請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/88381完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 吳家麟 | zh_TW |
| dc.contributor.advisor | Ja-Ling Wu | en |
| dc.contributor.author | 黃建豪 | zh_TW |
| dc.contributor.author | Chien-Hao Huang | en |
| dc.date.accessioned | 2023-08-09T16:48:37Z | - |
| dc.date.available | 2023-11-09 | - |
| dc.date.copyright | 2023-08-09 | - |
| dc.date.issued | 2023 | - |
| dc.date.submitted | 2023-07-26 | - |
| dc.identifier.citation | Dimitriadou A, Gregoriou A. Predicting Bitcoin Prices Using Machine Learning. Entropy. 2023 May 10;25(5):777.
Uras N, Marchesi L, Marchesi M, Tonelli R. Forecasting Bitcoin closing price series using linear regression and neural networks models. PeerJ Computer Science. 2020 Jul 6;6:e279. Greff K, Srivastava RK, Koutník J, Steunebrink BR, Schmidhuber J. LSTM: A search space odyssey. IEEE transactions on neural networks and learning systems. 2016 Jul 8;28(10):2222-32. Zeng A, Chen M, Zhang L, Xu Q. Are transformers effective for time series forecasting?. arXiv preprint arXiv:2205.13504. 2022 May 26. Liu Y, Wu H, Wang J, Long M. Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting. InAdvances in Neural Information Processing Systems 2022. Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I. Attention is all you need. Advances in neural information processing systems. 2017;30. Wu H, Xu J, Wang J, Long M. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. Advances in Neural Information Processing Systems. 2021 Dec 6;34:22419-30. Zhou H, Zhang S, Peng J, Zhang S, Li J, Xiong H, Zhang W. Informer: Beyond efficient transformer for long sequence time-series forecasting. InProceedings of the AAAI conference on artificial intelligence 2021 May 18 (Vol. 35, No. 12, pp. 11106-11115). Charandabi SE, Kamyar K. Prediction of cryptocurrency price index using artificial neural networks: a survey of the literature. European Journal of Business and Management Research. 2021 Nov 9;6(6):17-20. Khedr AM, Arif I, El‐Bannany M, Alhashmi SM, Sreedharan M. Cryptocurrency price prediction using traditional statistical and machine‐learning techniques: A survey. Intelligent Systems in Accounting, Finance and Management. 2021 Jan;28(1):3-4. Sridhar S, Sanagavarapu S. Multi-head self-attention transformer for dogecoin price prediction. In2021 14th International Conference on Human System Interaction (HSI) 2021 Jul 8 (pp. 1-6). IEEE. Velankar S, Valecha S, Maji S. Bitcoin price prediction using machine learning. In2018 20th International Conference on Advanced Communication Technology (ICACT) 2018 Feb 11 (pp. 144-147). IEEE. Rathan K, Sai SV, Manikanta TS. Crypto-currency price prediction using decision tree and regression techniques. In2019 3rd International Conference on Trends in Electronics and Informatics (ICOEI) 2019 Apr 23 (pp. 190-194). IEEE. Li C, Qian G. Stock Price Prediction Using a Frequency Decomposition Based GRU Transformer Neural Network. Applied Sciences. 2022 Dec 24;13(1):222. Yang L, Li J, Dong R, Zhang Y, Smyth B. NumHTML: Numeric-Oriented Hierarchical Transformer Model for Multi-task Financial Forecasting. InProceedings of the AAAI Conference on Artificial Intelligence 2022 Jun 28 (Vol. 36, No. 10, pp. 11604-11612). Hu X. Stock price prediction based on temporal fusion transformer. In2021 3rd International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI) 2021 Dec 3 (pp. 60-66). IEEE. Muhammad T, Aftab AB, Ahsan M, Muhu MM, Ibrahim M, Khan SI, Alam MS. Transformer-Based Deep Learning Model for Stock Price Prediction: A Case Study on Bangladesh Stock Market. arXiv preprint arXiv:2208.08300. 2022 Aug 17. Ko CR, Chang HT. LSTM-based sentiment analysis for stock price forecast. PeerJ Computer Science. 2021 Mar 11;7:e408. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/88381 | - |
| dc.description.abstract | 在本研究中，我們使用訓練管道增強 (TPE) 方法以增強基於 Transformer 的加密貨幣價格預測模型。 我們提出了三種訓練管道增強機制：零偏移、時間序列加權和多符號迭代訓練。 並且，我們在加密市場數據集（包括比特幣、以太坊和幣安幣）上對這些機制進行定量評估，以證明它們在提高性能方面的有效性。此外，我們將討論每種機制結果的潛在原因。 | zh_TW |
| dc.description.abstract | In this study, we enhance transformer-based models for crypto price forecasting using Training Pipeline Enhancement (TPE) methods. We propose three Training Pipeline Enhancement mechanisms: Zero Shift, Time Series Weighting, and Multi-symbol Iteration Training. We also quantitatively evaluate these mechanisms on crypto market datasets, including Bitcoin, Ethereum, and Binance Coin, to demonstrate their effectiveness in enhancing performance. Furthermore, we will discuss the potential reasons for the results obtained from each mechanism. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2023-08-09T16:48:37Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2023-08-09T16:48:37Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 致謝 i
摘要 ii Abstract iii Contents iv List of Figures vi List of Tables viii 1 Introduction 1 1.1 Crypto Price Forecasting 2 1.2 Transformer Model 2 1.3 Training Pipeline Enhancement (TPE) 3 2 Experiment Setting 4 2.1 Selection of Transformer-based Models 4 2.2 Selection of Datasets 5 2.3 Selection of Hyperparameters 6 2.4 Selection of Metrics 7 2.5 Construction of Benchmark 8 3 The 3 Enhancement Methods 9 3.1 Mechanism 1: The Zero Shift 9 3.1.1 The Mechanism 9 3.1.2 Experimental Results Associated with the Zero-Shift Mechanism 12 3.1.3 Discussion 13 3.2 Mechanism 2: Time Series Weighting 15 3.2.1 The Mechanism 15 3.2.2 Experimental Results Associated with the Time Series Weighting Mechanism 17 3.2.3 Discussion 19 3.3 Mechanism 3: Multi-symbol Iteration Training 20 3.3.1 The Mechanism 20 3.3.2 Three Versions of the Multi-symbol Iteration Training Mechanism 20 3.3.3 Results and Discussions 24 4 Conclusion and Future Work 27 References 28 | - |
| dc.language.iso | en | - |
| dc.title | 基於 Transformer 模型在預測加密貨幣價格的訓練管道增強：一項實證研究 | zh_TW |
| dc.title | Training Pipeline Enhancements for Transformer-Based Models in Forecasting Crypto Prices: An Empirical Study | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 111-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 陳文進;許超雲 | zh_TW |
| dc.contributor.oralexamcommittee | Wen-Chin Chen;Chau-Yun Hsu | en |
| dc.subject.keyword | 加密貨幣,價格預測,時間序列預測,訓練管道增強,Transformer模型, | zh_TW |
| dc.subject.keyword | Cryptocurrency,Price prediction,Time Series Forecasting,Training Pipeline Enhancement,Transformer model, | en |
| dc.relation.page | 29 | - |
| dc.identifier.doi | 10.6342/NTU202302107 | - |
| dc.rights.note | 未授權 | - |
| dc.date.accepted | 2023-07-28 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 資訊工程學系 | - |
| 顯示於系所單位： | 資訊工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-111-2.pdf 目前未授權公開取用 | 1.28 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。