• Ritesh Tandon

The foundation of the economy is the stock market. People used to have the notion that investing in the stock market included more risks. Performing analysis, forecasting, and selecting a stock to purchase have never been simple tasks. Traditional techniques of analysing fundamental and technical features have been used for a long time to predict the stock market. Machine learning has greatly improved the accessibility and accuracy of stock market forecasts. Many different techniques using Large Language Models (LLMs) have been utilised for stock market prediction. This study aims to compare several LLM techniques for stock market prediction via a review of the literature. The news headline dataset used in this comparative research is provided from Kaggle and covers the years 2010–2020. Additional historical data is obtained from Yahoo Finance and covers the years 2000–2010. Afterwards, the news headlines underwent text preparation. The study reveals that BERT has an accuracy of 86.25% and Fin BERT has an accuracy of 83.6% after thorough comparison with benchmark algorithms. The findings show that the system might be used in the stock market and provide important information on LLMs algorithms for stock data prediction and sentiment analysis using financial news headlines.

Stock market, trends analysis, Financial, BERT, Price prediction, machine learning.

"Prediction of Stock Market Trends Based on Large Language Models ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 9, page no.a615-a622, September-2024, Available :http://www.jetir.org/papers/JETIR2409071.pdf

"Prediction of Stock Market Trends Based on Large Language Models ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 9, page no. ppa615-a622, September-2024, Available at : http://www.jetir.org/papers/JETIR2409071.pdf