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{198049,
        author = {Kunal Bensla and Vivek Bandi and Aditya Chauhan and Shreyash Gupta and Dr. Dnyaneshwar Bavkar},
        title = {FinSight: AI Based Stock Market Trend Prediction using LSTM with Sentiment Analysis},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {7953-7960},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=198049},
        abstract = {Stock markets are hard to predict because prices change due to many factors at once, and no single model works well for all kinds of stocks. In this paper we present FinSight, a hybrid prediction system that combines Long Short-Term Memory (LSTM) networks with XGBoost to forecast the next-day closing price for NIFTY50 stocks. One of the key ideas in our system is that we separate stocks into two groups stable and volatile based on their recent price behaviour, and we train a separate model for each group. The LSTM part learns patterns from historical price sequences, and then XGBoost takes those learned features and produces the final price prediction. We also built a small pipeline that automatically pulls the latest data from Yahoo Finance so the system always works on fresh data. We tested FinSight on twenty NIFTY50 stocks over ten years of data and got an average R² of 0.93, RMSE of 97.4, MAPE of 2.11%, and Directional Accuracy of 71.3%. These results are better than standalone LSTM, BiLSTM, CNN–LSTM, and classical statistical models on all four metrics.},
        keywords = {Stock Market Prediction, LSTM, XGBoost, Hybrid Deep Learning, Volatility Modelling, NIFTY50, Feature Engineering, Gradient Boosting, Financial Time Series.},
        month = {April},
        }