Research on the Prediction of A-Share 'High Stock Dividend' Phenomenon—A Feature Adaptive Improved Multi-Layers Ensemble Model
Autor: | Bingwen Li, Jinshi Zhao, Yi Fu, Qianwen Bi |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2021 |
Předmět: |
Computer science
General Physics and Astronomy lcsh:Astrophysics 02 engineering and technology computer.software_genre Article 0502 economics and business Genetic algorithm lcsh:QB460-466 0202 electrical engineering electronic engineering information engineering Feature (machine learning) feature adaptive improvement lcsh:Science 050208 finance Ensemble forecasting multi-layers stacking algorithm 05 social sciences Base (topology) A share high stock dividend lcsh:QC1-999 Information extraction financial market Dividend 020201 artificial intelligence & image processing lcsh:Q Data mining F1 score computer lcsh:Physics |
Zdroj: | Entropy, Vol 23, Iss 416, p 416 (2021) Entropy Volume 23 Issue 4 |
ISSN: | 1099-4300 |
Popis: | Since the “high stock dividend” of A-share companies in China often leads to the short-term stock price increase, this phenomenon’s prediction has been widely concerned by academia and industry. In this study, a new multi-layer stacking ensemble algorithm is proposed. Unlike the classic stacking ensemble algorithm that focused on the differentiation of base models, this paper used the equal weight comprehensive feature evaluation method to select features before predicting the base model and used a genetic algorithm to match the optimal feature subset for each base model. After the base model’s output prediction, the LightGBM (LGB) model was added to the algorithm as a secondary information extraction layer. Finally, the algorithm inputs the extracted information into the Logistic Regression (LR) model to complete the prediction of the “high stock dividend” phenomenon. Using the A-share market data from 2010 to 2019 for simulation and evaluation, the proposed model improves the AUC (Area Under Curve) and F1 score by 0.173 and 0.303, respectively, compared to the baseline model. The prediction results shed light on event-driven investment strategies. |
Databáze: | OpenAIRE |
Externí odkaz: |