Forecasting Stock Market Trends with LSTM-Based Deep Learning Models

• Author(s): Prince Verma; Samriddhi Singh
• Paper ID: 1716441
• Page: 1889-1896
• Published Date: 20-04-2026
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 9 Issue 10 April-2026

Abstract

Forecasting movements in the stock market has long been one of the most desired yet frustrating tasks in data science. Stock markets are volatile, emotional, and driven by factors that no individual model could ever hope to capture entirely. In this study, we analyze and compare how well LSTM neural networks can predict stock movement trends and, more specifically, what impact the architecture itself may have. Using ten years of daily trade data (from 2014 through 2024) for three stocks – Apple Inc. (AAPL), Reliance Industries (RELIANCE.NS), and NIFTY 50 index, we have compared how well five different architectures – starting with a simple one-layer LSTM to a more sophisticated approach of a three-layer stacked LSTM with attention mechanisms – fared in their predictions. Our feature selection ranges from technical analysis tools, such as RSI, MACD, and Bollinger bands, to economic indicators, like VIX and spread between treasury yields. Of our models, the stacked LSTM with attention turned out to have the best performance, with a MAPE of 1.73% and accuracy in predicting price direction of 84.6%, significantly better than any other model tried (ARIMA, GRU, XGBoost, LSTMs). We have tested our models on the stock market crash caused by COVID-19 in early 2020 to see their performance during out-of-domain situations, i.e., when market conditions drastically change, as well as what those results imply about the use of these models in practice.

Keywords

LSTM, Stock Market Prediction, Deep Learning, Time Series Forecasting, Technical Indicators, Attention Mechanism, Recurrent Neural Network, Financial Analytics

Citations

IRE Journals:
Prince Verma, Samriddhi Singh "Forecasting Stock Market Trends with LSTM-Based Deep Learning Models" Iconic Research And Engineering Journals Volume 9 Issue 10 2026 Page 1889-1896 https://doi.org/10.64388/IREV9I10-1716441

IEEE:
Prince Verma, Samriddhi Singh "Forecasting Stock Market Trends with LSTM-Based Deep Learning Models" Iconic Research And Engineering Journals, 9(10) https://doi.org/10.64388/IREV9I10-1716441