Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{196340,
        author = {Gracey sanuja Das and Dr.Devang Thakar},
        title = {Stock market predicition system under market realities},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {2874-2880},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=196340},
        abstract = {Stock price prediction is getting very difficult now a days as the market keep on changing and it is getting very unpredictable due to many reasons affecting it regularly. Real markets have noisy data, it is volatile, and they frequently change as being calm and turbulent in many phases without even giving any warnings.
Many other models mainly focus on accuracy of the model for prediction without considering the cost and other changing market behavior such as volatility, market regime shifts and many more. So this the main gap I am going to cover in my study of research.
My study uses the day-by-day data of RELIANCE.NS starting from 2016. From this we are going to extract the features like returns, volatility, trends, RSI and MACD. After studying these features, we are going to see the how the model judges the accuracy based on these parameters. How the model is accurate enough to predict the next day price based on its historical data even if the market has a crisis. I will be comparing several models through this data to see which model performs the best even if the data is noisy and market conditions makes it unstable to predict it.
Among all the methods tested, I found the best accurate prediction by XGBoost as I handles the market complexity better than any other simple model. The LSTM also performed very well as helped to tackle the trend-based situations during the market instability. So overall, this shows how data science methods are used in the best way to show how market would behave in future even after uncertainty.},
        keywords = {},
        month = {April},
        }