特貼文為訓練資料並以向量化的方式來表示一天的推文資訊(日向量)。首先清理Twitter原始資料，經過日向量模型把每天的推文轉換成日向量，最後以日向量為基礎用Sequence to Sequence模型進行比特幣漲跌幅進行預測。整個系統分別在日向量模型及Sequence to Sequence模型各採用了1個attention模型。
實驗結果可以看出隨著日向量維度上升預測準確率會略為上升，而SequenceDecoder model 的attention model可以較明顯的提升預測準確度。最後，我們個別分析7天的預測結果，發現預測越前面的天數(下一天，下兩天)準確率越高，這也和我們的直覺相符合。

With the accelerated development of artificial intelligence, some people want to use it to predict market trends. Simultaneously, digital currency, headed by Bitcoin and Ethereum, caught people’s attention because of its soaring price in last year. The reputation of digital currency get higher and higher in social media and traditional media. People certainly hope to use AI to predict the digital currency market.
In this research, we use Twitter posts as training data and vectored method to represent the tweet information (day vector) per day. After cleaning Twitter raw data, we converted the tweets in the giving day as day vector and feed the day vector to sequence to Sequence model use to predict the change of Bitcoin price. The entire system uses attention model in day vector model and the sequence to sequence model, respectively.
The experiments show that the prediction accuracy rise slightly by increasing day vector dimension and the attention model of the SequenceDecoder model can significantly improve the accuracy. Finally, we analyzed the 7-day predicted results individually and found that the accuracy decrease when predicting latter day. This meet our understanding that it is harder to predict the latter day than the near day.

[1] "wikipedia," [Online] Available: https://en.wikipedia.org/wiki/Ethereum.
[2] WU, Yonghui, et al. " Google's neural machine translation system: Bridging the gap between human and machine translation." arXiv Preprint arXiv, 2016.
[3] J. BOLLEN, H. MAO and X. ZENG, "Twitter mood predicts the stock market." Journal of Computational Science, p. 1-8, 2011.
[4] DING, Xiao, et al. "Deep learning for event-driven stock prediction.," Ijcai, p. 2327-2333, 2015.
[5] HU, Ziniu, et al. "Listening to chaotic whispers: A deep learning framework for news-oriented stock trend prediction." in Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining. , 2018.
[6] wikipedia, "Fundamental_analysis" [Online] Available: https://en.wikipedia.org/wiki/Fundamental_analysis.
[7] wikipedia, "Technical_analysis" [Online] Available: https://en.wikipedia.org/wiki/Technical_analysis.
[8] "Blockchain Capital Bitcoin Survey Fall 2017" [Online] Available: https://www.survey.blockchain.capital/.
[9] "Bitcoin falls $1,000 after South Korea promises crackdown on trading" [Online] Available: https://www.theguardian.com/technology/2017/dec/28/bitcoin-falls-south-korea-crackdown-trading.
[10] S. HOCHREITER and J. SCHMIDHUBER, "Long short-term memory." Neural Computation, p. 1735-1780, 1997.
[11] R. PASCANU, T. MIKOLOV and Y. BENGIO, "On the difficulty of training recurrent neural networks." International Conference on Machine Learning, p. 1310-1318, 2013.
[12] I. SUTSKEVER, O. VINYALS and Q. V. LE, "Sequence to sequence learning with neural networks." Advances in Neural Information Processing Systems, p. 3104-3112, 2014.
[13] A. Karpathy, "The Unreasonable Effectiveness of Recurrent Neural Networks" 2015. [Online] Available: http://karpathy.github.io/2015/05/21/rnn-effectiveness/.
[14] D. BAHDANAU, K. CHO and Y. BENGIO, "Neural machine translation by jointly learning to align and translate." arXiv Preprint arXiv, 2014.
[15] T. e. a. MIKOLOV, “Distributed representations of words and phrases and their compositionality.,” Advances in Neural Information Processing Systems, p. 3111-3119, 2013.
[16] "word2vec" Google, [Online] Available: https://code.google.com/archive/p/word2vec/.
[17] Q. LE and T. MIKOLOV "Distributed representations of sentences and documents." International Conference on Machine Learning, p. 1188-1196, 2014.
[18] "github" [Online] Available: https://github.com/taspinar/twitterscraper.
[19] JAQUES, Natasha, et al. "Tuning recurrent neural networks with reinforcement learning" 2017.
[20] XIA, Yingce, et al. "Deliberation networks: Sequence generation beyond one-pass decoding." Advances in Neural Information Processing Systems, p. 1784-1794, 2017.