基于趨勢分解算法的深度學習選股方法研究

武承慧; 張宏建

0
0
瀏覽
下載

摘要
關鍵詞
基金信息
論文圖表
動態公開評議
相關論文
評論

Research on Deep Learning Stock Selection Method Based on Trend Decomposition Algorithm

首發時間：2023-06-27

Wu Cheng-Hui ^{1
2}
Wu Cheng-Hui(2001-),Student, research direction is data analysis and deep learning modeling
Zhang Hong-Jian ³
Zhang Hong-Jian(1998-),Student, research direction is artificial intelligence and neural network computing

1、School of Materials Science and Technology, Beijing Forestry University，Beijing 100083
2、School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing 100876
3、School of Electronic Engineering , Beijing University of Posts and Telecommunications, Beijing 100876

Abstract：Some studies using machine learning and deep learning models did not fully explore other indicator features that affect stock price trends, resulting in significant prediction errors and difficulty in directly applying the prediction results to obtain excess returns. Therefore, it is necessary to establish an efficient deep learning model based on stock characteristics and fully explore the factors that affect stock price trends to improve prediction accuracy.In view of the shortcomings of traditional stock trend prediction, this paper constructs LSTM-BP neural network based on Tianniuxu optimization for stock price prediction, and constructs PCA-BP neural network model based on particle swarm optimization based on multi angle correlation analysis for trend prediction. Taking into account both price prediction and trend prediction dimensions, construct a deep quantitative stock selection method. In this process, a stock trend decomposition judgment algorithm is proposed to identify and classify the stock data, improve the data utilization, build a new data set, and use the particle swarm optimization to adjust and optimize the parameters.The results of strategy backtesting show that compared to other deep learning strategies and benchmark strategies, the stock selection method and strategy proposed in this article have significantly improved in terms of victory and return. This indicates that the model has good predictive ability and application potential, and can provide effective decision support for stock investment.

keywords： Trend decomposition Deep learning Parameter optimization Stock selection methods Quantitative strategy

點擊查看論文中文信息

基于趨勢分解算法的深度學習選股方法研究

武承慧 ¹
Wu Cheng-Hui(2001-),Student, research direction is data analysis and deep learning modeling
張宏建 ²
Zhang Hong-Jian(1998-),Student, research direction is artificial intelligence and neural network computing

1、北京林業大學材料科學與技術學院，北京 100083
2、北京郵電大學電子工程學院，北京 100876

摘要：部分研究使用機器學習和深度學習模型時未充分挖掘影響股票價格趨勢的其他指標特征，導致了較大的預測誤差且預測結果很難直接應用于獲得超額收益。因此，有必要針對股票特征建立高效的深度學習模型，并充分挖掘影響股票價格趨勢的因子以提高預測精準度。本文針對傳統股票趨勢預測的不足，構建了基于天牛須優化的LSTM-BP神經網絡進行股票價格預測，構建了基于多角度相關性分析的基于粒子群優化的PCA-BP神經網絡模型進行趨勢預測。綜合考慮價格預測和趨勢預測兩個維度，構建深度量化選股方法。并在此過程中提出了一種股票趨勢分解判定算法對股票數據進行識別和分類標記，提升了數據利用率，構建新的數據集并使用基于粒子群優化算法進行參數調整和優化。策略回測結果結果顯示，相較于其他深度學習策略和基準策略，本文提出的選股方法和選股策略在勝率和收益率方面均有大幅提升。表明該模型具有較好的預測能力和應用潛力，可為股票投資提供有效的決策支持。

關鍵詞：深度學習趨勢分解參數優化選股方法量化策略

基金：

論文圖表：

引用

導出參考文獻

.txt

.ris

.doc

Wu Cheng-Hui,Zhang Hong-Jian. Research on Deep Learning Stock Selection Method Based on Trend Decomposition Algorithm[EB/OL]. Beijing:Sciencepaper Online[2023-06-27]. http://www.gulakh.com/releasepaper/content/202306-88.

No.****

動態公開評議

共計0人參與

動態評論進行中

評論

全部評論

0/1000

論文編號	202306-88
論文題目	基于趨勢分解算法的深度學習選股方法研究
文獻類型
收錄期刊	上傳封面中文期刊英文期刊期刊名稱（中文）期刊名稱（英文）年，卷（）上傳封面中文專著英文專著書名（中文）書名（英文）出版地出版社出版年上傳封面中文譯著英文譯著書名（中文）書名（英文）出版地出版社出版年上傳封面中文論文集英文論文集編者.論文集名稱（中文） [c]. 出版地出版社出版年， - 編者.論文集名稱（英文） [c]. 出版地出版社出版年，- 上傳封面中文文獻英文文獻期刊名稱（中文）期刊名稱（英文）日期-- 在線地址http:// 上傳封面中文文獻英文文獻文題（中文）文題（英文）出版地出版社,出版日期-- 上傳封面中文文獻英文文獻文題（中文）文題（英文）出版地出版社,出版日期--
英文作者寫法：中外文作者均姓前名后，姓大寫，名的第一個字母大寫，姓全稱寫出，名可只寫第一個字母，其后不加實心圓點“.”, 作者之間用逗號“，”分隔，最后為實心圓點“.”, 示例1：原姓名寫法：Albert Einstein,編入參考文獻時寫法：Einstein A. 示例2：原姓名寫法：李時珍；編入參考文獻時寫法：LI S Z. 示例3：YELLAND R L,JONES S C,EASTON K S,et al.