Journal of Computer Applications ›› 2022, Vol. 42 ›› Issue (1): 280-286.DOI: 10.11772/j.issn.1001-9081.2021020306

• Frontier and comprehensive applications • Previous Articles    

Application of Stacking-Bagging-Vote multi-source information fusion model for financial early warning

Lu ZHANG, Jiapeng LIU(), Dongmei TIAN   

  1. College of Economics and Management,China Jiliang University,Hangzhou Zhejiang 310018,China
  • Received:2021-03-02 Revised:2021-06-21 Accepted:2021-06-23 Online:2022-01-11 Published:2022-01-10
  • Contact: Jiapeng LIU
  • About author:ZHANG Lu, born in 1995, M. S. candidate. Her research interests include corporate finance, data mining.
    LIU Jiapeng, born in 1969, Ph. D., professor. His research interests include financial information.
    TIAN Dongmei, born in 1996, M. S. candidate. Her research interests include intelligent investment, quantitative trading.
  • Supported by:
    National Social Science Foundation of China(18BGL224)


张露, 刘家鹏(), 田冬梅   

  1. 中国计量大学 经济与管理学院,杭州 310018
  • 通讯作者: 刘家鹏
  • 作者简介:张露(1995—),女,浙江宁波人,硕士研究生,主要研究方向:公司金融、数据挖掘
    刘家鹏(1969—),男,山东日照人,教授,博士,CCF会员,主要研究方向:金融信息; 田东梅(1996—),女,河南南阳人,硕士研究生,主要研究方向:智能投资、量化交易。
  • 基金资助:


Ensemble resampling technology can solve the problem of imbalanced samples in financial early warning research to some extent. Different ensemble models and different ensemble resampling technologies have different suitabilities. It is found in the study that Up-Down ensemble sampling and Tomek-Smote ensemble sampling were respectively suitable for Bagging-Vote ensemble model and Stacking fusion model. Based on the above, a Stacking-Bagging-Vote (SBV) multi-source information fusion model was built. Firstly, the Bagging-Vote model based on Up-Down ensemble sampling and the Stacking model based on Tomek-Smote sampling were fused. Then, the stock trading data were added and processed by Kalman filtering, so that the interactive fusion optimization of data level and model level was realized, and the SBV multi-source information fusion model was finally obtained. This fusion model not only has a great improvement in the prediction performance by taking into account prediction accuracy and prediction precision simultaneously, but also can select the corresponding SBV multi-source information fusion model to perform the financial early warning to meet the actual needs of different stakeholders by adjusting the parameters of the model.

Key words: financial early warning, multi-source information fusion, ensemble resampling technology, Stacking-Bagging-Vote (SVB) model, Kalman filtering


集成重采样技术可以在一定程度上解决财务预警研究中样本的不平衡性难题,而不同的集成模型与不同的重采样集成技术有不同的适配性。研究发现,Up-Down集成采样与Tomek-Smote集成采样分别适配于Bagging-Vote集成模型和Stacking融合模型。基于此,构建了Stacking-Bagging-Vote (SBV)多源信息融合模型。首先,将基于Up-Down集成采样的Bagging-Vote模型与基于Tomek-Smote采样的Stacking模型进行融合;然后,加入股票的交易数据,并对该数据用卡尔曼滤波进行处理,从而形成数据层次和模型层次的交互式融合优化;最终,得到SBV多源信息融合模型。该融合模型不仅在预测性能上有了较大的提升,能较好地兼顾模型的预测准确度和预测精确率,并且可以根据利益相关者的实际需要,通过调整模型参数,来选择对应的SBV多源信息融合模型进行财务预警预测。

关键词: 财务预警, 多源信息融合, 集成重采样技术, Stacking-Bagging-Vote模型, 卡尔曼滤波

CLC Number: