Stock prediction under COVID-19 based on LSTM

Qi, Yongrui; Yu, Wenbo; Deng, Yancong

doi:10.1109/ipec51340.2021.9421323

Cited by 5 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, the number of decision trees and the number of features randomly selected by each node of the decision tree are ought to be set distinctly for different research problems. Based on Qi et al's study, [12] we set the number of decision trees to be 500, and the number of features selected randomly by each node of the decision tree is log2 d≈7. LSTM neural network was employed in technical analysis and sentimental analysis in this essay.…”

Section: 3model Explanationmentioning

confidence: 99%

Macroeconomic Factors Modeling Optimization in Stock Prediction Using Machine Learning

Chen¹

2022

Advances in Economics, Business and Management Research

View full text Add to dashboard Cite

Stock prediction has been a focus of research in recent years. Traders are seeking to acquire an effective model to predict the stock prices in the future to make investments and earn arbitrages. Methods in machine learning and deep learning have been broadly used in economic model buildings. However, important factors like macroeconomic environments and government regulations were not considered effective in most cases. With different events happening in various situations, the influences can be extremely different. In this essay, we will use machine learning methods to analyze the impacts of various conditions and how this will optimize prediction accuracy. In the meantime, it will offer a new perspective of view to conduct technical and sentimental analysis based on the premise of fundamental analysis.

show abstract

Section: 3model Explanationmentioning

confidence: 99%