Stock price prediction study based on LSTM and random forest model

Yunkai He1, * , Bo Yang2, Yifan Yao3, Zikai Lu4, Liqun Yu5

(1: Nanchang Hangkong University, Jiangxi, China

 2: Xian Innovation College of Yanan University, Shanxi, China 

3: Hubei University of Technology, Hubei, China 4: Jiangsu Ocean University, Jiangsu, China 5: Huaiyin Normal University, Jiangsu, China)

ABSTRACT 

The growing impact of global climate change on the economy and financial markets highlights the importance of environmental factors in the financial sector. The purpose of this study is to explore the correlation between environmental factors and the overall performance of the stock market, and the short‐term impact of extreme weather events on the stock prices of specific industries (e. g., energy industries), and to build a commodity price prediction model to provide investors with more comprehensive and accurate financial market analysis and decision support. Through multi‐source data collection and analysis, we found the correlation between environmental factors and the overall stock performance index, and revealed the impact of extreme weather events on energy stock prices. Meanwhile, the LSTM and random forest regression model were used to predict commodity prices, revealing the importance of environmental factors in financial markets, and providing a useful reference for the study of the correlation between environmental factors and financial markets. 

Keywords: Climate Change; Financial Markets; Environmental Factors; Emergencies; Stock Forecast

REFERENCES 

[1] Fan Jin, Li Shanshan, Feng Yumeng, Zhao Zhi Yang & He Sheng. Application of wavelet‐LSTM model in trend prediction of pulmonary tuberculosis. The Journal o f Preventive Medical Intelligence 1‐5. 

[2] Zhou Xiang, Zhang Shiming, Su Linpeng & Zhang Shouping. Preof monthly preci pitation based on attention mechanism and LSTM‐CCN. The Peopleʹs Yangtze Rive r 1‐9. 

[3] Qiao Shengyang, Xu Huiying, Zhu Xinzhong, Zhou Yuhao, Wei Yuanwang & Zha ng Jinjia. contactless heart rate estimation based on deep spatiotemporal feature m odel. Journal of Jiaxing College 1‐10. 

[4] Ding Hailan & Qi Kunyu. Automatic extraction of Chinese text topic sentences ba sed on the TextRank algorithm and similarity. Journal of Jilin University (Engineer ing Edition) 1‐9. 62 

[5] LAN Yunchuan, Liao Xiaoqiang & Qiu Siqi. The port crane bearing group conside ring the constraints of maintenance personnel. Industrial Engineering and Manage ment 1‐15. 

[6] Pan Baisong, Xue Shuchen, Xie Shaojun & Li Yifan. Method for predicting residua l life of harmonic reducer based on soft wheel crack extension. Computer Integrat ed Manufacturing System 1‐22. 

[7] MA Kai,SHEN Chaopeng,XU Ziyue & HE Daming.Transfer learning framework for streamflow prediction in large‐scale transboundary catchments:Sensitivity analysis and applicability in data‐scarce basins.Journal of Geographical Sciences1‐26. 

[8] Yan Yan, Qian Xingying, Yan Pengbin & Yang Jie. Federated learning statistical pr ediction of location big data and differential privacy protection methods. Compute r applications 1‐12. 

[9] Wenzhuo Gao,Fanghao Liu,Chengxuan Li,Mengyao Shi,Aiqing Lin,Yongjun Dong & Jingfu Guo.(2024).A portable terminal for acoustic monitoring and online recogniti on of bats with CNN‐LSTM.Measurement Science and Technology(7).

[10] Xikun Wei,Guojie Wang,Paula Farina Grosser & Britta Schmalz.(2024).Using explain able artificial intelligence (XAI) methods to understand the nonlinear relationship b etween the Three Gorges Dam and downstream flood.Journal of Hydrology: Regio nal Studies101776‐.

Yunkai He, Bo Yang, Yifan Yao, Zikai Lu, Liqun Yu.pdf