學術產出-Theses
Article View/Open
Publication Export
-
題名 運用Google Trends情緒萃取建構人工智慧量化交易策略：以台灣加權指數期貨為例
Devising Quantitative Trading Strategies with Artificial-Intelligence using Google Trends Sentiment Extraction：The Case of TAIEX Futures作者 王德諭
Wang, De-Yu貢獻者 江彌修
Chiang, Mi-Hsiu
王德諭
Wang, De-Yu關鍵詞 Google Trends
機器學習
隨機森林
市場情緒萃取
台灣加權指數期貨
下方風險
Google Trends
Machine learning
Random forest
Market sentiment extraction
TAIEX futures
Down-side risk日期 2021 上傳時間 1-Jul-2021 18:09:32 (UTC+8) 摘要 基於Google Trends的投資人情緒萃取，本文提供一具情緒表徵學習能力的集成預測框架。以隨機森林模型建構台灣加權指數期貨量化交易策略為例，本文探究輔以情緒萃取的分類器特徵生成之於模型預測能力及其量化交易策略之影響。本文的研究發現，輔以市場負面情緒(FEARS指數)以及股市關注度(Company_SVI)特徵生成，能有效提高隨機森林模型之陰性預測能力，其量化交易策略於測試區間之累積損益與風險比率皆勝出於大盤。特別地，我們發現2020年新冠疫情之後，輔以情緒特徵生成之模型預測能力及交易策略績效都能夠有效提升，在獲得與大盤相同績效的同時，承受虧損的幅度以及時間皆呈現大幅縮減。另外，當允許市場情緒萃取作近一步正負面之區分，本文發現陰性預測率雖能更有效提升，然而對下方風險的趨避能力下降，從而減損其量化交易策略之績效。
By extracting public investor sentiment from Google Trends, this thesis provides an ensemble prediction framework that allows for sentiment representation-learning. Based on random forest models, TAIEX futures trading strategies are devised to examine the impacts of the added sentiment dimension on the random forest models’ predictive abilities and the trading strategies’ risk-reward performances. Our numerical findings show that, sentiment assisted representation-learning, when attributed by FEARS and Company_SVI indices, can effectively improve the downside predictive ability of random forest models, resulting in higher cumulative returns and better risk-return profiles relative to simple buy-and-holds. Further evidence suggests that, adopting sentiment assisted representation learning, especially during the post-pandemic era (after 2020), helps to maintain a comparable risk-return profile relative to that of a buy-and-hold while at the same time significantly reduces the extent of losses and the time endured for losses. In addition, upon further categorizing market sentiment as positive or negative, the random forest models’ downside predictive power is found to increase while the strategies’ downside-risk-aversive ability seems to decrease, leading to an overall detrimental effect on trading performance.參考文獻 一、中文部分林哲鵬, 李春安, & 葉智丞. (2012). 投資人情緒與價格動能之關聯性. 管理與系統, 19(4), 729-759.鄭仁杰, & 江彌修. (2019). 漫步於隨機森林-輔以多數決學習的台股指數期貨交易策略. 經濟論文, 47(3), 395-448.二、英文部分Ahundjanov, B. B., Akhundjanov, S. B., &Okhunjanov, B. B. (2020). Information Search and Financial Markets under COVID-19. Entropy, 22(7), 791.Antweiler, W., & Frank, M. Z. (2004). Is all that talk just noise? The information content of internet stock message boards. The Journal of finance, 59(3), 1259-1294.Ballings, M., Van den Poel, D., Hespeels, N., & Gryp, R. (2015). Evaluating multiple classifiers for stock price direction prediction. Expert systems with Applications, 42(20), 7046-7056.Barber, B. M., & Odean, T. (2008). All that glitters: The effect of attention and news on the buying behavior of individual and institutional investors. The review of financial studies, 21(2), 785-818.Beer, F., Hervé, F., & Zouaoui, M. (2012). Is big brother watching us? Google, investor sentiment and the stock market. Economics Bulletin, Forthcoming.Blume, L., D. Easley, and M. O’Hara (1994), “Market Statistics and Technical Analysis: The Role of Volume,” Journal of Finance, 49(1), 153–181.Breiman, L. (2001). Random forests. Machine learning, 45(1), 5-32.Breiman, L., Friedman, J., Stone, C. J., & Olshen, R. A. (1984). Classification and regression trees. CRC press.Carneiro, H. A., &Mylonakis, E. (2009). Google trends: a web-based tool for real-time surveillance of disease outbreaks. Clinical infectious diseases, 49(10), 1557-1564.Cutler, D. M., Poterba, J. M., & Summers, L. H. (1988). What moves stock prices? (No. w2538). National Bureau of Economic Research.Da, Z., Engelberg, J., & Gao, P. (2011). In search of attention. The Journal of Finance, 66(5), 1461-1499.Da, Z., Engelberg, J., & Gao, P. (2015). The sum of all FEARS investor sentiment and asset prices. The Review of Financial Studies, 28(1), 1-32.De Long, J. B., Shleifer, A., Summers, L. H., & Waldmann, R. J. (1990). Noise trader risk in financial markets. Journal of political Economy, 98(4), 703-738.Go, A., Bhayani, R., and Huang, L. (2009). Twitter sentiment classification using distant supervision. Technical report, Stanford University.Huang, M. Y., Rojas, R. R., & Convery, P. D. (2019). Forecasting stock market movements using Google Trend searches. Empirical Economics, 1-19.Khaidem, L., S. Saha, and S. R. Dey (2016), “Predicting the Direction of Stock Market Prices Using Random Forest,” arXiv preprint arXiv:160500003.Kumar, M. and M. Thenmozhi (2006), “Forecasting Stock Index Movement: A Comparison of Support Vector Machines and Random Forest,” Working Paper, The Ninth Indian Institute of Capital Markets ConferenceMondria, J., Wu, T., & Zhang, Y. (2010). The determinants of international investment and attention allocation: Using internet search query data. Journal of International Economics, 82(1), 85-95.Ren, N., M. Zargham, and S. Rahimi (2006), “A Decision Tree-Based Classification Approach to Rule Extraction for Security Analysis,” International Journal of Information Technology and Decision Making, 5(1), 227–240.Richards, A. (2005), “Big Fish in Small Ponds: The Trading Behavior and Price Impact of Foreign Investors in Asian Emerging Equity Markets,” Journal of Financial and Quantitative Analysis, 40(1), 1–27.Sen, J. and T. Chaudhuri (2017), “A Robust Predictive Model for Stock Price Forecasting,” Working Paper, The 5th International Conference on Business Analytics and Intelligence.Shiller, R. J., Fischer, S., & Friedman, B. M. (1984). Stock prices and social dynamics. Brookings papers on economic activity, 1984(2), 457-510.Simon, D. P. and R. A. Wiggins (2001), “S&P Futures Returns and Contrary Sentiment Indicators,” Journal of Futures Markets, 21(5), 447–462.Tetlock, P. C. (2007). Giving content to investor sentiment: The role of media in the stock market. The Journal of finance, 62(3), 1139-1168.Tetlock, P. C., Saar‐Tsechansky, M., &Macskassy, S. (2008). More than words: Quantifying language to measure firms` fundamentals. The Journal of Finance, 63(3), 1437-1467.Vu, T. T., Chang, S., Ha, Q. T., & Collier, N. (2012). An experiment in integrating sentiment features for tech stock prediction in twitter. 描述 碩士
國立政治大學
金融學系
108352030資料來源 http://thesis.lib.nccu.edu.tw/record/#G0108352030 資料類型 thesis dc.contributor.advisor 江彌修 zh_TW dc.contributor.advisor Chiang, Mi-Hsiu en_US dc.contributor.author (Authors) 王德諭 zh_TW dc.contributor.author (Authors) Wang, De-Yu en_US dc.creator (作者) 王德諭 zh_TW dc.creator (作者) Wang, De-Yu en_US dc.date (日期) 2021 en_US dc.date.accessioned 1-Jul-2021 18:09:32 (UTC+8) - dc.date.available 1-Jul-2021 18:09:32 (UTC+8) - dc.date.issued (上傳時間) 1-Jul-2021 18:09:32 (UTC+8) - dc.identifier (Other Identifiers) G0108352030 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/135943 - 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) 108352030 zh_TW dc.description.abstract (摘要) 基於Google Trends的投資人情緒萃取，本文提供一具情緒表徵學習能力的集成預測框架。以隨機森林模型建構台灣加權指數期貨量化交易策略為例，本文探究輔以情緒萃取的分類器特徵生成之於模型預測能力及其量化交易策略之影響。本文的研究發現，輔以市場負面情緒(FEARS指數)以及股市關注度(Company_SVI)特徵生成，能有效提高隨機森林模型之陰性預測能力，其量化交易策略於測試區間之累積損益與風險比率皆勝出於大盤。特別地，我們發現2020年新冠疫情之後，輔以情緒特徵生成之模型預測能力及交易策略績效都能夠有效提升，在獲得與大盤相同績效的同時，承受虧損的幅度以及時間皆呈現大幅縮減。另外，當允許市場情緒萃取作近一步正負面之區分，本文發現陰性預測率雖能更有效提升，然而對下方風險的趨避能力下降，從而減損其量化交易策略之績效。 zh_TW dc.description.abstract (摘要) By extracting public investor sentiment from Google Trends, this thesis provides an ensemble prediction framework that allows for sentiment representation-learning. Based on random forest models, TAIEX futures trading strategies are devised to examine the impacts of the added sentiment dimension on the random forest models’ predictive abilities and the trading strategies’ risk-reward performances. Our numerical findings show that, sentiment assisted representation-learning, when attributed by FEARS and Company_SVI indices, can effectively improve the downside predictive ability of random forest models, resulting in higher cumulative returns and better risk-return profiles relative to simple buy-and-holds. Further evidence suggests that, adopting sentiment assisted representation learning, especially during the post-pandemic era (after 2020), helps to maintain a comparable risk-return profile relative to that of a buy-and-hold while at the same time significantly reduces the extent of losses and the time endured for losses. In addition, upon further categorizing market sentiment as positive or negative, the random forest models’ downside predictive power is found to increase while the strategies’ downside-risk-aversive ability seems to decrease, leading to an overall detrimental effect on trading performance. en_US dc.description.tableofcontents 第一章 緒論 1第二章 文獻回顧 6第一節 市場情緒相關文獻 6第二節 機器學習相關文獻 8第三章 研究方法 10第一節 隨機森林與決策樹 10第二節 特徵生成 11第三節 模型預測能力衡量指標 16第四節 績效衡量指標 18第四章 實證結果與分析 20第一節 交易策略執行步驟與特徵變數之配置策略 20第二節 資料描述與敘述統計 21第三節 模型參數配置及特徵重要性 22第四節 模型預測能力與策略績效檢視 26第五節 策略多空單績效檢視與週期分析 36第五章 結論與後續研究建議 44參考文獻 48表次表 3-1 ： 混淆矩陣 17表 4-1 ： 修正後台灣加權指數期貨期貨價格報酬率敘述統計 22表 4-2 ： 資料漲跌日數與比例 23表 4-3 ： 修正後台灣加權指數期貨各區間績效指標 23表 4-4 ：基準策略於訓練區間之袋外混淆矩陣 27表 4-5 ： 基準策略於測試區間之混淆矩陣 28表 4-6 ： 策略4於訓練區間之袋外混淆矩陣 31表 4-7 ： 策略4於測試區間之混淆矩陣 31表 4-8 ： 策略5於訓練區間之袋外混淆矩陣 34表 4-9 ： 策略5於測試區間之混淆矩陣 34表 4-10 ： 各項策略於訓練區間內之績效比較 37表 4-11 ： 各項策略於測試區間內之績效比較 39表 4-12 ： 策略4與策略5於全部區間之年週期分析 41圖次圖 4-1 ： 策略4之特徵變數重要性 24圖 4-2 ： 策略4特徵變數重要性的差之盒鬚圖 25圖 4-3 ： 策略4特徵變數之層次聚類樹狀圖 26圖 4-4 ： 基準策略之多空單跌幅比較 30圖 4-5 ： 基準策略於測試區間之跌幅表現 30圖 4-6 ： 基準策略與單純持有多單策略於全部區間之累積報酬比較 30圖 4-7 ： 策略4之多空單跌幅比較 32圖 4-8 ： 策略4於測試區間之跌幅表現 33圖 4-9 ： 策略4與單純持有多單策略於全部區間之累積報酬比較 33圖 4-10 ： 策略5之多空單跌幅比較 35圖 4-11 ： 策略5於測試區間之跌幅表現 35圖 4-12 ： 策略5與單純持有多單策略於全部區間之累積報酬比較 36圖 4-13 ： 單純持有策略於全部區間之每月損益 42圖 4-14 ： 策略4於全部區間之每月損益 43 zh_TW dc.format.extent 2506782 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0108352030 en_US dc.subject (關鍵詞) Google Trends zh_TW dc.subject (關鍵詞) 機器學習 zh_TW dc.subject (關鍵詞) 隨機森林 zh_TW dc.subject (關鍵詞) 市場情緒萃取 zh_TW dc.subject (關鍵詞) 台灣加權指數期貨 zh_TW dc.subject (關鍵詞) 下方風險 zh_TW dc.subject (關鍵詞) Google Trends en_US dc.subject (關鍵詞) Machine learning en_US dc.subject (關鍵詞) Random forest en_US dc.subject (關鍵詞) Market sentiment extraction en_US dc.subject (關鍵詞) TAIEX futures en_US dc.subject (關鍵詞) Down-side risk en_US dc.title (題名) 運用Google Trends情緒萃取建構人工智慧量化交易策略：以台灣加權指數期貨為例 zh_TW dc.title (題名) Devising Quantitative Trading Strategies with Artificial-Intelligence using Google Trends Sentiment Extraction：The Case of TAIEX Futures en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) 一、中文部分林哲鵬, 李春安, & 葉智丞. (2012). 投資人情緒與價格動能之關聯性. 管理與系統, 19(4), 729-759.鄭仁杰, & 江彌修. (2019). 漫步於隨機森林-輔以多數決學習的台股指數期貨交易策略. 經濟論文, 47(3), 395-448.二、英文部分Ahundjanov, B. B., Akhundjanov, S. B., &Okhunjanov, B. B. (2020). Information Search and Financial Markets under COVID-19. Entropy, 22(7), 791.Antweiler, W., & Frank, M. Z. (2004). Is all that talk just noise? The information content of internet stock message boards. The Journal of finance, 59(3), 1259-1294.Ballings, M., Van den Poel, D., Hespeels, N., & Gryp, R. (2015). Evaluating multiple classifiers for stock price direction prediction. Expert systems with Applications, 42(20), 7046-7056.Barber, B. M., & Odean, T. (2008). All that glitters: The effect of attention and news on the buying behavior of individual and institutional investors. The review of financial studies, 21(2), 785-818.Beer, F., Hervé, F., & Zouaoui, M. (2012). Is big brother watching us? Google, investor sentiment and the stock market. Economics Bulletin, Forthcoming.Blume, L., D. Easley, and M. O’Hara (1994), “Market Statistics and Technical Analysis: The Role of Volume,” Journal of Finance, 49(1), 153–181.Breiman, L. (2001). Random forests. Machine learning, 45(1), 5-32.Breiman, L., Friedman, J., Stone, C. J., & Olshen, R. A. (1984). Classification and regression trees. CRC press.Carneiro, H. A., &Mylonakis, E. (2009). Google trends: a web-based tool for real-time surveillance of disease outbreaks. Clinical infectious diseases, 49(10), 1557-1564.Cutler, D. M., Poterba, J. M., & Summers, L. H. (1988). What moves stock prices? (No. w2538). National Bureau of Economic Research.Da, Z., Engelberg, J., & Gao, P. (2011). In search of attention. The Journal of Finance, 66(5), 1461-1499.Da, Z., Engelberg, J., & Gao, P. (2015). The sum of all FEARS investor sentiment and asset prices. The Review of Financial Studies, 28(1), 1-32.De Long, J. B., Shleifer, A., Summers, L. H., & Waldmann, R. J. (1990). Noise trader risk in financial markets. Journal of political Economy, 98(4), 703-738.Go, A., Bhayani, R., and Huang, L. (2009). Twitter sentiment classification using distant supervision. Technical report, Stanford University.Huang, M. Y., Rojas, R. R., & Convery, P. D. (2019). Forecasting stock market movements using Google Trend searches. Empirical Economics, 1-19.Khaidem, L., S. Saha, and S. R. Dey (2016), “Predicting the Direction of Stock Market Prices Using Random Forest,” arXiv preprint arXiv:160500003.Kumar, M. and M. Thenmozhi (2006), “Forecasting Stock Index Movement: A Comparison of Support Vector Machines and Random Forest,” Working Paper, The Ninth Indian Institute of Capital Markets ConferenceMondria, J., Wu, T., & Zhang, Y. (2010). The determinants of international investment and attention allocation: Using internet search query data. Journal of International Economics, 82(1), 85-95.Ren, N., M. Zargham, and S. Rahimi (2006), “A Decision Tree-Based Classification Approach to Rule Extraction for Security Analysis,” International Journal of Information Technology and Decision Making, 5(1), 227–240.Richards, A. (2005), “Big Fish in Small Ponds: The Trading Behavior and Price Impact of Foreign Investors in Asian Emerging Equity Markets,” Journal of Financial and Quantitative Analysis, 40(1), 1–27.Sen, J. and T. Chaudhuri (2017), “A Robust Predictive Model for Stock Price Forecasting,” Working Paper, The 5th International Conference on Business Analytics and Intelligence.Shiller, R. J., Fischer, S., & Friedman, B. M. (1984). Stock prices and social dynamics. Brookings papers on economic activity, 1984(2), 457-510.Simon, D. P. and R. A. Wiggins (2001), “S&P Futures Returns and Contrary Sentiment Indicators,” Journal of Futures Markets, 21(5), 447–462.Tetlock, P. C. (2007). Giving content to investor sentiment: The role of media in the stock market. The Journal of finance, 62(3), 1139-1168.Tetlock, P. C., Saar‐Tsechansky, M., &Macskassy, S. (2008). More than words: Quantifying language to measure firms` fundamentals. The Journal of Finance, 63(3), 1437-1467.Vu, T. T., Chang, S., Ha, Q. T., & Collier, N. (2012). An experiment in integrating sentiment features for tech stock prediction in twitter. zh_TW dc.identifier.doi (DOI) 10.6814/NCCU202100594 en_US
