Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Advanced Stock Market Prediction Using Long Short-Term Memory Networks: A Comprehensive Deep Learning Framework

Rajneesh Chaudhary

TL;DR

The paper tackles short-term NASDAQ tech stock forecasting by integrating historical price data with sentiment signals using a sentiment-aware LSTM framework. It introduces a 60-day sliding-window approach with moving-average features and VADER-based sentiment, implemented in a web-accessible visualization tool. Empirically, the method achieves strong accuracy, with Apple reaching a MAPE of $2.72\%$ and sub-$3\%$ MAPE for other stocks, outperforming ARIMA baselines. The work demonstrates the value of combining quantitative time series with qualitative sentiment signals for practical, real-time investment insights, while outlining avenues for future improvements such as attention-based architectures and macroeconomic data integration.

Abstract

Predicting stock market movements remains a persistent challenge due to the inherently volatile, non-linear, and stochastic nature of financial time series data. This paper introduces a deep learning-based framework employing Long Short-Term Memory (LSTM) networks to forecast the closing stock prices of major technology firms: Apple, Google, Microsoft, and Amazon, listed on NASDAQ. Historical data was sourced from Yahoo Finance and processed using normalization and feature engineering techniques. The proposed model achieves a Mean Absolute Percentage Error (MAPE) of 2.72 on unseen test data, significantly outperforming traditional models like ARIMA. To further enhance predictive accuracy, sentiment scores were integrated using real-time news articles and social media data, analyzed through the VADER sentiment analysis tool. A web application was also developed to provide real-time visualizations of stock price forecasts, offering practical utility for both individual and institutional investors. This research demonstrates the strength of LSTM networks in modeling complex financial sequences and presents a novel hybrid approach combining time series modeling with sentiment analysis.

Advanced Stock Market Prediction Using Long Short-Term Memory Networks: A Comprehensive Deep Learning Framework

TL;DR

The paper tackles short-term NASDAQ tech stock forecasting by integrating historical price data with sentiment signals using a sentiment-aware LSTM framework. It introduces a 60-day sliding-window approach with moving-average features and VADER-based sentiment, implemented in a web-accessible visualization tool. Empirically, the method achieves strong accuracy, with Apple reaching a MAPE of and sub- MAPE for other stocks, outperforming ARIMA baselines. The work demonstrates the value of combining quantitative time series with qualitative sentiment signals for practical, real-time investment insights, while outlining avenues for future improvements such as attention-based architectures and macroeconomic data integration.

Abstract

Predicting stock market movements remains a persistent challenge due to the inherently volatile, non-linear, and stochastic nature of financial time series data. This paper introduces a deep learning-based framework employing Long Short-Term Memory (LSTM) networks to forecast the closing stock prices of major technology firms: Apple, Google, Microsoft, and Amazon, listed on NASDAQ. Historical data was sourced from Yahoo Finance and processed using normalization and feature engineering techniques. The proposed model achieves a Mean Absolute Percentage Error (MAPE) of 2.72 on unseen test data, significantly outperforming traditional models like ARIMA. To further enhance predictive accuracy, sentiment scores were integrated using real-time news articles and social media data, analyzed through the VADER sentiment analysis tool. A web application was also developed to provide real-time visualizations of stock price forecasts, offering practical utility for both individual and institutional investors. This research demonstrates the strength of LSTM networks in modeling complex financial sequences and presents a novel hybrid approach combining time series modeling with sentiment analysis.
Paper Structure (37 sections, 6 equations, 17 figures, 2 tables, 1 algorithm)

This paper contains 37 sections, 6 equations, 17 figures, 2 tables, 1 algorithm.

Table of Contents

  1. Nomenclature
  2. Introduction
  3. Problem Statement
  4. Research Contributions
  5. Related Work
  6. Statistical Models
  7. Machine Learning Approaches
  8. Deep Learning Methods
  9. Deep Learning Techniques
  10. Sentiment Analysis
  11. Artificial Neural Networks
  12. Overview
  13. Long Short-Term Memory Networks
  14. Data Description
  15. Methodology
  16. ...and 22 more sections

Figures (17)

  • Figure 1: LSTM Cell Structure selvin2017stock.
  • Figure 2: Closing Price Trends for Apple Stock (April 2024–April 2025).
  • Figure 3: Closing Price Trends for Google Stock (April 2024–April 2025).
  • Figure 4: Closing Price Trends for Microsoft Stock (April 2024–April 2025).
  • Figure 5: Closing Price Trends for Amazon Stock (April 2024–April 2025).
  • ...and 12 more figures