Research Article
Tokyo Stock Exchange Prediction with a Hybrid Model of Lightgbm and DNN
@INPROCEEDINGS{10.4108/eai.26-5-2023.2334222, author={Yishuai Yang and Xuan Zhang and Shuyi Liu and Wenke Du}, title={Tokyo Stock Exchange Prediction with a Hybrid Model of Lightgbm and DNN}, proceedings={Proceedings of the 2nd International Conference on Mathematical Statistics and Economic Analysis, MSEA 2023, May 26--28, 2023, Nanjing, China}, publisher={EAI}, proceedings_a={MSEA}, year={2023}, month={7}, keywords={jpx tokyo stock exchange investment lightgbm dnn sharpe ratio}, doi={10.4108/eai.26-5-2023.2334222} }- Yishuai Yang
Xuan Zhang
Shuyi Liu
Wenke Du
Year: 2023
Tokyo Stock Exchange Prediction with a Hybrid Model of Lightgbm and DNN
MSEA
EAI
DOI: 10.4108/eai.26-5-2023.2334222
Abstract
As stock investment has become an increasingly mainstream way of wealth management, researchers have increasingly attached importance to the study of stock price prediction, and constantly used a variety of methods to predict its price trend. In this paper, we pay attention to the JPX Tokyo Stock Exchange Prediction. The dataset is provided by Kaggle platform. We hybrid LightGBM and DNN to predict the stock price. Sharpe Ratio is our evaluation metrics. The results show that our hybrid model owns the best performance with the highest Sharpe Ratio score 0.152, which is 0.041, 0.032, 0.004 higher than Xgboost, Lightgbm and DNN respectively.
Copyright © 2023–2024 EAI