International Research Journal of Innovations in Engineering and Technology - IRJIET International Open Access, Monthly, Peer Reviewed, Reputed Journal ISSN (online): 2581-3048

Impact Factor (2025): 6.9

DOI Prefix: 10.47001/IRJIET

Forecasting Future Trends: An LSTM Approach to Identifying High Growth Sectors

Abstract

Predicting trends in the financial stock market is a challenging task for researchers due to its complex and dynamic nature. The stock market has always been complex due to the market’s volatility and non-linearity. Accurate forecasting is difficult, and forecasting errors can result in significant investment risks, even with techniques like diffusion modelling and forecasting. Understanding the pattern of the sector price of the particular company by predicting its financial growth and future development will be highly beneficial. This study optimizes a predictive machine learning model based on long-short term memory (LSTM) neural networks to predict the most performing sector in the Indian sector indices. Using historical data, the LSTM model is used to predict future sector developments. The historical data from the past five years was obtained via Yahoo Finance from January 1, 2019, to December 31, 2023. The proposed method is designed for the ten sectors of the Indian economy. An LSTM model is designed to predict the future sector performance. To predict the three months after, i.e, on April 30, 2024, the actual and predicted returns of each sector are computed. This method is used to choose the most progressive sector based on a ranking system. The proposed model indicates the high accuracy of the LSTM model.

Country : India

1 Heena J. Patel2 Dr. Prashant P. Pittalia

  1. Assistant Professor, M.K. Institute of Computer Studies, Bharuch-392001, Gujarat, India
  2. Professor, P.G. Department of Computer Science and Technology, Sardar Patel University-Vallabh Vidyanagar, Gujarat, India

IRJIET, Volume 9, Issue 8, August 2025 pp. 44-49

doi.org/10.47001/IRJIET/2025.908006

Full Paper
Download

References

  1. H. Markowitz, “Portfolio Selection,” J. Finance, vol. 7, no. 1, pp. 77–91, 1952, doi: 10.1111/j.1540-6261.1952.tb01525.x.
  2. Chaweewanchon, A., & Chaysiri, R. (2022). Markowitz Mean-Variance Portfolio Optimization with Predictive Stock Selection Using Machine Learning. International Journal of Financial Studies, 10(3), 64. https://doi.org/10.3390/ijfs10030064.
  3. Dariusz Kobielaa, Dawid Kreftaa, Weronika Krol´, Paweł Weichbroth “ARIMA vs LSTM on NASDAQ stock exchange data”, 26th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES 2022).
  4. www.NSE.india
  5. M. Kumbure, “Machine learning techniques and data Stock market forecasting: A literature Review of the portfolio optimization problem,” doi: 10.1016/j.eswa2022.116659.
  6. Tanya Garg, Daljeetsingh Bawa, “Evaluation of Statistics model for timeseries data forecasting”, Science and technology journal vol. II issue: I January 2023, ISSN:2312-3388, https/doi.org/10.2223/stj.2022.11.01.06
  7. K. Vikranth, P.S. Nethravathi and K. Krishna Prasad, “PRICE PREDICTION SYSTEM – A PREDICTIVE DATA ANALYTICS USING ARIMA MODEL”, ICTACT JOURNAL ON SOFT COMPUTING, JANUARY 2024, VOLUME: 14, ISSUE: 03, ISSN: 2229-6956 (ONLINE), DOI: 10.21917/ijsc 2024.0463.
  8. Kelvin J.L. Koa, “Diffusion Variational Autoencoder for Tackling Stochasticity in Multi-Step Regression Stock Price Prediction”, CIKM '23: Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, October 2023, Pages 1087 – 1096, https://doi.org/10.1145/3583780.3614844
  9. J, K., E, H., Jacob, M. S., & R, D. (2021). Stock price prediction based on an LSTM Deep learning model. 2021 International Conference on System, Computation, Automation and Networking (ICSCAN), 1–4. https://doi.org/10.1109/icscan53069.2021.9526491
  10. Ahire, P., Lad, H., Parekh, S., Kabrawala, S., Student, & Engineering, C. (2021). LSTM BASED STOCK PRICE PREDICTION.
  11. J. Sen, S. Mehtab, A. Dutta, and S. Mondal, "Precise Stock Price Prediction for Optimized Portfolio Design Using an LSTM Model," 2021 19th OITS International Conference on Information Technology (OCIT), Bhubaneswar, India, 2021, pp. 210-215, doi: 10.1109/OCIT53463.2021.00050.
  12. Tripathi, S. S., & Tripathi, S. (2022). Can stock prices be predicted? A Comparative study of LSTM and SVR for financial market forecast. TechRxiv. https://doi.org/10.36227/techrxiv.21158932.v2
  13. Pramod, & Pm, Mallikarjuna. (2021). Stock Price Prediction Using LSTM. Test Engineering and Management. 83. 5246-5251.
  14. Hiransha Ma, Gopalakrishnan E.Ab , Vijay Krishna Menonab, Soman K.P.*.,” NSE stock market prediction using deep learning model”, International Conference on Computational Intelligence and Data Science (ICCIDS 2018).
  15. Geeta Kolte, Varadraj Kini, Harikrishnan Nair, Prof. Suresh Babu K. S.,” Stock Market Prediction using Deep Learning” ISIN NO: 2321-9653,  IJRASET, https://doi.org/10.22214/ijraset.2022.41159
  16. Sen, J. (2021). Robust Portfolio Design and Stock Price Prediction Using an Optimized LSTM Model. 2021 IEEE 18th India Council International Conference (INDICON). OR Sen, Jaydip. “Robust Portfolio Design and Stock Price Prediction Using an Optimized LSTM Model.” 2021 IEEE 18th India Council International Conference (INDICON), 2021.
  17. Sen, Jaydip. “Analysis of Sectoral Profitability of the Indian Stock Market Using an LSTM Regression Model.” ArXiv (Cornell University), 2021.
  18. A.Chatterjee, H. Bhowmick, and J. Sen, "Stock Volatility Prediction using Time Series and Deep Learning Approach," 2022 IEEE 2nd Mysore Sub Section International Conference (MysuruCon), Mysuru, India, 2022, pp. 1-6, doi: 10.1109/MysuruCon55714.2022.9972559.

Copyright @ 2026-2017 IRJIET. All Right Reserved.

Developed by Byzero Technologies