Loading...
|
Please use this identifier to cite or link to this item:
https://nccur.lib.nccu.edu.tw/handle/140.119/157748
|
| Title: | 情緒指標下的原油價格之預測與交易策略
Crude Oil Price Forecasting and Trading Strategies Based on Sentiment Indicators |
| Authors: | 王廷宇
Wang, Ting-Yu |
| Contributors: | 曾正男
Tzeng, Jeng-Nan
王廷宇
Wang, Ting-Yu |
| Keywords: | 情緒指標
交易策略
門檻自迴歸模型
原油價格
時間序列分析
Sentiment Indicator
Trading Strategy
Threshold Autoregressive Model
Crude Oil Price
Time Series Analysis |
| Date: | 2025 |
| Issue Date: | 2025-07-01 14:40:18 (UTC+8) |
| Abstract: | 本研究探討結合投資人情緒指標與門檻自我迴歸模型（TAR）於西德克薩斯中級原油（WTI）市場中的價格預測與交易策略設計。原油價格波動對全球經濟及金融市場影響甚鉅，因此建立準確的預測模型與有效的交易策略至關重要。傳統預測模型往往無法充分掌握原油市場的高度非線性與突發事件，故本研究納入投資人情緒指標以提升模型預測能力，並設計能有效提升報酬、降低風險的策略。本研究使用2013年至2023年之WTI價格、道瓊指數、美元指數與舊金山聯準會發布之每日新聞情緒指數，運用含外生變數的TAR模型，將情緒區分為悲觀、不確定與樂觀，並設計相應的買賣訊號與停損停利規則。透過T檢定比較情緒指標交易策略與定期定額策略於不同持有天數（1至5日）及預測期間（1至5年）下的績效差異。研究結果顯示，長期持有策略較能穩定獲利且波動較小，情緒指標的納入可顯著提升預測精準度與策略績效，整體優於未使用情緒指標的定期定額策略。特別是在五年推測期間，結合情緒的策略表現更為穩定。然而，2020年COVID-19爆發期間的市場劇烈波動對所有策略產生負面影響。
This study investigates the integration of investor sentiment indicators with the Threshold Autoregressive (TAR) model for forecasting West Texas Intermediate (WTI) crude oil prices and designing trading strategies. Oil price volatility significantly affects the global economy and financial markets, making accurate forecasting and effective strategies essential. Traditional models often struggle with the nonlinear and event-driven nature of oil markets; hence, this study incorporates sentiment indicators to improve forecasting accuracy and risk-adjusted returns. Using data from 2013 to 2023—including WTI prices, the Dow Jones Index, the US Dollar Index, and the Federal Reserve Bank of San Francisco’s daily news sentiment index—this research applies an extended TAR model with exogenous variables. Investor sentiment is categorized into pessimistic, uncertain, and optimistic states, with corresponding buy/sell signals and stop-loss/take-profit rules. T-tests compare the performance of sentiment-based TAR strategies versus dollar-cost averaging (DCA) across different holding periods (1 to 5 days) and forecasting horizons (1 to 5 years). Results indicate that longer holding periods generally yield more stable and higher returns. Incorporating sentiment significantly enhances both prediction and trading performance, especially over longer time horizons. The sentiment-based strategy consistently outperforms the DCA strategy, though extreme market volatility during the COVID-19 outbreak in 2020 negatively affected all strategies. |
| Reference: | Thieu Thi Thanh Ha （Emily）（2017）。以原油價格及產量分析原油價格之門檻值。明志科技大學，新北市。
江政儒（2020）。應用ARIMA建立公部門航空油料需求預測模型。國防大學，桃園市。
吳宗諭（2021）。資料科學與條件風險價值強化學習於原油價格預測與採購決策。國立成功大學，臺南市。
林唯人（2024）。結合網路關鍵字熱度的原油價格預測研究：應用演算法於原油市場分析。長庚大學，桃園市。
林靜怡（2007）。股價、匯率及外資買賣超之非線性關係-多變量門檻模型之應用。財務金融學刊，15（4），103-132。
洪毓婷（2016）。時間數列模型在原油價格預測之比較分析。國立臺北大學，新北市。
陳光鑫（2023）。原油價格預測之研究：量化與文字探勘模型之分析。長庚大學，桃園市。
陳成一（2010）。原油價格避險及交易策略分析。輔仁大學，新北市。
陳雨彤（2021）。天然氣價格預測模型之比較分析。國立臺北大學，新北市。
程美齡（2022）。原油價格預測單一變數模型之比較。國立臺灣海洋大學，基隆市。
葉修為（2018）。交易策略、股價走勢和石油價格是否有助於匯率預測？國立清華大學，新竹市。
趙英宏、 趙元和（2008）。 數值分析。 台北市：五南圖書出版股份有限公司。
劉岭、王聚杰,、李建平（2022）。融合新聞影響力衰減的國際原油價格預測研究。系統工程理論與實踐，42（10）， 2710-2720。
Asimakopoulos, S., & Karavias, Y. (2016). The impact of government size on economic growth: A threshold analysis. Economics Letters, 139, 65-68.
Aziz, M. I. A., Barawi, M. H., & Shahiri, H. (2022). Is Facebook PROPHET Superior than Hybrid ARIMA Model to Forecast Crude Oil Price? [Article]. Sains Malaysiana, 51(8), 2633-2643. https://doi.org/10.17576/jsm-2022-5108-22.
Bai, Y., Li, X., Yu, H., & Jia, S. (2022). Crude oil price forecasting incorporating news text [Article]. International Journal of Forecasting, 38(1), 367-383，https://doi.org/10.1016/j.ijforecast.2021.06.006
Baumeister, J., & A. Leit˜ao. (2020). On iterative methods for solving ill-posed problems modeled by partial differential equations. arXiv: 2011.14441, Nov 2020.
Beckmann, J., Czudaj, R. L., & Arora, V. (2020). The relationship between oil prices and exchange rates: Revisiting theory and evidence. Energy Economics, 88, 104772.
Bello-Angulo, D., Mantilla-Duarte, C., Montes-Paez, E. and Guerrero-Martin, C. (2021), “Box-Jenkins Methodology Application to Improve Crude Oil Production Forecasting: Case Study in a Colombian Field”, Arabian Journal for Science and Engineering (2021). https://doi.org/10.1007/s13369-021-05997-7.
Ben Noble, James W. Daniel (2002). Applied Linear Algebra (3rd ed.). Pearson.
Borelli, M. (2023). Social media corporations as actors of counter-terrorism. New Media & Society, 25(11), 2877-2897.
Bowerman, B. L. and O’Connel, R. T. (1993), Forecasting and Time Series: An Applied Approach, 3rd Edition, CA: Duxbury Press.
Brana, S., & Prat, S. (2016). The effects of global excess liquidity on emerging stock market returns: Evidence from a panel threshold model. Economic Modelling, 52, 26-34.
Chang, T. H., Huang, C. M. & Lee, M. C. (2009). Threshold effect of the economic growth rate on the renewable energy development from a change in energy price: Evidence from OECD countries. Energy Policy, 37 (12), 5796-5802.
Cheikh, N. B., & Louhichi, W. (2016). Revisiting the role of inflation environment in exchange rate pass-through: A panel threshold approach. Economic Modelling, 52, 233-238.
Cheng, M. L., Chu, C. W., & Hsu, H. L. (2023). A study of univariate forecasting methods for crude oil price [Article]. Maritime Business Review, 8(1), 32-47. https://doi.org/10.1108/MABR-09-2021-0076。
Cristiane Aparecida Pendeza Martinez, Andre´ Lu´Is Machado Martinez, Glaucia Maria Bressan ∗ , Emerson Vitor Castelani And Roberto Molina De Souza. (2019). Multiple Solutions For A Fourth Order Equation With Nonlinear Boundary Conditions: Theoretical And Numerical Aspects. Differential Equations & Applications, Vol. 11, 335-348.
David Kincaid, Ward Cheney. (2002). Numerical Analysis: Mathematics of Scientific Computing (3rd ed.). American Mathematical Society.
David Poole. (2014). Linear Algebra: A Modern Introduction (4th ed.). Cengage Learning.
Ding, Y., He, D., Wu, J., & Xu, X. (2022). Crude Oil Spot Price Forecasting Using Ivanov-Based LASSO Vector Autoregression [Article]. Complexity, 2022, Article 5011174. https://doi.org/10.1155/2022/5011174.
Drachal, K. (2021), “Forecasting Crude Oil Real Prices with Averaging Time-Varying VAR Models”, Resources Policy, 74, Article 102244.
Drachal, K. (2023). Forecasting the Crude Oil Spot Price with Bayesian Symbolic Regression [Article]. Energies, 16(1), Article 4. https://doi.org/10.3390/en16010004。
Dritsaki, C., Niklis, D., & Stamatiou, P. (2021). Oil Consumption Forecasting Using ARIMA Models: An Empirical Study for Greece”, International Journal of Energy Economics and Policy, 11(4), 214-224.
Duan, H. and Liu, Y. (2021). Research on a Grey Prediction Model Based on Energy Prices and Its Applications. Computers & Industrial Engineering, 162, Article 107729.
Edward M. Landesman, Magnus R. Hestenes. (1991). Linear Algebra for Mathematics, Science, and Engineering. Pearson College Div
Erwin Kreyszig (1998). Advanced Engineering Mathematics (8th ed.). John Wiley & Sons.
Fang, Y., Wang, W., Wu, P., & Zhao, Y. (2023). A sentiment-enhanced hybrid model for crude oil price forecasting [Article]. Expert Systems with Applications, 215, Article 119329. https://doi.org/10.1016/j.eswa.2022.119329.
Gilbert Strang. (2006). Linear Algebra and Its Applications (4th ed.). Cengage Learning
Gong, X., Guan, K., & Chen, Q. (2022). The role of textual analysis in oil futures price forecasting based on machine learning approach [Article]. Journal of Futures Markets, 42(10), 1987-2017. https://doi.org/10.1002/fut.22367.
Gupta, N. and Nigam, S. (2020), “Crude Oil Price Prediction Using Artificial Neural Network”, Procedia Computer Science, 170, 642-647.
Hansen, B. E. (1999). Threshold effects in non-dynamic panels: Estimation, testing, and inference. Journal of Econometrics, 93(2), 345–368. https://doi.org/10.1016/S0304-4076(99)00025-1.
Hansen, B. E. (2000). Sample splitting and threshold estimation. Econometrica, 68(3), 575–603. https://doi.org/10.1111/1468-0262.00124.
Haque, M. I., & Shaik, A. R. (2021). Predicting crude oil prices during a pandemic: A comparison of arima and garch models [Article]. Montenegrin Journal of Economics, 17(1), 197-207. https://doi.org/10.14254/1800-5845/2021.17-1.15.
Herstein, I. N., & David, J. W. (1988). Matrix Theory and Linear Algebra. Macmillan Pub Co.
Howard Anton, Chris Rorres. (2005). Elementary Linear Algebra with Applications (9th ed.). Wiley, INC.
Hu, Z. (2021). Crude oil price prediction using CEEMDAN and LSTM-attention with news sentiment index [Article]. Oil and Gas Science and Technology, 76, Article 2021010. https://doi.org/10.2516/ogst/2021010.
Huang, B. N., Hwang, M. J., & Peng, H. P., 2005. The asymmetry of the impact of oil price shocks on economic activities: An application of the multivariate threshold model. Energy Economics, 27 (3), 455-476.
Huang, J., Chu, C. W., & Hsu, H. L. (2022). A Comparative Study of Univariate Models for Container Throughput Forecasting of Major Ports in Asia, Proceedings of the Institution of Mechanical Engineers Part M. Journal of Engineering for the Maritime Environment, 236 (1), 163-170.
Huang, J., Chu, C. W., & Tsai, Y. C. (2020). Container Throughput Forecasting for International Ports in Taiwan. Journal of Marine Science and Technology, 28 (5), 456-469.
International Energy Agency. (2021). Oil market report – December 2021. https://www.iea.org/reports/oil-market-report-december-2021.
International Energy Agency. (2022). Oil market report – May 2022. https://www.iea.org/reports/oil-market-report-may-2022.
International Monetary Fund. (2023). World economic outlook – October 2023: Commodity special feature. https://www.imf.org/-/media/Files/Publications/WEO/2023/October/English/commodityspecialfeature.ashx.
Jiang, H., Hu, W., Xiao, L., & Dong, Y. (2022). A decomposition ensemble based deep learning approach for crude oil price forecasting [Article]. Resources Policy, 78, Article 102855. https://doi.org/10.1016/j.resourpol.2022.102855.
Joshi, D. L., & Modi, D. K. (2024). Combine study of technical indicator Bollinger Bands and Moving Average Convergence Divergence in Nepal Stock Exchange Limited. International Research Journal of MMC, 5(3), 66–74. https://doi.org/10.3126/irjmmc.v5i3.68477.
Kim, B.H., Chun, S.E., & Min, H.G. (2009). Nonlinear dynamics in arbitrage of the S&P500 index and futures: A threshold error-correction model. Economic Modelling.
Liang, X., Luo, P., Li, X., Wang, X., & Shu, L. (2023). Crude oil price prediction using deep reinforcement learning [Article]. Resources Policy, 81, Article 103363. https://doi.org/10.1016/j.resourpol.2023.103363。
Lin Li, Ping Lin , Xinhui Si, & Liancun Zheng. (2017). A numerical study for multiple solutions of a singular boundary value problem arising from laminar flow in a porous pipe with moving wall. Journal of computational and applied mathematics, 313, 536-549.
Lin, H., & Sun, Q. (2020). Crude oil prices forecasting: An approach of using Ceemdan-based multi-layer gated recurrent unit networks [Article]. Energies, 13(7), Article 1543. https://doi.org/10.3390/en13071543.
Lin, Y., Xiao, Y. and Li, F. (2020). Forecasting Crude Oil Price Volatility via a HM-EGARCH Model. Energy Economics, 87, Article 104693.
Liu, J., & Huang, X. (2021). Forecasting Crude Oil Price Using Event Extraction [Article]. IEEE Access, 9, 149067-149076. https://doi.org/10.1109/ACCESS.2021.3124802。
Liu, W., Wang, C., Li, Y., Liu, Y., & Huang, K. (2021). Ensemble forecasting for product futures prices using variational mode decomposition and artificial neural networks. Chaos, Solitons & Fractals, 146, 110822.
Lu, Q., Li, Y., Chai, J., & Wang, S. (2020). Crude oil price analysis and forecasting: A perspective of “new triangle”. Energy Economics, 87, 104721.
Moodi, F., Jahangard-Rafsanjani, A., & Zarifzadeh, S. (2023). Feature selection and regression methods for stock price prediction using technical indicators. arXiv. https://arxiv.org/abs/2310.09903.
Norouzi, N. and Fani, M. (2020). Black Gold Falls, Black Plague Arise - An OPEC Crude Oil Price Forecast Using a Gray Prediction Model. Upstream Oil and Gas Technology, 5, Article 100015.
Pal, D., & Mitra, S. K. (2015). Asymmetric impact of crude price on oil product pricing in the United States: An application of multiple threshold nonlinear autoregressive distributed lag model. Economic Modelling, 51, 436-443.
Pour, M. M. A., Hajizadeh, E., & Farineya, P. (2022). A New Transformer-Based Hybrid Model for Forecasting Crude Oil Returns. AUT Journal of Modeling and Simulation, 54(1), 19-30. https://doi.org/10.22060/miscj.2022.20734.5263
Qin, Q., Huang, Z., Zhou, Z., Chen, C., & Liu, R. (2023). Crude oil price forecasting with machine learning and Google search data: An accuracy comparison of single-model versus multiple-model. Engineering Applications of Artificial Intelligence, 123, 106266.
Qin, X., Zhou, C., & Wu, C. (2016). Revisiting asymmetric price transmission in the U.S. oil-gasoline markets: A multiple threshold error-correction analysis. Economic Modelling, 52, 583-591.
R. Byron Bird, Warren E. Stewart, Edwin N. Lightfoot. (2001). Transport Phenomena (2nd ed.). Wiley.
Redha, R. A., & Yousif, S. A. (2023). Crude Oil Price Forecasts Using Support Vector Regression and Technical Indicators [Article]. Iraqi Journal of Science, 64(5), 2512-2520.
Richard L. Burden, J., & Douglas, F. (2010). Numerical Analysis (9th ed.). Cengage Learning.
Ron Larson, Robert P. Hostetler, & Bruce H. E. (1997). Calculus (6th ed.). Houghton Mifflin.
Salas, E. H., & Garrett Etgen. (1998) . Calculus (8th ed.). John Wiley & Sons, INC.
Sheng, Y., Zhang, J., Tan, W., Wu, J., Lin, H., & Sun, G. (2021). Application of Grey Forecasting Model to CPI Index Forecast. Advances in Artificial Intelligence and Security. ICAIS 2021. Communications in Computer and Information Science, 1423, 312-321
Stephen, H. F., Arnold, J. I., & Lawrence, E. S. (2002). Linear Algebra (4th ed.). Pearson.
Steven, J. L. (1911). Linear Algebra with Applications (7th ed.). Pearson College Div
Sun, J., Zhao, P., & Sun, S. (2022). A new secondary decomposition-reconstruction-ensemble approach for crude oil price forecasting [Article]. Resources Policy, 77, Article 102762.
Tong, H. (1978). On a threshold model. In C. H. Chen (Ed.), Pattern recognition and signal processing (pp. 575–586). Amsterdam: Sijthoff & Noordhoff.
Tong, H., & Lim, K. S. (1980). Threshold autoregression, limit cycles and cyclical data. Journal of the Royal Statistical Society: Series B (Methodological), 42(3), 245–292.
Tsagkanos, A., & Siriopoulo, C. (2015). Stock markets and industrial production in north and south of Euro-zone: Asymmetric effects via threshold cointegration approach. The Journal of Economic Asymmetries, 12 (2), 162-172.
Tsay, R. S. (1998). Testing and Modeling Multivariate Threshold Models. Journal of the American Statistical Association, 93 (443), 1188–1202.
Tse & Chan.(2010). The Lead-Lag relation between the S&P500 spot and futures markets : and intraday-data analysis using a threshold regression model. The Japanese Economic Review.
U.S. Energy Information Administration. (2022). Crude oil prices increased in 2021 as global crude oil demand outpaced supply. https://www.eia.gov/todayinenergy/detail.php?id=50738.
Wang, Z. X., He, L. Y. and Zhao, Y. F. (2021) “Forecasting the Seasonal Natural Gas Consumption in the US Using a Gray Model with Dummy Variables”, Applied Soft Computing, 113, Article 108002.
World Bank. (2023). Commodity markets outlook – October 2023. https://openknowledge.worldbank.org/server/api/core/bitstreams/27189ca2-d947-4ca2-8e3f-a36b3b5bf4ba/conten.
Wu, B., Wang, L., Lv, S. X., & Zeng, Y. R. (2021). Effective crude oil price forecasting using new text-based and big-data-driven model [Article]. Measurement: Journal of the International Measurement Confederation, 168, Article 108468. https://doi.org/10.1016/j.measurement.2020.108468。
Wu, J., Dong, J., Wang, Z., Hu, Y., & Dou, W. (2023). A novel hybrid model based on deep learning and error correction for crude oil futures prices forecast. Resources Policy, 83, 103602.
Xian, L., He, K., Wang, C., & Lai, K. K. (2020). Factor analysis of financial time series using EEMD-ICA based approach. Sustainable Futures, 2, 100003.
Xu, K., & Niu, H. (2022). Do EEMD based decomposition-ensemble models indeed improve prediction for crude oil futures prices? Technological Forecasting and Social Change, 184, 121967.
Xu, K., & Wang, W. (2023). Limited information limits accuracy: Whether ensemble empirical mode decomposition improves crude oil spot price prediction? [Article]. International Review of Financial Analysis, 87, Article 102625.
Xu, Y. and Lien, D. (2021). Forecasting Volatilities of Oil and Gas Assets: A Comparison of GAS, GARCH, and EGARCH Models. Journal of Forecasting, https://doi.org/10.1002/for.2812.
Xue, J., Ding, J., Zhao, L., Zhu, D. and Li, L. (2022). An Option Pricing Model Based on a Renewable Energy Price index”, Energy, 239, part B, Article 122117.
Yao, T. and Wang, Z. (2021). Crude Oil Price Prediction Based on LSTM Network and GM (1,1) Model. Grey Systems: Theory and Application, 11 (1), 80-94.
Yu, F., Liu, Y. and Zhang, C. (2021). Forecasting the Price of Fuel Oil: A STL(ELM+ARIMA) Combination Approach. Journal of Physics: Conference Series, 1903, Article 012048.
Zhao, G., Xue, M., & Cheng, L. (2023). A new hybrid model for multi-step WTI futures price forecasting based on self-attention mechanism and spatial–temporal graph neural network. Resources Policy, 85, 103956.
Zhe, J., Lin, Z., Lingling, Z., & Bo, W. (2022). Investor sentiment and machine learning: Predicting the price of China's crude oil futures market [Article]. Energy, 247, Article 123471. https://doi.org/10.1016/j.energy.2022.123471。
Zhu, H. M., Li, S. H., & Yu, K., 2011. Crude oil shocks and stock markets: A panel threshold cointegration approach. Energy Economics, 33 (5), 987-994.
Zohreh Ranjbar. (2010). Numerical Solution of Ill-posed Cauchy Problems for Parabolic Equations. Linköping Studies in Science and Technology. Dissertations, 1300. |
| Description: | 碩士
國立政治大學
應用數學系
108751013 |
| Source URI: | http://thesis.lib.nccu.edu.tw/record/#G0108751013 |
| Data Type: | thesis |
| Appears in Collections: | [應用數學系] 學位論文
|
Files in This Item:
| File |
Description |
Size | Format | |
|---|
| 101301.pdf | | 1932Kb | Adobe PDF | 0 | View/Open |
|
All items in 政大典藏 are protected by copyright, with all rights reserved.
|
