學術產出-Theses
Article View/Open
Publication Export
-
題名 建構動態時間校正與聚類分析的選股模型實證研究
An Empirical Study of Stock Selection Strategies on Dynamic Time Warping and Cluster Analysis作者 曾子軒
Tseng, Tzu-Hsuan貢獻者 廖四郎
Liao, Szu-Lang
曾子軒
Tseng, Tzu-Hsuan關鍵詞 動態時間校正
聚類分析
Dynamic time warping
K-medoids
Fuzzy c-medoids
Dynamic time warping
Cluster analysis
K-medoids
Fuzzy c-medoids日期 2022 上傳時間 1-Aug-2022 17:29:38 (UTC+8) 摘要 本文探討動態時間校正及聚類分析應用於台灣股票市場之實證研究。目前相關的分類機器學習模型用於股票市場的文獻,大多以預測報酬率為基礎,輔以使用財務資料或技術指標而成,為了要將報酬率分類,必須定義標籤類別,使得我們必須主觀界定各個報酬率類別的邊界。再者,相似報酬率的股票對應的財務資料或技術指標,往往在時間上有領先或落後,導致在區分股票標的相似程度有困難,因此,本研究探討並試圖解決時間序列領先或落後的辨識相似度問題,並捨去需要事先定義類別標籤的方法,將相似的股票做聚類分析。本文研究動態時間校正計算股票走勢相似度,並使用聚類分析將股票分群,從中建立交易策略發想,並比較不同的聚類分析模型所對應的結果。其結果顯示,動態時間校正更能有效辨識實際相似的股票走勢,其克服時間序列相似卻不同步的問題;聚類分析用於股票分群也有很好的表現,有助於選出報酬較好的標的。
This paper discusses the application of dynamic time warping algorithm and cluster analysis for stock selection and trading strategy in Taiwan stock market. Recently, the researches of classification machine learning model which are used in the stock market are mostly based on the classification of the predicted rate of return, supplemented by the use of financial data or technical indicators. Therefore, it is necessary to define different categories of rates of return. Furthermore, the financial data or technical indicators corresponding to stocks with similar returns usually lead or lag in time, which makes it difficult to distinguish the similarity of stocks. Therefore, we expect to solve the identification similarity of leading or lagging time series problems, and cluster the similar stocks. In this paper, dynamic time warping algorithm is used to calculate the level of similarity in the trend of stocks, and cluster analysis is used to group the stocks. And then, we build an empirical study of stock selection strategies, and compare the difference of clustering analysis models. The result shows that the dynamic time warping algorithm can more effectively identify the actual similar stock trends, and the cluster models we used also have good performance for stocks grouping, which help to select stocks with better returns.參考文獻 1. Berndt, D. J., & Clifford, J. (1994). Using dynamic time warping to find patterns in time series. Paper presented at the KDD workshop.2. Cuong, N. A., Mai, D. S., Hop, D. T., Ngo, L. T., & Long, P. T. (2021). Fuzzy C-Medoids Clustering Based on Interval Type-2 Inituitionistic Fuzzy Sets. Paper presented at the 2021 RIVF International Conference on Computing and Communication Technologies (RIVF).3. Itakura, F. (1975). Minimum prediction residual principle applied to speech recognition. IEEE Transactions on acoustics, speech, and signal processing, 23(1), 67-72.4. Izakian, H., Pedrycz, W., & Jamal, I. (2015). Fuzzy clustering of time series data using dynamic time warping distance. Engineering Applications of Artificial Intelligence, 39, 235-244.5. Jin, X., & Han, J. (2010). K-Medoids Clustering, Encyclopedia of Machine Learning. In: Springer US.6. Kaufman, L., & Rousseeuw, P. J. (1990). Partitioning around medoids (program pam). Finding groups in data: an introduction to cluster analysis, 344, 68-125.7. Keogh, E., & Ratanamahatana, C. A. (2005). Exact indexing of dynamic time warping. Knowledge and information systems, 7(3), 358-386.8. Kim, S.-W., Park, S., & Chu, W. W. (2001). An index-based approach for similarity search supporting time warping in large sequence databases. Paper presented at the Proceedings 17th international conference on data engineering.9. Krishnapuram, R., Joshi, A., Nasraoui, O., & Yi, L. (2001). Low-complexity fuzzy relational clustering algorithms for web mining. IEEE transactions on Fuzzy Systems, 9(4), 595-607.10. Labroche, N. (2010). New incremental fuzzy c medoids clustering algorithms. Paper presented at the 2010 Annual Meeting of the North American Fuzzy Information Processing Society.11. Petitjean, F., Ketterlin, A., & Gançarski, P. (2011). A global averaging method for dynamic time warping, with applications to clustering. Pattern recognition, 44(3), 678-693.12. Ratanamahatana, C. A., & Keogh, E. (2005). Three myths about dynamic time warping data mining. Paper presented at the Proceedings of the 2005 SIAM international conference on data mining.13. Sakoe, H., & Chiba, S. (1978). Dynamic programming algorithm optimization for spoken word recognition. IEEE Transactions on acoustics, speech, and signal processing, 26(1), 43-49.14. Sammut, C., & Webb, G. I. (2017). Encyclopedia of machine learning and data mining: Springer Publishing Company, Incorporated.15. Torra, V. (2015). On the selection of m for Fuzzy c-Means. Paper presented at the IFSA-EUSFLAT.16. Yi, B.-K., Jagadish, H. V., & Faloutsos, C. (1998). Efficient retrieval of similar time sequences under time warping. Paper presented at the Proceedings 14th International Conference on Data Engineering. 描述 碩士
國立政治大學
金融學系
109352023資料來源 http://thesis.lib.nccu.edu.tw/record/#G0109352023 資料類型 thesis dc.contributor.advisor 廖四郎 zh_TW dc.contributor.advisor Liao, Szu-Lang en_US dc.contributor.author (Authors) 曾子軒 zh_TW dc.contributor.author (Authors) Tseng, Tzu-Hsuan en_US dc.creator (作者) 曾子軒 zh_TW dc.creator (作者) Tseng, Tzu-Hsuan en_US dc.date (日期) 2022 en_US dc.date.accessioned 1-Aug-2022 17:29:38 (UTC+8) - dc.date.available 1-Aug-2022 17:29:38 (UTC+8) - dc.date.issued (上傳時間) 1-Aug-2022 17:29:38 (UTC+8) - dc.identifier (Other Identifiers) G0109352023 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/141064 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 金融學系 zh_TW dc.description (描述) 109352023 zh_TW dc.description.abstract (摘要) 本文探討動態時間校正及聚類分析應用於台灣股票市場之實證研究。目前相關的分類機器學習模型用於股票市場的文獻,大多以預測報酬率為基礎,輔以使用財務資料或技術指標而成,為了要將報酬率分類,必須定義標籤類別,使得我們必須主觀界定各個報酬率類別的邊界。再者,相似報酬率的股票對應的財務資料或技術指標,往往在時間上有領先或落後,導致在區分股票標的相似程度有困難,因此,本研究探討並試圖解決時間序列領先或落後的辨識相似度問題,並捨去需要事先定義類別標籤的方法,將相似的股票做聚類分析。本文研究動態時間校正計算股票走勢相似度,並使用聚類分析將股票分群,從中建立交易策略發想,並比較不同的聚類分析模型所對應的結果。其結果顯示,動態時間校正更能有效辨識實際相似的股票走勢,其克服時間序列相似卻不同步的問題;聚類分析用於股票分群也有很好的表現,有助於選出報酬較好的標的。 zh_TW dc.description.abstract (摘要) This paper discusses the application of dynamic time warping algorithm and cluster analysis for stock selection and trading strategy in Taiwan stock market. Recently, the researches of classification machine learning model which are used in the stock market are mostly based on the classification of the predicted rate of return, supplemented by the use of financial data or technical indicators. Therefore, it is necessary to define different categories of rates of return. Furthermore, the financial data or technical indicators corresponding to stocks with similar returns usually lead or lag in time, which makes it difficult to distinguish the similarity of stocks. Therefore, we expect to solve the identification similarity of leading or lagging time series problems, and cluster the similar stocks. In this paper, dynamic time warping algorithm is used to calculate the level of similarity in the trend of stocks, and cluster analysis is used to group the stocks. And then, we build an empirical study of stock selection strategies, and compare the difference of clustering analysis models. The result shows that the dynamic time warping algorithm can more effectively identify the actual similar stock trends, and the cluster models we used also have good performance for stocks grouping, which help to select stocks with better returns. en_US dc.description.tableofcontents 第一章 緒論 1第一節 研究動機與目的 1第二節 研究貢獻 2第二章 文獻回顧 3第一節 動態時間校正相關研究 3第二節 聚類分析相關研究 4第三章 研究方法 6第一節 距離度量 6第二節 動態時間校正 6第三節 聚類分析模型 10第四節 實證研究架構與績效衡量 14第四章 模型建構與實證分析 20第一節 資料來源與資料預處理 20第二節 模型設置及訓練 22第三節 實證結果 25第五章 結論與展望 35第一節 研究結論 35第二節 未來展望 36參考文獻 37 zh_TW dc.format.extent 1942556 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0109352023 en_US dc.subject (關鍵詞) 動態時間校正 zh_TW dc.subject (關鍵詞) 聚類分析 zh_TW dc.subject (關鍵詞) Dynamic time warping zh_TW dc.subject (關鍵詞) K-medoids zh_TW dc.subject (關鍵詞) Fuzzy c-medoids zh_TW dc.subject (關鍵詞) Dynamic time warping en_US dc.subject (關鍵詞) Cluster analysis en_US dc.subject (關鍵詞) K-medoids en_US dc.subject (關鍵詞) Fuzzy c-medoids en_US dc.title (題名) 建構動態時間校正與聚類分析的選股模型實證研究 zh_TW dc.title (題名) An Empirical Study of Stock Selection Strategies on Dynamic Time Warping and Cluster Analysis en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) 1. Berndt, D. J., & Clifford, J. (1994). Using dynamic time warping to find patterns in time series. Paper presented at the KDD workshop.2. Cuong, N. A., Mai, D. S., Hop, D. T., Ngo, L. T., & Long, P. T. (2021). Fuzzy C-Medoids Clustering Based on Interval Type-2 Inituitionistic Fuzzy Sets. Paper presented at the 2021 RIVF International Conference on Computing and Communication Technologies (RIVF).3. Itakura, F. (1975). Minimum prediction residual principle applied to speech recognition. IEEE Transactions on acoustics, speech, and signal processing, 23(1), 67-72.4. Izakian, H., Pedrycz, W., & Jamal, I. (2015). Fuzzy clustering of time series data using dynamic time warping distance. Engineering Applications of Artificial Intelligence, 39, 235-244.5. Jin, X., & Han, J. (2010). K-Medoids Clustering, Encyclopedia of Machine Learning. In: Springer US.6. Kaufman, L., & Rousseeuw, P. J. (1990). Partitioning around medoids (program pam). Finding groups in data: an introduction to cluster analysis, 344, 68-125.7. Keogh, E., & Ratanamahatana, C. A. (2005). Exact indexing of dynamic time warping. Knowledge and information systems, 7(3), 358-386.8. Kim, S.-W., Park, S., & Chu, W. W. (2001). An index-based approach for similarity search supporting time warping in large sequence databases. Paper presented at the Proceedings 17th international conference on data engineering.9. Krishnapuram, R., Joshi, A., Nasraoui, O., & Yi, L. (2001). Low-complexity fuzzy relational clustering algorithms for web mining. IEEE transactions on Fuzzy Systems, 9(4), 595-607.10. Labroche, N. (2010). New incremental fuzzy c medoids clustering algorithms. Paper presented at the 2010 Annual Meeting of the North American Fuzzy Information Processing Society.11. Petitjean, F., Ketterlin, A., & Gançarski, P. (2011). A global averaging method for dynamic time warping, with applications to clustering. Pattern recognition, 44(3), 678-693.12. Ratanamahatana, C. A., & Keogh, E. (2005). Three myths about dynamic time warping data mining. Paper presented at the Proceedings of the 2005 SIAM international conference on data mining.13. Sakoe, H., & Chiba, S. (1978). Dynamic programming algorithm optimization for spoken word recognition. IEEE Transactions on acoustics, speech, and signal processing, 26(1), 43-49.14. Sammut, C., & Webb, G. I. (2017). Encyclopedia of machine learning and data mining: Springer Publishing Company, Incorporated.15. Torra, V. (2015). On the selection of m for Fuzzy c-Means. Paper presented at the IFSA-EUSFLAT.16. Yi, B.-K., Jagadish, H. V., & Faloutsos, C. (1998). Efficient retrieval of similar time sequences under time warping. Paper presented at the Proceedings 14th International Conference on Data Engineering. zh_TW dc.identifier.doi (DOI) 10.6814/NCCU202200715 en_US