學術產出-Theses
Article View/Open
Publication Export
-
題名 以集成學習建構混合模型預測台灣加權股價指數之趨勢
Forecasting the Trend of TAIEX by Using Ensemble Learning作者 徐維延
Hsu, Wei-Yan貢獻者 黃泓智
Huang, Hong-Chih
徐維延
Hsu, Wei-Yan關鍵詞 台股大盤
集成學習
混合模型
技術分析指標
總體經濟指標
Taiwan Capitalization Weighted Stock Index
Ensemble Learning
Blending Model
Technical Indicators
Macroeconomic Indicators日期 2019 上傳時間 7-Aug-2019 16:15:50 (UTC+8) 摘要 本研究的目標在於如何準確地預測台灣加權股價指數在數日後是否上漲至超過預設門檻，蒐集並萃取台灣加權股價指數之技術指標、其他國際重要股市指數及台灣總體經濟指標三種面向資料作為特徵值，總共有192個特徵。藉由集成學習的概念提出一個混合模型，並以單純的隨機森林模型作為標竿進行比較。因蒐集之資料皆具有時間性，故使用增長式視窗滾動法(Increasing Window Rolling)以驗證模型績效表現。結果顯示，單純的隨機森林模型雖在短天期的預測準確率高，但易受門檻標準訂定的影響，使得樣本呈現分類失衡的現象；反之在長天期的預測準確率較低，但對於不同門檻值也較為穩定，同時AUC指標也呈現較佳的表現。雖然此研究提出的混合模型並無在模型準確率上有明顯優於單純的隨機森林模型，但也觀察到混合模型的預測若能避開國際金融動盪的時期，模型表現應能不錯。
The purpose of this study is emphasized how to accurately forecast the uptrend of Taiwan Capitalization Weighted Stock Index (TAIEX) in next few days, which is required to exceed different default thresholds. The data collections in three aspects comprise technical indicators of TAIEX, other influential stock markets in the world and Taiwan’s macroeconomic indicators as model inputs. After extracting the crucial information behind these variables, there are 192 features in total.By proposing a blending model based on ensemble learning, the study will present a comparison with the simple random forest model. Besides, it is worth noting that raw data is temporal ordering; therefore, “Increasing Window Rolling” will be the validation method to evaluate the performance of models. The results have shown that the simple random forest model has high predictions in short periods but prone to be affected by different default thresholds, which may make sample imbalanced. On the contrary, predictions are less accurate in long periods but more stable under different default thresholds. In addition, the AUCs are also better. Although the proposed blending model is not significantly superior to the simple random forest model, it may still provide a good performance if phase of financial crisis is disregarded.參考文獻 Ahmed Imran Hunjra, Muhammad Irfan Chani, Muhammad Shahzad, Muhammad Farooq and Kamran Khan (2014). “The Impact of Macroeconomic Variables on Stock Prices in Pakistan,” International Journal of Economics and Empirical Research, 2(1), 13-21.Allan Timmermann and Clive William John Granger (2004). “Efficient Market Hypothesis and Forecasting,” International Journal of Forecasting, 20(1), 15-27.Amith Vikram Megaravalli, Gabriele Sampagnaro and Louis Murray (2018). Macroeconomic Indicators and Their Impact on Stock Markets in ASIAN 3: A Pooled Mean Group Approach,” Cogent Economics and Finance, 6, 1-14.Berninger, Jordan (2018). “Forecasting the Time Series of Apple Inc.`s Stock Price,” UCLA Electronic Theses and Dissertations.Christopher N. Avery, Judith A. Chevalier and Richard J. Zeckhauser (2016)."The "CAPS" Prediction System and Stock Market Returns," Review of Finance, European Finance Association, 20(4), 1363-1381.Depei Bao and Zehong Yang (2008). “Intelligent Stock Trading System by Turning Point Confirming and Probabilistic Reasoning,” Expert Systems with Applications, 34(1), 620-627.Eugene F. Fama (1970). “Efficient Capital Markets: A Review of Theory and Empirical Work,” The Journal of Finance, 25(2), 383-417.Felipe Giacomel, Renata Galante and Adriano Pareira (2015). “An Algorithmic Trading Agent Based on A Neural Network Ensemble: A Case of Study in North American and Brazilian Stock Markets,” IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology.Haoming Li, Tianlun Li and Zhijun Yang (2014). “Algorithmic Trading Strategy Based on Massive Data Mining,” Stanford University.Jan Ivar Larsen (2010). “Predicting Stock Prices Using Technical Analysis and Machine Learning,” Thesis, Norwegian University of Science and Technology.Jawad Khan and Imran Khan (2018). “The Impact of Macroeconomic Variables on Stock Prices: A Case Study of Karachi Stock Exchange,” Journal of Economics and Sustainable Development, 9(13), 15-25.Joseph Tagne Talla (2013). “Impact of Macroeconomic Variables on the Stock Market Prices of the Stockholm Stock Exchange (OMXS30),” Master´s Thesis within International Financial Analysis.K. Nirmala Devi, V. Murali Bhaskaran and G. Prem Kumar (2015). “Cuckoo Optimized SVM for Stock Market Prediction,” IEEE Sponsored 2nd International Conference on Innovations in Information, Embedded and Communication systems (ICJJECS).Leo Breiman (1994). “Bagging Predictors,” Machine Learning 26(2), 123-140.Luckyson Khaidem, Snehanshu Saha and Sudeepa Roy Dey (2016). “Predicting the Direction of Stock Market Prices Using Random Forest,” arXiv preprint arXiv:160500003.Ludmila Kuncheva and Chris Whitaker (2003). “Measures of Diversity in Classifier Ensembles and Their Relationship with the Ensemble Accuracy,” Machine Learning 51(2), 181-207.Michael C. Jensen (1978). “Some Anomalous Evidence Regarding Market Efficiency,” Journal of Financial Economics, 6, Nos. 2/3 95-101.Ramazan Gencay (1999). “Linear, Non-Linear and Essential Foreign Exchange Rate Prediction with Simple Technical Trading Rules,” Journal of International Economics 47(1), 91-107.Segal and Mark R (2004). “Machine Learning Benchmarks and Random Forest Regression,” Center for Bioinformatics and Molecular Biostatistics, UC, San Francisco, California.Snehanshu Saha, Swati Routh and Bidisha Goswami (2014). “Modeling Vanilla Option Prices: A Simulation Study by An Implicit Method,” Journal of advances in Mathematics, 6(1), 834-848.Suryoday Basak, Saibal Kar, Snehanshu Saha, Luckyson Khaidem and Sudeepa Roy Dey (2019). “Predicting the Direction of Stock Market Prices Using Tree-Based Classifiers,” The North American Journal of Economics and Finance, Volume 47, 552-567.Xinjie (2014). “Stock Trend Prediction with Technical Indicators Using SVM,” Stanford University.Yoav Freund and Robert E. Schapire (1996). “Experiments with a New Boosting Algorithm,” Machine Learning: Proceedings of the Thirteenth International Conference, 148-156.Yuqing Dai and Yuning Zhang (2013). “Machine Learning in Stock Price Trend Forecasting,” Stanford University. 描述 碩士
國立政治大學
風險管理與保險學系
106358009資料來源 http://thesis.lib.nccu.edu.tw/record/#G0106358009 資料類型 thesis dc.contributor.advisor 黃泓智 zh_TW dc.contributor.advisor Huang, Hong-Chih en_US dc.contributor.author (Authors) 徐維延 zh_TW dc.contributor.author (Authors) Hsu, Wei-Yan en_US dc.creator (作者) 徐維延 zh_TW dc.creator (作者) Hsu, Wei-Yan en_US dc.date (日期) 2019 en_US dc.date.accessioned 7-Aug-2019 16:15:50 (UTC+8) - dc.date.available 7-Aug-2019 16:15:50 (UTC+8) - dc.date.issued (上傳時間) 7-Aug-2019 16:15:50 (UTC+8) - dc.identifier (Other Identifiers) G0106358009 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/124755 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 風險管理與保險學系 zh_TW dc.description (描述) 106358009 zh_TW dc.description.abstract (摘要) 本研究的目標在於如何準確地預測台灣加權股價指數在數日後是否上漲至超過預設門檻，蒐集並萃取台灣加權股價指數之技術指標、其他國際重要股市指數及台灣總體經濟指標三種面向資料作為特徵值，總共有192個特徵。藉由集成學習的概念提出一個混合模型，並以單純的隨機森林模型作為標竿進行比較。因蒐集之資料皆具有時間性，故使用增長式視窗滾動法(Increasing Window Rolling)以驗證模型績效表現。結果顯示，單純的隨機森林模型雖在短天期的預測準確率高，但易受門檻標準訂定的影響，使得樣本呈現分類失衡的現象；反之在長天期的預測準確率較低，但對於不同門檻值也較為穩定，同時AUC指標也呈現較佳的表現。雖然此研究提出的混合模型並無在模型準確率上有明顯優於單純的隨機森林模型，但也觀察到混合模型的預測若能避開國際金融動盪的時期，模型表現應能不錯。 zh_TW dc.description.abstract (摘要) The purpose of this study is emphasized how to accurately forecast the uptrend of Taiwan Capitalization Weighted Stock Index (TAIEX) in next few days, which is required to exceed different default thresholds. The data collections in three aspects comprise technical indicators of TAIEX, other influential stock markets in the world and Taiwan’s macroeconomic indicators as model inputs. After extracting the crucial information behind these variables, there are 192 features in total.By proposing a blending model based on ensemble learning, the study will present a comparison with the simple random forest model. Besides, it is worth noting that raw data is temporal ordering; therefore, “Increasing Window Rolling” will be the validation method to evaluate the performance of models. The results have shown that the simple random forest model has high predictions in short periods but prone to be affected by different default thresholds, which may make sample imbalanced. On the contrary, predictions are less accurate in long periods but more stable under different default thresholds. In addition, the AUCs are also better. Although the proposed blending model is not significantly superior to the simple random forest model, it may still provide a good performance if phase of financial crisis is disregarded. en_US dc.description.tableofcontents 第一章 研究背景與動機 1第一節 機器學習之發展 1第二節 監督式學習框架 2第三節 模型偏差與變異數之抵換關係 2第四節 集成學習方法 4第二章 文獻回顧 7第三章 研究方法 9第一節 研究架構 9第二節 資料來源與預先處理 10第三節 變數介紹 10第四章 資料前置處理與特徵生成 15第一節 上漲標準訂定 15第二節 月頻資料處理 15第三節 技術指標生成 15第四節 特徵標準化過程 27第五章 模型建構與績效 29第一節 混合模型架構 29第二節 績效評估 36第六章 結論與建議 44參考文獻 46附錄 49 zh_TW dc.format.extent 2072468 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0106358009 en_US dc.subject (關鍵詞) 台股大盤 zh_TW dc.subject (關鍵詞) 集成學習 zh_TW dc.subject (關鍵詞) 混合模型 zh_TW dc.subject (關鍵詞) 技術分析指標 zh_TW dc.subject (關鍵詞) 總體經濟指標 zh_TW dc.subject (關鍵詞) Taiwan Capitalization Weighted Stock Index en_US dc.subject (關鍵詞) Ensemble Learning en_US dc.subject (關鍵詞) Blending Model en_US dc.subject (關鍵詞) Technical Indicators en_US dc.subject (關鍵詞) Macroeconomic Indicators en_US dc.title (題名) 以集成學習建構混合模型預測台灣加權股價指數之趨勢 zh_TW dc.title (題名) Forecasting the Trend of TAIEX by Using Ensemble Learning en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) Ahmed Imran Hunjra, Muhammad Irfan Chani, Muhammad Shahzad, Muhammad Farooq and Kamran Khan (2014). “The Impact of Macroeconomic Variables on Stock Prices in Pakistan,” International Journal of Economics and Empirical Research, 2(1), 13-21.Allan Timmermann and Clive William John Granger (2004). “Efficient Market Hypothesis and Forecasting,” International Journal of Forecasting, 20(1), 15-27.Amith Vikram Megaravalli, Gabriele Sampagnaro and Louis Murray (2018). Macroeconomic Indicators and Their Impact on Stock Markets in ASIAN 3: A Pooled Mean Group Approach,” Cogent Economics and Finance, 6, 1-14.Berninger, Jordan (2018). “Forecasting the Time Series of Apple Inc.`s Stock Price,” UCLA Electronic Theses and Dissertations.Christopher N. Avery, Judith A. Chevalier and Richard J. Zeckhauser (2016)."The "CAPS" Prediction System and Stock Market Returns," Review of Finance, European Finance Association, 20(4), 1363-1381.Depei Bao and Zehong Yang (2008). “Intelligent Stock Trading System by Turning Point Confirming and Probabilistic Reasoning,” Expert Systems with Applications, 34(1), 620-627.Eugene F. Fama (1970). “Efficient Capital Markets: A Review of Theory and Empirical Work,” The Journal of Finance, 25(2), 383-417.Felipe Giacomel, Renata Galante and Adriano Pareira (2015). “An Algorithmic Trading Agent Based on A Neural Network Ensemble: A Case of Study in North American and Brazilian Stock Markets,” IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology.Haoming Li, Tianlun Li and Zhijun Yang (2014). “Algorithmic Trading Strategy Based on Massive Data Mining,” Stanford University.Jan Ivar Larsen (2010). “Predicting Stock Prices Using Technical Analysis and Machine Learning,” Thesis, Norwegian University of Science and Technology.Jawad Khan and Imran Khan (2018). “The Impact of Macroeconomic Variables on Stock Prices: A Case Study of Karachi Stock Exchange,” Journal of Economics and Sustainable Development, 9(13), 15-25.Joseph Tagne Talla (2013). “Impact of Macroeconomic Variables on the Stock Market Prices of the Stockholm Stock Exchange (OMXS30),” Master´s Thesis within International Financial Analysis.K. Nirmala Devi, V. Murali Bhaskaran and G. Prem Kumar (2015). “Cuckoo Optimized SVM for Stock Market Prediction,” IEEE Sponsored 2nd International Conference on Innovations in Information, Embedded and Communication systems (ICJJECS).Leo Breiman (1994). “Bagging Predictors,” Machine Learning 26(2), 123-140.Luckyson Khaidem, Snehanshu Saha and Sudeepa Roy Dey (2016). “Predicting the Direction of Stock Market Prices Using Random Forest,” arXiv preprint arXiv:160500003.Ludmila Kuncheva and Chris Whitaker (2003). “Measures of Diversity in Classifier Ensembles and Their Relationship with the Ensemble Accuracy,” Machine Learning 51(2), 181-207.Michael C. Jensen (1978). “Some Anomalous Evidence Regarding Market Efficiency,” Journal of Financial Economics, 6, Nos. 2/3 95-101.Ramazan Gencay (1999). “Linear, Non-Linear and Essential Foreign Exchange Rate Prediction with Simple Technical Trading Rules,” Journal of International Economics 47(1), 91-107.Segal and Mark R (2004). “Machine Learning Benchmarks and Random Forest Regression,” Center for Bioinformatics and Molecular Biostatistics, UC, San Francisco, California.Snehanshu Saha, Swati Routh and Bidisha Goswami (2014). “Modeling Vanilla Option Prices: A Simulation Study by An Implicit Method,” Journal of advances in Mathematics, 6(1), 834-848.Suryoday Basak, Saibal Kar, Snehanshu Saha, Luckyson Khaidem and Sudeepa Roy Dey (2019). “Predicting the Direction of Stock Market Prices Using Tree-Based Classifiers,” The North American Journal of Economics and Finance, Volume 47, 552-567.Xinjie (2014). “Stock Trend Prediction with Technical Indicators Using SVM,” Stanford University.Yoav Freund and Robert E. Schapire (1996). “Experiments with a New Boosting Algorithm,” Machine Learning: Proceedings of the Thirteenth International Conference, 148-156.Yuqing Dai and Yuning Zhang (2013). “Machine Learning in Stock Price Trend Forecasting,” Stanford University. zh_TW dc.identifier.doi (DOI) 10.6814/NCCU201900623 en_US
