The effectiveness of stock prediction models: evidence from time series analysis and machine learning scenarios
Download as PDF
DOI: 10.23977/FMESS2022.065
Author(s)
Qinglin Chen, Shuya Ma, Ruochen Yang
Corresponding Author
Shuya Ma
ABSTRACT
In the era of big data, stock prediction models usher in a new era. In this paper, we will discuss several state-of-art stock prediction models, including decision tree-based model, neural network model and time series model. Based on the analysis we figure out the applicability and limitations of each model, as well as demonstrate the future prospect. Overall, these results shed light on how the application of machine learning and big data can improve the accuracy and reliability of stock price predictions.
KEYWORDS
Stock price predict, Deep learning, ANN, DNN, Random Forest, XGBoost, LightGBM, Time Series, ARIMA