| dc.contributor | 資科系 | |
| dc.creator (作者) | 黃瀚萱 | |
| dc.creator (作者) | Huang, Hen-Hsen | |
| dc.date (日期) | 2020-04 | |
| dc.date.accessioned | 4-六月-2021 14:38:45 (UTC+8) | - |
| dc.date.available | 4-六月-2021 14:38:45 (UTC+8) | - |
| dc.date.issued (上傳時間) | 4-六月-2021 14:38:45 (UTC+8) | - |
| dc.identifier.uri (URI) | http://nccur.lib.nccu.edu.tw/handle/140.119/135521 | - |
| dc.description.abstract (摘要) | Risk is an important component when constructing a trading strategy. However, most of the previous works that make the price movement prediction on the basis of the opinions on social media platforms do not take the risk into consideration. In order to hedge the market-risk, we propose an idea of an opinion-based pair trading strategy. Comparing with the task setting of the previous works, our experimental results show that the neural network models with the pair-wise task setting perform better in both accuracy and profitability metrics. That introduces a new research direction for future researches on opinion-based price movement predictions. | |
| dc.format.extent | 743849 bytes | - |
| dc.format.mimetype | application/pdf | - |
| dc.relation (關聯) | WWW `20: Companion Proceedings of the Web Conference 2020, Association for Computing Machinery, pp.69-70 | |
| dc.subject (關鍵詞) | Pair trading ; financial social media ; text mining | |
| dc.title (題名) | Hedging via Opinion-based Pair Trading Strategy | |
| dc.type (資料類型) | conference | |
| dc.identifier.doi (DOI) | 10.1145/3366424.3382701 | |
| dc.doi.uri (DOI) | https://doi.org/10.1145/3366424.3382701 | |
