Loading...
|
Please use this identifier to cite or link to this item:
https://nccur.lib.nccu.edu.tw/handle/140.119/139548
|
| Title: | 機器學習結合波動聚集分析之投資策略實證研究
An Empirical Study of Investment Strategies Based on Machine Learning and Volatility Cluster Analysis |
| Authors: | 李強
Li, Qiang |
| Contributors: | 廖四郎
Liao, Szu-Lang
李強
Li, Qiang |
| Keywords: | 機器學習
因子合成
波動聚集
量化投資
Machine Learning
Factor Composition
Volatility Clustering
Quantitative Investment |
| Date: | 2022 |
| Issue Date: | 2022-04-01 15:02:02 (UTC+8) |
| Abstract: | 量化投資和機器學習在大數據時代充分展現了其獨特的優勢和魅力，兩者結合更是如虎添翼。機器學習不僅可以彌補量化投資的短板，還可以為量化投資的發展提供新的思路和方向。本文主要研究是否可以通過機器學習算法進行因子合成，以及該方法是否比傳統方法更有效。選取波動率、年化收益率、最大回撤、信息比率、夏普比率等評價指標進行因子分層回測結果的對比分析。
本文認為機器學習算法對量化投資和股票預測具有一定的重要性影響，為投資者的決策提供可行的解決方案。另外，本文詳細介紹了波動聚集現象和金融時間序列模型。然後本文將波動聚集性作為因子加入到策略的機器學習部分進行應用，以原策略為對照，並對回測結果進行詳細對比分析。
綜上可見，波動聚集現象的實際應用是值得研究的，這樣可以提高量化策略的性能和穩健性，同時對波動聚集現象的應用和發展提供了新想法。本文對 XGBoost 算法和量化投資中的波動聚集現象進行了研究和改進，為滬深 300 股票市場的量化投資者提供了一個新觀點。
Quantitative investment and machine learning have adequately demonstrated their unique advantages and charms in this big data era and they become even more powerful by combination. Machine learning not only help to overcome the disadvantages of quantitative investment, but also provides new ideas and directions for its development. This paper mainly studies whether machine learning algorithm can be applied in factor composition, and whether its effect is better than the traditional method. Evaluation indexes such as volatility, annualized rate of return, maximum drawdown, information ratio and Sharpe ratio are selected to compare and analyze the results of factors` layered back test.
This paper points out that machine learning algorithm has guiding significance for quantitative investment and stock prediction, providing investors a feasible plan for decision-making. In addition, this paper introduces the phenomenon of volatility clustering and the financial time series model in detail. Then, this paper adds the volatility clustering as a factor to the machine learning part of the strategy, and compares and analyzes the back test results in detail by taking the initial strategy as a comparison.
We concluded that the practical application of volatility clustering is worth studying, which can improve the performance and robustness of quantitative strategy, and also provide a new idea for the application and development of volatility clustering. Our research and improvement on XGBoost algorithm and volatility clustering provide a new perspectives for quantitative investors in CSI 300. |
| Reference: | [1] 肖晞暉，（2018）。基於大資料和機器學習的量化選股模型研究。華中師範大學。
[2] 鄒玉江，（2018）。基於機器學習的滬深 300 指數走勢預測研究。山東大學.
[3] 楊世林，（2018）。基於聚寬量化投資平臺的股票多因子策略應用。浙江大學。
[4] Harris M, Raviv A, (1993). Differences of opinion make a horse race. The Review of Financial Studies, 6(3):473-506.
[5] Harry Markowitz, (1952). Portfolio selection Journal of Finance. March, 7(1):77-91.
[6] Black Fischer, Myron Scholes, (1973). The Pricing of Options and Corporate Liabilities. Journal of Political Economy, 81(3):637-654.
[7] Lukac, Brorsen, Irwin, (1986). A comparison of twelve technical trading systems with market efficiency implications. Station bulletin - Dept. of Agricultural Economics, Purdue University, Agricultural Experiment Station (USA).
[8] V.N Vapnik, (1995). The Nature of Statistical Learning Theory. New York: Springer-Verlag.
[9] Leo Breiman, (2001). Random Forests. Machine Learning, 45(1):5-32.
[10] Min, Lee, (2005). Bankruptcy prediction using support vector machine with optimal choice of kernel function parameters. Expert Systems with Applications, 28(4):603-614.
[11] Kim K.J, Han I, (2000). Genetic algorithms approach to feature discretization in artificial neural networks for the prediction of stock price index. Expert Systems with Applications, 19(2):125-132.
[12] Chen.Y.S, Cheng.C.H, (2009). Evaluating industry performance using extracted RGR rules based on feature selection and rough sets classifier. Expert Systems with Applications, 36(5):9448-9456.
[13] MC Lee, (2009). Using support vector machine with a hybrid feature selection method to the stock trend prediction. Expert Systems with Applications, 36(8):10896-10904.
[14] Majhi, Panda, Sahoo, (2009). Development and performance evaluation of FLANN based model for forecasting of stock markets. Expert Systems with Applications, 36(3):6800-6808.
[15] Ticknor, Jonathan, (2013). A Bayesian regularized artificial neural network for stock market forecasting. Expert Systems with Applications, 40(14):5501-5506.
[16] Somani, Talele, Sawant, (2015). Stock market prediction using Hidden Markov Model. Information Technology & Artificial Intelligence Conference.
[17] Ballings, Poel, Hespeels, (2015). Evaluating multiple classifiers for stock price direction prediction. Expert Systems with Applications, 42(20):7046-7056.
[18] Chen, Carlos, (2016). XGBoost: A Scalable Tree Boosting System.
[19] Mandelbrot B, (1963). New Methods in Statistical Economics. Journal of Political Economy, 71(5):421-440.
[20] Engle R F, (1982). Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation. Econometrica, 50(4):987-1007.
[21] Tim Bollerslev, (1986). Generalized autoregressive conditional heteroskedasticity. Journal of Econometrics, 31(3):307-327.
[22] Zakoian J M, (1994). Threshold heteroskedastic models. Journal of Economic Dynamics and Control, 18(5):931-955.
[23] Nelson, Daniel B, (1991). Conditional Heteroskedasticity in Asset Returns: A New Approach. Modelling Stock Market Volatility, 59(2):347-0.
[24] Bollerslev T, (1996). Fractionally integrated generalized autoregressive conditional heteroskedasticity. Journal of Econometrics, 74.
[25] Michael D. McKenzie, Heather Mitchell, Robert D, Brooks & Robert W, (2001). Power ARCH modelling of commodity futures data on the London Metal Exchange. The European Journal of Finance, 7(1):22-38.
[26] Chin Wen Cheong, Nor A H S M, Isa Z, (2007). Asymmetry and long-memory volatility: Some empirical evidence using GARCH. Physica A, 373(none):651-664.
[27] 吳微，陳維強，劉波，（2001）。用 BP 神經網路預測股票市場漲跌。大連理工大學學報，2001(01):9-15。
[28] 彭麗芳，孟志青，姜華，田密，（2006）。基於時間序列的支援向量機在股票預測中的應用。計算技術與自動化，2006(03):88-91。
[29] 錢穎能，胡運發，（2007）。用樸素貝葉斯分類法選股。電腦應用與軟體，2007(06):90-92。
[30] 左輝，樓新遠，（2008）。基於貝葉斯分類的選股方法。電腦知識與技術，2008(10):173-176+185。
[31] 余樂安，汪壽陽，（2009）。基於核主元聚類的股票分類。系統工程理論與實踐，29(12):1-8。
[32] 吳曼琪，（2010）。基於 K 均值聚類的 ST 股票分類研究及投資策略。中國城市經濟，2010(08):26+29。
[33] 劉毅（2012）。因子選股模型在中國市場的實證研究。復旦大學。
[34] 蘇治，傅曉媛，（2013）。核主成分遺傳演算法與 SVR 選股模型改進。統計研究，30(05):54-62。
[35] 曹正鳳，紀宏，謝邦昌，（2014）。使用隨機森林演算法實現優質股票的選擇。首都經濟貿易大學學報，16(02):21-27。
[36] 王淑燕，曹正鳳，陳銘芷，（2016）。隨機森林在量化選股中的應用研究。運籌與管理，25(03):163-168+177。
[37] 王莉，（2016）。基於人工智慧演算法的股票價格波動規律預測方法研究。吉林大學。
[38] 張昊，紀宏超，張紅宇，（2017）。XGBoost 演算法在電子商務商品推薦中的應用。物聯網技術，7(02):102-104。
[39] 淩筱玥，（2017）。基於 XGBoost 演算法的上證指數預測方案設計研究。上海師範大學。
[40] 田浩，（2018）。基於 XGBoost 的滬深 300 量化投資策略研究。上海師範大學。
[41] 唐齊鳴，陳健，（2001）。中國股市的 ARCH 效應分析。世界經濟，2001(03):29-36。
[42] 惠曉峰，柳鴻生，胡偉，et al，（2003）。基於時間序列 GARCH 模型的人民幣匯率預測。金融研究，2003(5)。
[43] 曹野，（2012）。基於 GARCH 族模型的黃金價格收益率及波動性研究。價值工程，2012(02):163-165。
[44] 周好文，徐守喜，謝金靜，(2012)。過度關注與噪音交易。雲南財經大學學報，28(3)。 |
| Description: | 碩士
國立政治大學
金融學系
107352040 |
| Source URI: | http://thesis.lib.nccu.edu.tw/record/#G0107352040 |
| Data Type: | thesis |
| DOI: | 10.6814/NCCU202200358 |
| Appears in Collections: | [金融學系] 學位論文
|
Files in This Item:
| File |
Description |
Size | Format | |
|---|
| 204001.pdf | | 3268Kb | Adobe PDF2 | 0 | View/Open |
|
All items in 政大典藏 are protected by copyright, with all rights reserved.
|
