Loading...
|
Please use this identifier to cite or link to this item:
https://nccur.lib.nccu.edu.tw/handle/140.119/136354
|
| Title: | 依稀疏迴歸模型檢驗硬情緒：基於指數報酬的可預測性
In Search of Index Return Predictability: Based On Sparse Predictive Regressions With Hard Information |
| Authors: | 林彣珊
Lin, Wen-Shan |
| Contributors: | 江彌修
Chiang, Mi-Hsiu
林彣珊
Lin, Wen-Shan |
| Keywords: | 稀疏迴歸模型
特徵生成
硬情緒
Sparse regression model
Feature generation
Hard sentiment |
| Date: | 2021 |
| Issue Date: | 2021-08-04 14:49:46 (UTC+8) |
| Abstract: | 近年來有許多學者提出投資人情緒對金融市場的趨勢改變有很大的關係，亦透過建構情緒指標來驗證變數情緒討論有助於幫助市場趨勢預測的準確度提升；而金融市場受到各種不同面向的變數影響，也導致市場趨勢預測更加複雜、困難，近年來也有許多文獻討論預測市場趨勢的模型，其中以機器學習訓練模型，能處理巨量的高維度資料，有效解決傳統迴歸模型在變數增加預測能力下降的問題，在預測上有更好的表現。因此本研究以稀疏迴歸模型作為預測模型，透過挑選隱含投資人情緒的硬資訊作為變數討論，來驗證稀疏迴歸規模型有助於篩選資訊，減少模型內變數數量，在多變數的情況下能提升預測準確度；除此之外，亦透過稀疏迴歸模型的懲罰項特性，來探討所萃取出來的特徵是否有一致性，能幫助投資人更準確的掌握隱含情緒異象的硬資訊。
In recent years, many scholars have pointed out that investor sentiment has a great relationship with changes in financial market trends, and the construction of sentiment indicators to verify variable sentiment discussions can help improve the accuracy of market trend forecasting; financial markets are subject to various aspects. The influence of the variables in the market has also made market trend prediction more complicated and difficult. In recent years, there have been many articles discussing models for predicting market trends. Among them, machine learning training models can handle huge amounts of high-dimensional data, effectively solving the increasing variables of traditional regression models. The problem of declining forecasting ability has better performance in forecasting. Therefore, this study uses a sparse regression model as a predictive model. By selecting hard information that implies investor sentiment as a variable discussion, it is verified that the sparse regression can help filter information and reduce the number of variables in the model and improve the accuracy of prediction. In addition, the penalty feature of the sparse regression model is also used to explore whether the extracted features are consistent, which can help investors more accurately grasp hard information that implies emotional anomalies. |
| Reference: | [1]Ait-Sahalia, Y., Andritzky, J., Jobst, A., Nowak, S., & Tamirisa, N. (2012). Market response to policy initiatives during the global financial crisis. Journal of International Economics, 87(1), 162-177.
[2]Bianchi, D., & Tamoni, A. (2020). Sparse predictive regressions: Statistical performance and economic significance. Machine Learning for Asset Management: New Developments and Financial Applications, 75-113.
[3]Baker, M., & Wurgler, J. (2006). Investor sentiment and the crosssection of stock returns. The journal of Finance, 61(4), 1645-1680.
[4]Brown, G. W., & Cliff, M. T. (2004). Investor sentiment and the near-term stock market. Journal of empirical finance, 11(1), 1-27.
[5]Baker, M., & Stein, J. C. (2004). Market liquidity as a sentiment indicator. Journal of Financial Markets, 7(3), 271-299.
[6]Chen, H., Chong, T. T. L., & She, Y. (2014). A principal component approach to measuring investor sentiment in China. Quantitative Finance, 14(4), 573-579.
[7]Chun, S. H., & Kim, S. H. (2004). Data mining for financial prediction and trading:Application to single and multiple markets. Expert Systems with Applications, 26(2),131–139.
[8]Curme, C., Preis, T., Stanley, H. E., & Moat, H. S. (2014). Quantifying the semantics of search behavior before stock market moves. Proceedings of the National Academy of Sciences of the United States of America, 111(32), 11600–11605.
[9]Ding, W., Mazouz, K., & Wang, Q. (2019). Investor sentiment and the cross-section of stock returns: new theory and evidence. Review of Quantitative Finance and Accounting, 53(2), 493-525.
[10]Friedman, J., Hastie, T., & Tibshirani, R. (2010). Regularization paths for generalized linear models via coordinate descent. Journal of statistical software, 33(1), 1.
[11]Georgopoulou, A., & Wang, J. (2017). The trend is your friend: Time-series momentum strategies across equity and commodity markets. Review of Finance, 21(4), 1557-1592.
[12]Hurst, B., Ooi, Y. H., & Pedersen, L. H. (2017). A century of evidence on trend-following investing. The Journal of Portfolio Management, 44(1), 15-29.
[13]Lam, M. (2004). Neural network techniques for financial performance prediction: Integrating fundamental and technical analysis. Decision Support Systems, 37(4),
567–581.
[14]Liu, L., Ma, F., Zeng, Q., & Zhang, Y. (2020). Forecasting the aggregate stock market volatility in a data-rich world. Applied Economics, 1-16.
[15]Li, X., Ma, J., Wang, S. Y., & Zhang, X. (2015). How does Google search affect trader positions and crude oil prices? Economic Modelling, 49, 162–171.
[16]Liberti, J. M., & Petersen, M. A. (2019). Information: Hard and soft. Review of Corporate Finance Studies, 8(1), 1-41.
[17]Neely, C. J., Rapach, D. E., Tu, J., & Zhou, G. (2014). Forecasting the equity risk premium: the role of technical indicators. Management science, 60(7), 1772-1791.
[18]Orosel, G. O. (1998). Participation costs, trend chasing, and volatility of stock prices. The Review of Financial Studies, 11(3), 521-557.
[19]Ogutu, J. O., Schulz-Streeck, T., & Piepho, H. P. (2012, December). Genomic selection using regularized linear regression models: ridge regression, lasso, elastic net and their extensions. In BMC proceedings (Vol. 6, No. 2, pp. 1-6). BioMed Central.
[20]Paye, B. S. (2012). ‘Déjà vol’: Predictive regressions for aggregate stock market volatility using macroeconomic variables. Journal of Financial Economics, 106(3), 527-546.
[21]Panagiotidis, T., Stengos, T., & Vravosinos, O. (2020). A principal component-guided sparse regression approach for the determination of bitcoin returns. Journal of Risk and Financial Management, 13(2), 33.
[22]Sermpinis, G., Tsoukas, S., & Zhang, P. (2018). Modelling market implied ratings using LASSO variable selection techniques. Journal of Empirical Finance, 48, 19-35.
[23]Wilcoxson, J., Follett, L., & Severe, S. (2020). Forecasting Foreign Exchange Markets Using Google Trends: Prediction Performance of Competing Models. Journal of Behavioral Finance, 1-11.
[24]Wenjie Ding & Khelifa Mazouz & Qingwei Wang, (2019). "Investor sentiment and the cross-section of stock returns: new theory and evidence," Review of Quantitative Finance and Accounting, Springer, vol. 53(2), pages 493-525, August.
[25]Welch, I., & Goyal, A. (2008). A comprehensive look at the empirical performance of equity premium prediction. The Review of Financial Studies, 21(4), 1455-1508.
[26]Zhang, Y., Ma, F., & Wang, Y. (2019). Forecasting crude oil prices with a large set of predictors: Can LASSO select powerful predictors?. Journal of Empirical Finance, 54, 97-117.
[27]Zweig, M. E. (1973). An investor expectations stock price predictive model using closed-end fund premiums. The Journal of Finance, 28(1), 67-78.
[28]Zhang, X. Z., Hu, Y., Xie, K., Zhang, W. G., Su, L. J., & Liu, M. (2015). An evolutionary trend reversion model for stock trading rule discovery. Knowledge-Based Systems,79, 27–35. |
| Description: | 碩士
國立政治大學
金融學系
108352005 |
| Source URI: | http://thesis.lib.nccu.edu.tw/record/#G0108352005 |
| Data Type: | thesis |
| DOI: | 10.6814/NCCU202100650 |
| Appears in Collections: | [金融學系] 學位論文
|
Files in This Item:
| File |
Description |
Size | Format | |
|---|
| 200501.pdf | | 873Kb | Adobe PDF2 | 0 | View/Open |
|
All items in 政大典藏 are protected by copyright, with all rights reserved.
|
