📄 Abstract
This study examines how well traditional statistical methods and modern techniques perform in predicting stock prices in the IT and automobile sectors. With stock markets becoming more complex and unpredictable, there is a need for better forecasting methods. The main objective of this study is to compare the effectiveness of the Long Short-Term Memory (LSTM) model with the traditional ARIMA model in predicting stock price movements. Traditional forecasting methods often struggle to capture sudden changes and complex patterns in stock prices. Because of this, their predictions may not always be accurate in real market conditions. This study attempts to overcome these limitations by using more flexible and adaptive approaches that can better reflect actual market behavior. This study uses two different approaches for comparison: The ARIMA model, implemented using EViews The LSTM model, developed using Python and visualized with Matplotlib The analysis is based on monthly stock price data from 2020 to 2025 for ten companies: IT Sector: TCS, Infosys, Oracle Financial Services, L&T, Persistent Systems Automobile Sector: Bajaj Auto, Maruti Suzuki, Hero MotoCorp, Ashok Leyland, Mahindra & Mahindra A simple random sampling method was used to select: 5 companies from the IT sector 5 companies from the automobile sector The results show that the LSTM model generally provides better predictions than the ARIMA model, especially when the market is unstable. In the IT sector, companies such as Oracle Financial Services and Persistent Systems showed results closer to actual trends when using LSTM. In the automobile sector, Mahindra & Mahindra and Bajaj Auto also showed more accurate predictions with the LSTM model. The findings suggest that using modern forecasting techniques can help investors and managers make better decisions. These methods can improve risk management, provide clearer insights into market trends, and support better financial planning. Companies that adopt such approaches may gain an advantage in competitive and changing markets. The study concludes that the LSTM model performs better than the ARIMA model in predicting stock prices, particularly in uncertain market conditions. More advanced forecasting methods can offer improved accuracy and help in making better investment and financial decisions in both IT and automobile sectors.
🏷️ Keywords
📚 How to Cite:
N.Amaranath, Dr. K. V. Geetha Devi , A STUDY ON LEVERAGING ARTIFICIAL INTELLIGENCE TO PREDICT STOCK MARKET TRENDS OF INFORMATION TECHNOLOGY & AUTOMOBILE COMPANIES-A COMPREHENSIVE ANALYSIS , Volume 13 , Issue 6, June 2026, EPRA International Journal of Economics, Business and Management Studies (EBMS) , Pages: 24 - 30 ,