研究生: |
黃明源 Huang, Ming-Yuan |
---|---|
論文名稱: |
統計與機器學習方法的資產價格預測—以比特幣為例 Asset Price Forecasting with Statistical and Machine Learning Methods-The case study of Bitcoin |
指導教授: |
何宗武
Ho, Tsung-Wu |
口試委員: |
施人英
Shih, Jen-Ying 楊浩彥 Yang, Hao-Yen 何宗武 Ho, Tsung-Wu |
口試日期: | 2023/04/27 |
學位類別: |
碩士 Master |
系所名稱: |
全球經營與策略研究所 Graduate Institute of Global Business and Strategy |
論文出版年: | 2023 |
畢業學年度: | 111 |
語文別: | 中文 |
論文頁數: | 66 |
中文關鍵詞: | 比特幣 、格蘭傑因果相關檢驗 、VAR 、ARIMA 、SVM 、GBM 、ENET 、組合預測法 |
英文關鍵詞: | Bitcoin, Granger Causality, VAR, ARIMA, SVM, GBM, ENET, Combination Forecast |
DOI URL: | http://doi.org/10.6345/NTNU202301224 |
論文種類: | 學術論文 |
相關次數: | 點閱:111 下載:19 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
資產價格的預測性在市場效率假說提出後便受到眾多討論,至今亦有許多研究係利用此概念在不同的金融資產上進行實證分析。隨著近年加密貨幣的快速發展,其價格劇烈的增長吸引許多投機客進入該市場,而使得發展及波動更加劇烈,在市值大幅成長的同時也引來學者的警告,諾貝爾經濟學獎得主Joseph Stiglitz 與Robert Shiller便稱其為「危險的投機泡沫」。本研究同時利用傳統時間序列模型與機器學習模型,對比特幣報酬與價格進行預測並比較預測表現。我們發現機器學習模型對報酬進行預測,有較小的預測誤差,表現優於傳統時間序列模型,然而透過繪圖則顯現出其較佳的預測效果係來自較低幅度的波動,實際上預測表現並不理想。而後利用組合預測法改善,根據Diebold-Mariano 檢定的結果,雖然比起單一傳統時間序列模型來得要好,卻也是源自低幅度的波動所致。基於上述結果,我們認為比特幣的價格或報酬的可預測性較低。
The predictability of asset prices has been widely discussed since the introduction of the market efficiency hypothesis and has been applied to various financial assets. With the rapid development of cryptocurrencies in recent years, their volatile price growth has attracted many speculators to enter the market, leading to even more intense development and fluctuations. As a result, scholars have issued warnings, with Nobel laureates in economics Joseph Stiglitz and Robert Shiller referring to it as a "dangerous speculative bubble". This study simultaneously employs both traditional time series models and machine learning models to predict the returns and prices of Bitcoin, comparing their predictive performances. We found that machine learning models have smaller prediction errors than traditional time series models in predicting returns. However, visualizations show that superior predictive performance of machine learning models is due to lower magnitude volatility. Based on the results, we conclude that predicting prices or returns of Bitcoin is much infeasible.
Amélie, C, Olivier, D and Kim, JH. (2016). Stock return predictability: Evaluation based on interval forecasts. Bull Econ Res., 74, 363– 385.
Balcilar, M., Bouri, E., Gupta, R. and Roubaud, D. (2017). Can volume predict Bitcoin returns and volatility? A quantiles-based approach. Economic Modelling, 64, 74-81.
Bustos, O. and Pomares-Quimbaya, A. (2020). Stock market movement forecast: A Systematic review. Expert Systems with Applications, 156, 113464.
Clemen, R.T. (1989) Combining Forecasts: A Review and Annotated Bibliography. International Journal of Forecasting, 5, 559-583.
Cornell, Bradford and Dietrich, J. Kimball, (1978), Mean-Absolute-Deviation versus Least-Squares Regression Estimation of Beta Coefficients, Journal of Financial and Quantitative Analysis, 13, 123-131
Dai, Z., Li, T. and Yang, M. (2022). Forecasting stock return volatility: The role of shrinkage approaches in a data-rich environment. Journal of Forecasting, 41(5), 980– 996.
Danthine, J.-P. (1977). Martingale, market efficiency and commodity prices.” European Economic Review, 10, 1–17.
Diebold, F. X. and Mariano, R. S. (1995). Comparing Predictive Accuracy. Journal of Business and Economic Statistics, 13, 253-263.
Ding, Z., Granger, C. W. J. and Engle, R. F. (1993). A long memory property of stock market returns and a new model. Journal of Empirical Finance, 1(1), 83-106.
Evite, P. M. (2018). Efficient Market Hypothesis: Evidence from the Bitcoin Market (2010-2017). [Bachelor thesis, University of the Philippines Los Banos].
Fama, E. F. (1970). Efficient Capital Markets: A Review of Theory and Empirical Work. The Journal of Finance, 25(2), 383–417.
Felizardo, L.K., Oliveira, R., Del-Moral-Hernandez, E. and Cozman, F.G. (2019). Comparative study of Bitcoin price prediction using WaveNets, Recurrent Neural Networks and other Machine Learning Methods. 2019 6th International Conference on Behavioral, Economic and Socio-Cultural Computing (BESC), 1-6.
Fildes, R., & Petropoulos, F. (2015). Improving forecast quality in practice. Foresight: the International Journal of Applied Forecasting, (36), 5-12.
Gareth James, D. W., Trevor Hastie and Robert Tibshirani. (2017). An introduction to statistical learning (2nd ed.). Springer.
Guo, H., Zhang, D., Liu, S., Wang, L. and Ding, Y. (2021). Bitcoin price forecasting: A perspective of underlying blockchain transactions. Decision Support Systems, 151, 113650.
Hakim das Neves, R. (2020). Bitcoin pricing: impact of attractiveness variables. Financial Innovation, 6, 1-18.
Ibrahim, A., Kashef, R., Li, M., Valencia, E. and Huang, E. (2020) Bitcoin Network Mechanics: Forecasting the BTC Closing Price Using Vector Auto-Regression Models Based on Endogenous and Exogenous Feature Variables. Journal of Risk and Financial Management, 13(9), 189-210.
Jaquart, P., Dann, D. and Weinhardt, C. (2021). Short-term bitcoin market prediction via machine learning. The Journal of Finance and Data Science, 7, 45-66.
Kurihara, Y. and , A. (2017). The Market Efficiency of Bitcoin: A Weekly Anomaly Perspective. Journal of Applied Finance and Banking, 7, 57-64.
Lamothe-Fernández, P., Alaminos, D., Lamothe-López, P. and Fernández-Gámez, M. A. (2020). Deep Learning Methods for Modeling Bitcoin Price. Mathematics, 8(8), 12-45.
Mensi, Walid, Tiwari, Aviral and Yoon, Seong-Min, (2017), Global financial crisis and weak-form efficiency of Islamic sectoral stock markets: An MF-DFA analysis, Physica A: Statistical Mechanics and its Applications, 471, issue C, 135-146
Nagula, P. K. and Alexakis, C. (2022). A new hybrid machine learning model for predicting the bitcoin (BTC-USD) price. Journal of Behavioral and Experimental Finance, 36, 100741.
Okorie, D. I. and Lin, B. (2020). Crude oil price and cryptocurrencies: Evidence of volatility connectedness and hedging strategy. Energy Economics, 87, 104703.
Selmi, Refk, Tiwari, Aviral and Hammoudeh, Suleiman. (2018). Efficiency or speculation? A dynamic analysis of the Bitcoin market. Economics Bulletin. 38. 2037-2046.
Tsay, R. S. (2010). Analysis of financial time series (3rd ed.). Wiley.
Urquhart, A., (2016) “The inefficiency of Bitcoin.” Economics Letters, 148, 80-82.
Rizwan, M., Narej, S., & Javed, M. Bitcoin price prediction using deep learning algorithm. 2019 13thInternational Conference on Mathematics, Actuarial Science, Computer Science and Statistics,1-7.
Roll, R. (1972). Interest Rates on Monetary Assets and Commodity Price Index Changes. The Journal of Finance, 27(2), 251–277.
Wirawan, I Made & Widiyaningtyas, Triyanna & Hasan, Muchammad. (2019). Short Term Prediction on Bitcoin Price Using ARIMA Method. 260-265.
Yi, E., Yang, B., Jeong, M., Sohn, S. and Ahn, K. (2023). Market efficiency of cryptocurrency: evidence from the Bitcoin market. Scientific Reports, 13(1).
Zou, H., and Hastie, T. (2005). Regularization and Variable Selection via the Elastic Net. Journal of the Royal Statistical Society. Series B (Statistical Methodology), 67(2), 301–320.
何宗武、葉國俊、牟萬馨、林雅淇 (2021). 運用大數據機器學習方法預測臺灣經濟成長率. 中央銀行季刊, 43, 13-47.
何宗武 (2022). 財經時間序列預測:使用R的計量與機器學習方法 (1st ed.). 五南圖書出版有限公司.
朱君亞、林士貴、蔡炎龍、張安興 (2022).金融壓力事件預警模型:類神經網路、支援向量機與羅吉斯迴歸之比較.統計與資訊評論, 21, 117-150.
李惠妍、吳宗正、溫敏杰 (2006). 迴歸模式與類神經網路在台股指數期貨預測之研究. 經營管理論叢, 2(1), 83-99.
吳仲平(2018).比特幣價格與總體經濟變數之關聯性.﹝碩士論文。國立臺灣大學﹞臺灣博碩士論文知識加值系統.
洪詩婷(2018).比特幣與匯率、股市及景氣關聯性之研究.﹝碩士論文。國立政治大學﹞臺灣博碩士論文知識加值系統.
施育霖(2019).以機器學習方法預測股價:以台股金融類股為案例.﹝碩士論文。國立中興大學﹞臺灣博碩士論文知識加值系統.
陳江明(1993).臺灣股票市場報酬率之預測模型:平均數復歸行為之應用.﹝碩士論文。國立中央大學﹞臺灣博碩士論文知識加值系統.
陳旭昇 (2014). 時間序列分析:總體經濟與財務金融之應用 (2nd ed.). 東華書局暨新月圖書公司.
陳彥錚 (2013). 為什麼匯率組合預測有效?.﹝碩士論文。國立政治大學]臺灣博碩士論文知識加值系統.
陳振東、謝政翰(2019).應用機器學習與模糊推論於股價漲跌預測之研究.資訊管理學報, 26(2), 153-177.
許允禎(2018).比特幣與金融資產之關聯性探討.﹝碩士論文。國立政治大學﹞臺灣博碩士論文知識加值系統.
郭炳伸, 藍青玉 (2015). 模型組合與新台幣匯率預測. 臺灣經濟預測與政策, 46(1), 75-111.
郭維裕、陳威光、陳鴻隆、林信助 (2009) .動態隱含波動度模型:以臺指選擇權為例. 期貨與選擇權學刊, 2(2), 47-89.
潘志刚,韩颖 (2006).组合预测法在我国汽车市场需求预测中的应用.商业研究, 20, 126-129.
謝佳容(2017).比特幣匯率之實證分析.﹝碩士論文。國立臺灣大學﹞臺灣博碩士論文知識加值系統.
聶建中、馮正安、郭繼良(2001). 金融風暴期間新台幣兌美元匯率預測—倒傳遞神經網路之應用. 台灣金融財務季刊, 2(3), 119-147.