Transformer-based Model for Predicting Stock Market Trends

View at publisher Summarise with VIRAT
Authors: Shreyansh Goswami, Suditi Soni, Shivam Dixit, Anuj Singh
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Stock market trend forecasting is a complex task due to the market’s volatile and non-linear behavior. This paper presents a hybrid model combining CNN, Vision Transformer (ViT), Swin Transformer, and Random Forest to improve prediction accuracy. The proposed approach achieved 96.8% accuracy, outperforming individual models in both precision and generalization.

Fields of Study & Subjects

Stock Market Forecasting Methods Time Series Analysis and Forecasting Forecasting Techniques and Applications

Publication details

Journal / source
CRC Press eBooks
Pages
424–430
Publication date
25 March 2026
Language
EN
Document type
Book chapter