請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/99747完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 李家岩 | zh_TW |
| dc.contributor.advisor | Chia-Yen Lee | en |
| dc.contributor.author | 陳祖譽 | zh_TW |
| dc.contributor.author | Welbey Prasadirta | en |
| dc.date.accessioned | 2025-09-17T16:33:50Z | - |
| dc.date.available | 2025-09-18 | - |
| dc.date.copyright | 2025-09-17 | - |
| dc.date.issued | 2025 | - |
| dc.date.submitted | 2025-08-05 | - |
| dc.identifier.citation | Adesi, B. G., Finta, M. A., Legnazzi, C., and Sala, C. (2019). WTI crude oil option implied VaR and CVaR: An empirical application. Journal of Forecasting, 38(6): 552–563.
Akil, S., Sekkate, S., and Adib, A. (2024). Multimodal deep learning for oil price forecasting using economic indicators. Procedia Computer Science, 236: 402–409. Aldabagh, H., Zheng, X., Najand, M., and Mukkamala, R. (2024). Forecasting crude oil price using multiple factors. Journal of Risk and Financial Management, 17(9): 415. Anderson, L. B., Kanneganti, D., Houk, M. B., Holm, R. H., and Smith, T. (2023). Generative AI as a tool for environmental health research translation. GeoHealth, 7(7). Bagirov, M., and Mateus, C. (2025). Analyzing intraday volatility spillovers between oil prices and stock sectors. FEB-RN Research Paper, 50. Bai, Y., Li, X., Yu, H., and Jia, S. (2022). Crude oil price forecasting incorporating news text. International Journal of Forecasting, 38(1): 367–383. Bilal, M., Aamir, M., Abdullah, S., and Khan, F. (2024). Impacts of crude oil market on global economy: Evidence from the Ukraine-Russia conflict via fuzzy models. Heliyon, 10(3): e23874. Cao, Y., Lan, Y., Zhai, F., and Li, P. (2024). 5W1H extraction with large language models. Chen, P., Boukouvalas, Z., and Corizzo, R. (2024). A deep fusion model for stock market prediction with news headlines and time series data. Neural Computing and Applications, 36: 21229-21271. Chen, R., Deng, T., Huang, S., and Qin, R. (2015). Optimal crude oil procurement under fluctuating price in an oil refinery. European Journal of Operational Research, 245(2): 438–445. Chen, Y., He, K., and Tso, G. K. F. (2017). Forecasting crude oil prices: a deep learning -based model. Procedia Computer Science, 122: 300–307. Coronado, S., Jiménez-Rodríguez, R., and Rojas, O. (2018). An empirical analysis of the relationships between crude oil, gold and stock markets. The Energy Journal, 39(1): 193-208. Cui, Z., Li, T., Ding, Z., Li, X., and Wu, J. (2024). Probabilistic oil price forecasting with a variational mode decomposition-gated recurrent unit model incorporating pinball loss. Data Science and Management. Daneshvar, A., Ebrahimi, M., Salahi, F., Rahmaty, M., and Homayounfar, M. (2022). Brent crude oil price forecast utilizing deep neural network architectures. Computational Intelligence and Neuroscience, 2022(28): 1-13. Ding, L., Zhao, H., and Zhang, R. (2024). Predicting multi-frequency crude oil price dynamics: Based on MIDAS and STL methods. Energy, 313: 134003. Ding, Z., Smith-Renner, A., Zhang, W., Tetreault, J. R., and Jaimes, A. (2023). Harnessing the power of LLMs: Evaluating human-AI text co-creation through the lens of news headline generation. Elshendy, M., Fronzetti Colladon, A., Battistoni, E., and Gloor, P. A. (2018). Using four different online media sources to forecast the crude oil price. Journal of Information Science, 44(3): 408–421. Fan, Y., Liang, Q., and Wei, Y. M. (2008). A generalized pattern matching approach for multi-step prediction of crude oil price. Energy Economics, 30(3): 889–904. Fang, T., Zheng, C., and Wang, D. (2023). Forecasting the crude oil prices with an EMD-ISBM-FNN model. Energy, 263: 125407. Fang, Y., Wang, W., Wu, P., and Zhao, Y. (2023). A sentiment-enhanced hybrid model for crude oil price forecasting. Expert Systems with Applications, 215: 119329. García, J. S., and Rambaud, S. C. (2023). Volatility spillovers between oil and financial markets during economic and financial crises: A dynamic approach. Journal of Economics and Finance, 47(4): 1018–1040. Gasper, L., and Mbwambo, H. (2023). Forecasting crude oil prices by using ARIMA model: Evidence from Tanzania. Journal of Accounting Finance and Auditing Studies (JAFAS), 9(2). Ge, R. (2025). The research on factors influencing the global price of crude oil. Theoretical and Natural Science, 105(1): 8-14. Genc, T. S. (2017). The impact of lead time on capital investments. Journal of Economic Dynamics and Control, 82: 142–164. Giray, L. (2023). Prompt engineering with ChatGPT: A guide for academic writers. Annals of Biomedical Engineering, 51(2): 2629–2633. Guan, B., Mazouz, K., and Xu, Y. (2024). Asymmetric volatility spillover between crude oil and other asset markets. Energy Economics, 130: 107305. Han, L. J. (2025). Announcements, expectations, and stock returns with asymmetric information. Journal of Monetary Economics, 151: 103751. Han, P., Chen, H., Rasool, A., Jiang, Q., and Yang, M. (2025). MFB: A generalized multimodal fusion approach for bitcoin price prediction using time-lagged sentiment and indicator features. Expert Systems with Applications, 261: 125515. He, X. J. (2018). Crude oil prices forecasting: time series vs. SVR models. Journal of International Technology and Information Management, 27(2): 25–42. Huang, L., Yang, X., Lai, Y., Zou, A., and Zhang, J. (2024). Crude oil futures price forecasting based on variational and empirical mode decompositions and transformer model. Mathematics, 12(24): 4034. Huang, Y., and Deng, Y. (2021). A new crude oil price forecasting model based on variational mode decomposition. Knowledge-Based Systems, 213: 106669. Jiang, Y., Ning, K., Pan, Z., Shen, X., Ni, J., Yu, W., Schneider, A., Chen, H., Nevmyvaka, Y., and Song, D. (2025). Multi-modal time series analysis: A tutorial and survey. Jin, B., and Xu, X. (2024). Price forecasting through neural networks for crude oil, heating oil, and natural gas. Measurement: Energy, 1: 100001. Kakade, K. A., Ghate, K. S., Jaiswal, R. K., and Jaiswal, R. (2023). A novel approach to forecast crude oil prices using machine learning and technical indicators. Journal of Advances in Information Technology, 14(2): 302–310. Kaplan, H., Mundani, R.-P., Rölke, H., and Weichselbraun, A. (2023). CrudeBERT: Applying economic theory towards fine-tuning transformer-based sentiment analysis models to the crude oil market. Kathiravan, M., S, A. S., Frederick Fernandez, T., Mohan, A., Vijayakumar, M., and Manikandan, M. (2024). PREDMAC a stochastic Monte Carlo-driven predictive analytics framework integrating regression modelling for macroeconomic factor evaluation and forecasting of WTI crude oil price volatility. Journal of Information Systems Engineering and Management, 10 (34s). Kilian, L., and Zhou, X. (2020). The econometrics of oil market VAR models. Federal Reserve Bank of Dallas, Working Papers, 2020(2006). Kohlscheen, E. (2022). Quantifying the role of interest rates, the Dollar and Covid in oil prices. Kohlscheen, E. (2024). Forecasting oil prices with random forests. Empirical Economics, 66(2): 927–943. Lee, C. Y., Chou, B. J., and Huang, C. F. (2022). Data science and reinforcement learning for price forecasting and raw material procurement in petrochemical industry. Advanced Engineering Informatics, 51: 101443. Lee, C. Y., and Yang, S. H. (2023). Graph spatio-temporal networks for manufacturing sales forecast and prevention policies in pandemic era. Computers & Industrial Engineering, 182: 109413. Li, M. (2024). Prediction of the West Texas Intermediate crude oil price Using ARIMA model and ARIMA-GARCH model. Proceedings of the 1st International Conference on Innovations in Applied Mathematics, Physics and Astronomy, 1: 110– 118. Li, X., Shang, W., and Wang, S. (2019). Text-based crude oil price forecasting: A deep learning approach. International Journal of Forecasting, 35(4): 1548–1560. Li, Y., Jiang, S., Li, X., and Wang, S. (2021). The role of news sentiment in oil futures returns and volatility forecasting: Data-decomposition based deep learning approach. Energy Economics, 95: 105140. Lim, B., Arık, S., Loeff, N., and Pfister, T. (2021). Temporal fusion transformers for interpretable multi-horizon time series forecasting. International Journal of Forecasting, 37(4): 1748–1764. Lin, Y., Chen, K., Zhang, X., Tan, B., and Lu, Q. (2022). Forecasting crude oil futures prices using BiLSTM-Attention-CNN model with Wavelet transform. Applied Soft Computing, 130: 109723. Liu, J., and Huang, X. (2021). Forecasting crude oil price using event extraction. IEEE Access, 9: 149067-149076. Liu, Z., Huang, D., Huang, K., Li, Z., and Zhao, J. (2020). FinBERT: A pre-trained financial language representation model for financial text mining. Lu, H. W., and Lee, C. Y. (2022). Kernel-based dynamic ensemble technique for remaining useful life prediction. IEEE Robotics and Automation Letters, 7(2): 1142–1149. Lu, Q. (2024). Research on the relationship between global oil prices and economic indicators based on linear regression and ARIMAX models. Theoretical and Natural Science, 38(1): 133–139. Meghanadh, B., Aravalath, L., Joshi, B., Sathiamoorthy, R., and Kumar, M. (2019). Imputation of missing values in the fundamental data: Using MICE framework. Journal of Quantitative Economics, 17(3), 459–475. Ng’ang’a, F. W., and Oleche, M. (2022). Modelling and forecasting of crude oil price volatility comparative analysis of volatility models. Journal of Financial Risk Management, 11(01): 154–187. Ouyang, S., Zhang, J. M., Harman, M., and Wang, M. (2023). An empirical study of the non-determinism of ChatGPT in code generation. Patidar, A. K., Jain, P., Dhasmana, P., and Choudhury, T. (2024). Impact of global events on crude oil economy: a comprehensive review of the geopolitics of energy and economic polarization. GeoJournal, 89(2). Pei, Y., Cartlidge, J., Mandal, A., Gold, D., Marcilio, E., and Mazzon, R. (2025). Cross-modal temporal fusion for financial market forecasting. Selmi, R., Hammoudeh, S., and Wohar, M. E. (2023). What drives most jumps in global crude oil prices? Fundamental shortage conditions, cartel, geopolitics or the behavior of financial market participants. World Economy, 46(3): 598–618. Shabri, A., and Samsudin, R. (2014). Daily crude oil price forecasting using hybridizing wavelet and artificial neural network model. Mathematical Problems in Engineering, 2014: 1-10. Shao, H., and Li, Z. (2025). The predictive effect of heterogeneous investor behavior on commodity pricing. Humanities and Social Sciences Communications, 12: 490. Shao, H.-L., Shao, Y.-H., and Yang, Y.-H. (2021). New insights into price drivers of crude oil futures markets: Evidence from quantile ARDL approach. Shi, T., Kang, K., Choo, J., and Reddy, C. K. (2018). Short-text topic modeling via non-negative matrix factorization enriched with local word-context correlations. The Web Conference 2018 - Proceedings of the World Wide Web Conference, 2018: 1105–1114. Tsay, R. S. (2010). Analysis of financial time series (3rd ed.). John Wiley & Sons. Tuarob, S., Wettayakorn, P., Phetchai, P., Traivijitkhun, S., Lim, S., Noraset, T., and Thaipisutikul, T. (2021). DAViS: a unified solution for data collection, analyzation, and visualization in real-time stock market prediction. Financial Innovation, 7(1). Vizitiu, D., Alkazaz, S., and Servi, P. (2025). Return and volatility dynamics across asset classes: Constructing a portfolio to maximize risk-adjusted returns. Wang, H., Xie, Z., Chiu, D. K. W., and Ho, K. K. W. (2025). Multimodal market information fusion for stock price trend prediction in the pharmaceutical sector: Multimodal market information fusion for stock price trend prediction in the pharmaceutical sector. Applied Intelligence, 55(1). Wang, J., and Wang, J. (2021). A new hybrid forecasting model based on SW-LSTM and Wavelet Packet Decomposition: A case study of oil futures prices. Computational Intelligence and Neuroscience, 2021(1): 1-22. Wang, M., Cohen, S. B., and Ma, T. (2024). Modeling News Interactions and Influence for Financial Market Prediction. Wei, X., Cui, X., Cheng, N., Wang, X., Zhang, X., Huang, S., Xie, P., Xu, J., Chen, Y., Zhang, M., Jiang, Y., and Han, W. (2023). ChatIE: Zero-shot information extraction via chatting with ChatGPT. Windsor, E., and Cao, W. (2022). Improving exchange rate forecasting via a new deep multimodal fusion model. Applied Intelligence, 52(14): 16701–16717. Wu, B., Wang, L., Lv, S. X., and Zeng, Y. R. (2021). Effective crude oil price forecasting using new text-based and big-data-driven model. Measurement: Journal of the International Measurement Confederation, 168: 108468. Wu, W., Zhang, G., Tan, Z., Wang, Y., and Qi, H. (2025). Dual-forecaster: A multimodal time series model integrating descriptive and predictive texts. Xiang, Y. (2022). Using ARIMA-GARCH model to analyze fluctuation law of international oil price. Mathematical Problems in Engineering, 2022(11). Yu, Y., Si, X., Hu, C., and Zhang, J. (2019). A review of recurrent neural networks: LSTM cells and network architectures. Neural Computation, 31(7): 1235–1270. Zabelle, T. (2017). Consequence of Lead Time on Capital Project Outcomes. Zhang, K., and Hong, M. (2022). Forecasting crude oil price using LSTM neural networks. Data Science in Finance and Economics, 2(3): 163–180. Zhang, Y.-J., and Zhang, H. (2023). Volatility forecasting of crude oil market: Which structural change based GARCH models have better performance? The Energy Journal, 44(1): 175–194. Zhao, J. (2022). Exploring the influence of the main factors on the crude oil price volatility: An analysis based on GARCH-MIDAS model with Lasso approach. Resources Policy, 79: 103031. Zhao, L. T., Xing, Y. Y., Zhao, Q. R., and Chen, X. H. (2023). Dynamic impacts of online investor sentiment on international crude oil prices. Resources Policy, 82: 103506. Zhao, Y., Huang, Y., Wang, Z., and Liu, X. (2024). A new feature selection method based on importance measures for crude oil return forecasting. Neurocomputing, 581: 127470. Zhao, Z., Sun, S., Sun, J., and Wang, S. (2024). A novel hybrid model with two-layer multivariate decomposition for crude oil price forecasting. Energy, 288(6): 129740. Zheng, G., Li, Y., and Xia, Y. (2025). Crude oil price forecasting model based on neural networks and error correction. Applied Sciences (Switzerland), 15(3): 1055. Zou, Y., Yu, L., and He, K. (2023). Forecasting crude oil risk: A multiscale bidirectional generative adversarial network-based approach. Expert Systems with Applications, 212: 118743. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/99747 | - |
| dc.description.abstract | 原油市場是全球最具波動性且最具影響力的市場之一，其變動受到市場供需動態、宏觀經濟變化及地緣政治事件等複雜因素的交互影響。本研究提出一個多模態深度學習框架，透過整合結構化的數值指標與非結構化的文本特徵，預測原油價格。以西德州中級原油（WTI）即期價格為預測目標，模型結合了9,000多項與商品和宏觀經濟相關的變數，並輔以來自金融新聞的增強文本特徵。為克服新聞標題篇幅短且語意模糊的限制，本研究採用基於GPT的提示工程技術生成具情境感知摘要，並以FinBERT嵌入向量進行編碼。該框架將WTI價格序列分解為趨勢、季節性與殘差三個成分，並分別使用長短期記憶網路（LSTM）進行建模。研究進一步實作並比較三種模態融合策略—早期、中期與後期融合，以找出整合不同資料類型的最佳時機。自訂的混合損失函數則同時考慮預測誤差與價格走勢方向的準確性，以提升對趨勢變化的靈敏度。模型能預測未來最多八週的油價變化，為能源採購與金融風險管理提供決策支援。透過同時運用量化訊號與事件驅動的情緒資訊，本研究提供一個穩健、可解釋且自適應的解決方案，以因應原油市場的高度複雜性。 | zh_TW |
| dc.description.abstract | Crude oil markets are among the most volatile and globally influential, shaped by complex interactions between supply-demand dynamics, macroeconomic shifts, and geopolitical events. This study develops a multimodal deep-learning framework to forecast crude oil prices by integrating structured numerical indicators with unstructured textual features. Using the West Texas Intermediate (WTI) spot price as the target, the model combines over 9,000 commodity-related and macroeconomic variables with enriched textual features derived from financial news. To address the limitations of short and ambiguous headlines, the study employs GPT-based prompt engineering to generate context-aware summaries and encodes them using FinBERT embeddings. The framework decomposes the WTI price series into trend, seasonal, and residual components, modeling each separately with Long Short-Term Memory (LSTM) networks. It implements and compares three fusion strategies (early, intermediate, and late) to determine the optimal stage for modality integration. A hybrid loss function combines prediction error with directional accuracy to enhance trend sensitivity. The model forecasts oil prices up to eight weeks in advance, supporting informed decisions in energy procurement and financial risk management. By jointly leveraging quantitative signals and event-driven sentiment, this study presents a robust, interpretable, and adaptive solution for navigating the complexities of the oil market. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2025-09-17T16:33:50Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2025-09-17T16:33:50Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | Acknowledgment i
摘要 iv Abstract v Contents vi List of Figures ix List of Tables x 1 Introduction 1 1.1 Background and Motivation 1 1.1.1 Background 1 1.1.2 Motivation 6 1.2 Research Objectives 10 1.3 Research Plan 12 2 Literature Review 13 2.1 Overview of Forecasting Methods for Crude Oil Prices 13 2.1.1 Signal Decomposition Models 13 2.1.2 Time-Series Models 16 2.1.3 Structural Models 17 2.2 Overview of Multimodal Fusion for Financial Forecasting 22 2.3 Overview of Generative AI for Enhancing Textual Features 24 2.4 Summary and Discussion 26 3 Methodology 27 3.1 Data Collection 30 3.2 Text Feature Generation 32 3.3 Data Preprocessing 34 3.3.1 Data Cleaning and Transformation 34 3.3.2 Additive Time Series Decomposition 34 3.3.3 Augmented Dickey-Fuller Stationary Test 35 3.3.4 Granger Causality Test 36 3.3.5 Text Cleaning 38 3.3.6 CrudeBERT Sentiment Analysis 38 3.3.7 News Selection 40 3.3.8 FinBERT Word Embedding and Sentence Embedding 41 3.4 Multimodal Fusion and Multi-Step Forecasting 42 3.4.1 Sliding Window 42 3.4.2 Time Series Cross Validation 43 3.4.3 Hybrid Loss Function 44 3.4.4 Multimodal Fusion Strategy 47 3.4.5 LSTM Architecture for Sequential Forecasting 54 3.4.6 Model Evaluation 55 4 Experiment and Results 57 4.1 Results and Discussion of Prompt-Based Feature Generation 57 4.2 Analysis of Price Decomposition Components 59 4.3 Stationary Test Results via Augmented Dickey-Fuller (ADF) 60 4.4 Analysis of Granger-Based Selected Features 61 4.5 Comparison with Topic-Sentiment-Based Early Fusion Baseline 63 4.6 Comparison Across Original and GPT-Generated Textual Features 66 4.7 Comparison of Modality and Fusion Strategies 68 5 Conclusion and Future Works 84 5.1 Conclusion 84 5.2 Future Works 86 Bibliography 88 Appendix 98 A. Additional Results for the Best Baseline and Fusion Strategies 98 B. Forecasting Results Across All Baseline and Fusion Strategies 101 | - |
| dc.language.iso | en | - |
| dc.subject | 原油價格預測 | zh_TW |
| dc.subject | 多模態融合 | zh_TW |
| dc.subject | 宏觀經濟指標 | zh_TW |
| dc.subject | 金融新聞情緒 | zh_TW |
| dc.subject | 長短期記憶網路（LSTM） | zh_TW |
| dc.subject | 生成式人工智慧 | zh_TW |
| dc.subject | Macroeconomic Indicators | en |
| dc.subject | Crude Oil Price Forecasting | en |
| dc.subject | Generative AI | en |
| dc.subject | Long Short-Term Memory (LSTM) | en |
| dc.subject | Financial News Sentiment | en |
| dc.subject | Multimodal Fusion | en |
| dc.title | 融合新聞特徵與總體經濟指標於多模態原油價格預測 | zh_TW |
| dc.title | Multimodal Fusion for Crude Oil Price Forecasting with News Features and Macroeconomic Indicators | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 113-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 孫紹華;陳以錚;陳建錦 | zh_TW |
| dc.contributor.oralexamcommittee | Shao-Hua Sun;Yi-Cheng Chen;Chien-Chin Chen | en |
| dc.subject.keyword | 原油價格預測,多模態融合,宏觀經濟指標,金融新聞情緒,長短期記憶網路（LSTM）,生成式人工智慧, | zh_TW |
| dc.subject.keyword | Crude Oil Price Forecasting,Multimodal Fusion,Macroeconomic Indicators,Financial News Sentiment,Long Short-Term Memory (LSTM),Generative AI, | en |
| dc.relation.page | 104 | - |
| dc.identifier.doi | 10.6342/NTU202503225 | - |
| dc.rights.note | 同意授權(全球公開) | - |
| dc.date.accepted | 2025-08-08 | - |
| dc.contributor.author-college | 管理學院 | - |
| dc.contributor.author-dept | 資訊管理學系 | - |
| dc.date.embargo-lift | 2027-08-31 | - |
| 顯示於系所單位： | 資訊管理學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-113-2.pdf 此日期後於網路公開 2027-08-31 | 3.72 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。