2021年，隨著以比特幣(BTC)為首的加密貨幣牛市行情崛起，引起許多人的關注，為了想從中獲利不少投資人便開始進入加密貨幣交易市場，當中不乏投資經驗豐富的老手、 其他產業的投資專家或者無經驗卻想賺錢的投機客，屬於高風險高報酬的市場。由於影響加密貨幣的因素眾多其價格波動的趨勢也難以被預測，因此本研究將使用技術分析指標中的ORB(Opening Range Breakout)作為買賣比特幣的交易策略，配合近幾年因科技進步發展而被廣泛用於各項領域的深度學習為基礎，進一步改善單一深度學習模型可能發生過度擬合問題，本研究將使用集成學習方法結合三種深度學習模型，讓模型的預測能力能夠更加精確，最終將混和預測模型與技術分析指標，用於模擬比特幣的交易策略，評估方法的獲利能力。結果顯示ORB指標使用在比特幣交易具有強大的收益能力，本研究所提出的Ensemble-ORB方法，從2019年起至2022年底的總報酬為83705美金，累計回報率為505%，兩項指標皆以1.5倍的差距勝於 Chen et al. (2020)提出CNN-ORB的方法，證明技術指標的交易策略在比特幣市場上是有利可圖的，且所提出之方法可幫助投資者在買賣時給予建議，避免在價格波動劇烈的比特幣市場上發生極大的虧損。

In 2021, with the rise of the cryptocurrency bull market led by Bitcoin (BTC), it caught the attention of many people. To profit from this trend, numerous investors, including experienced traders, investment experts from other industries, and even speculative individuals without prior experience, began entering the cryptocurrency trading market. It is a high-risk, high-reward market. Due to the multitude of factors influencing cryptocurrency and the difficulty in predicting price fluctuations, this study utilizes the Opening Range Breakout (ORB) from technical analysis indicators as a trading strategy for buying and selling Bitcoin. With the rapid advancement of technology in recent years, deep learning has been widely applied in various fields. In order to improve the issue of overfitting that may occur in a single deep learning model, this study will employ ensemble learning by combining three different deep learning models to enhance the predictive accuracy of the model. Ultimately, the hybrid prediction model, along with the technical analysis indicators, is used to simulate a Bitcoin trading strategy and evaluate its profitability. The results demonstrate that the ORB indicator possesses strong profit-generating abilities in Bitcoin trading. The proposed Ensemble-ORB method in this study achieved a total return of $83,705 and a cumulative return rate of 505% from 2019 to the end of 2022. Both metrics outperformed Chen et al.'s (2020) CNN-ORB method by a factor of 1.5, proving that technical indicators' trading strategies are profitable in the Bitcoin market. Moreover, the proposed method can assist investors by providing advice during buying and selling, helping them avoid significant losses in the highly volatile Bitcoin market.

Aditya Pai, B., Devareddy, L., Hegde, S., & Ramya, B. S. (2022). A time series cryptocurrency price prediction using LSTM. In Emerging Research in Computing, Information, Communication and Applications (pp. 653-662). Springer, Singapore.
Andi, H. K. (2021). An accurate bitcoin price prediction using logistic regression with LSTM machine learning model. Journal of Soft Computing Paradigm, 3(3), 205-217.
Anghel, D. G. (2021). A reality check on trading rule performance in the cryptocurrency market: Machine leaning vs. technical analysis. Finance Research Letters, 39, 101655.
Aloud, M. (2021). A real-time adaptive bitcoin trading system using genetic programming. Journal of Theoretical and Applied Information Technology, 99(16).
Bai, S., Kolter, J. Z., & Koltun, V. (2018). An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271.
Basher, S. A., & Sadorsky, P. (2022). Forecasting bitcoin price direction with random forests: How important are interest rates, inflation, and market volatility?. Machine Learning with Applications, 100355.
Balcilar, M., Bouri, E., Gupta, R., & Roubaud, D. (2017). Can volume predict bitcoin returns and volatility? A quantiles-based approach. Economic Modelling, 64, 74-81.
Breiman, L. (1996). Bagging predictors. Machine learning, 24(2), 123-140.
Brito, J., & Castillo, A. (2013). Bitcoin: A primer for policymakers. Mercatus Center at George Mason University.
Brock, W., Lakonishok, J., & LeBaron, B. (1992). Simple technical trading rules and the stochastic properties of stock returns. The Journal of finance, 47(5), 1731-1764.
Cavalli, S., & Amoretti, M. (2021). CNN-based multivariate data analysis for bitcoin trend prediction. Applied Soft Computing, 101, 107065.
Chen, H. C., Syu, J. H., & Ho, J. M. (2020). Neural network-based ORB strategies for threshold classification on Taiwan futures market. In 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC) (pp. 4152-4158). IEEE.
Chen, T., & Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785-794).
Corbet, S., Eraslan, V., Lucey, B., & Sensoy, A. (2019). The effectiveness of technical trading rules in cryptocurrency markets. Finance Research Letters, 31, 32-37.
Detzel, A., Liu, H., Strauss, J., Zhou, G., & Zhu, Y. (2021). Learning and predictability via technical analysis: Evidence from bitcoin and stocks with hard‐to‐value fundamentals. Financial Management, 50(1), 107-137.
Gerritsen, D. F., Bouri, E., Ramezanifar, E., & Roubaud, D. (2020). The profitability of technical trading rules in the bitcoin market. Finance Research Letters, 34, 101263.
Gradojevic, N., Kukolj, D., Adcock, R., & Djakovic, V. (2021). Forecasting bitcoin with technical analysis: A not-so-random forest?. International Journal of Forecasting, 39(1),1-17.
Guo, C., Kang, X., Xiong, J., & Wu, J. (2022). A new time series forecasting model based on complete ensemble empirical mode decomposition with adaptive noise and temporal convolutional network. Neural Processing Letters, 1-21.
Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780.
Hisham, S., Makhtar, M., & Aziz, A. A. (2022).Combining multiple classifiers using ensemble method for anomaly detection in blockchain networks: A comprehensive review. International Journal of Advanced Computer Science and Applications, 13(8).
Hiroshima, J., & Otsuki, N. (2019). Evaluation by the aumann and serrano performance index and Sharpe ratio: bitcoin performance. Applied Economics, 51(39), 4282-4298.
Hudson, R., & Urquhart, A. (2021). Technical trading and cryptocurrencies. Annals of Operations Research, 297(1), 191-220.
Huang, J. Z., Huang, W., & Ni, J. (2019). Predicting bitcoin returns using high-dimensional technical indicators. The Journal of Finance and Data Science, 5(3), 140-155.
Hüseyinov, İ., & Uluçay, S. (2019, September). Application of genetic and particle swarm optimization algorithms to portfolio optimization problem: Borsa istanbul and crypto money exchange. In 2019 4th International Conference on Computer Science and Engineering (UBMK) (pp. 189-194). IEEE.
Kristoufek, L. (2015). What are the main drivers of the bitcoin price? Evidence from wavelet coherence analysis. PloS one, 10(4), e0123923.
Lansky, J. (2018). Possible state approaches to cryptocurrencies. Journal of Systems integration, 9(1), 19.
LeCun, Y., & Bengio, Y. (1995). Convolutional networks for images, speech, and time series. The handbook of brain theory and neural networks, 3361(10).
Li, Q. (2020, December). Predicting trends of bitcoin prices based on machine learning methods. In 2020 The 4th International Conference on Software and e-Business (pp. 49-52).
Manchanda, H., & Aggarwal, S. (2021). Forecasting cryptocurrency time series using adaboost-based ensemble learning techniques. In Innovations in Cyber Physical Systems (pp. 207-219). Springer, Singapore.
Nagula, P. K., & Alexakis, C. (2022). A new hybrid machine learning model for predicting the bitcoin (BTC-USD) price. Journal of Behavioral and Experimental Finance, 36, 100741.
Neely, C., Weller, P., & Dittmar, R. (1997). Is technical analysis in the foreign exchange market profitable? A genetic programming approach. Journal of financial and Quantitative Analysis, 32(4), 405-426.
Resta, M., Pagnottoni, P., & De Giuli, M. E. (2020). Technical analysis on the bitcoin market: trading opportunities or investors’ pitfall?. Risks, 8(2), 44.
Radeerom, M. (2014, April). Building a Trade System by genetic algorithm and technical analysis for Thai stock index. In Asian Conference on Intelligent Information and Database Systems (pp. 414-423). Springer, Cham.
Schatzmann, J. E., & Haslhofer, B. (2020). Bitcoin trading is irrational! An analysis of the disposition effect in bitcoin. arXiv preprint arXiv:2010.12415.
Sharpe. (1966). W. F. Mutual fund performance. Journal of Business. 39 (S1): 119–138.
Stavroyiannis, S. (2019). Can bitcoin diversify significantly a portfolio?. International Journal of Economics and Business Research, 18(4), 399-411.
Steadman, I. (2013). Wary of bitcoin? A guide to some other cryptocurrencies. Ars Technica, 11.
Syu, J. H., & Wu, M. E. (2021). Modifying ORB trading strategies using particle swarm optimization and multi-objective optimization. Journal of Ambient Intelligence and Humanized Computing, 1-13.
Tao, T., Liu, Y., Qiao, Y., Gao, L., Lu, J., Zhang, C., & Wang, Y. (2021). Wind turbine blade icing diagnosis using hybrid features and Stacked-XGBoost algorithm. Renewable Energy, 180, 1004-1013.
Wu, C. H., Lu, C. C., Ma, Y. F., & Lu, R. S. (2018). A new forecasting framework for bitcoin price with LSTM. In 2018 IEEE International Conference on Data Mining Workshops (ICDMW) (pp. 168-175). IEEE.
Wu, M. E., Syu, J. H., Lin, J. C. W., & Ho, J. M. (2021). Evolutionary ORB-based model with protective closing strategies. Knowledge-Based Systems, 216, 106769.
Ye, Z., Wu, Y., Chen, H., Pan, Y., & Jiang, Q. (2022). A Stacking ensemble deep learning model for bitcoin price prediction using twitter comments on bitcoin. Mathematics, 10(8), 1307.
Yu, F., & Koltun, V. (2015). Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122.
Zhao, B., Lu, H., Chen, S., Liu, J., & Wu, D. (2017). Convolutional neural networks for time series classification. Journal of Systems Engineering and Electronics, 28(1), 162-169.