Deep learning approach for stock closing price prediction: A hybrid approach using RNN–LSTM architecture

Collins Lemeke; Negin Aboutorabi; Farnoud Amiri; Salome Enoshi Uwah; Babatope Makinde; Professor Celestine Iwendi

Back

Deep learning approach for stock closing price prediction: A hybrid approach using RNN–LSTM architecture

Conference proceeding

Peer reviewed

Deep learning approach for stock closing price prediction: A hybrid approach using RNN–LSTM architecture

Collins Lemeke, Negin Aboutorabi, Farnoud Amiri, Salome Enoshi Uwah, Babatope Makinde and Professor Celestine Iwendi

Innovative Engineering and Scientific Approaches for Sustainable Economy and Ecotechnology : Proceedings of ICATEST 2025

ICATEST 2025 (Nashik, India, 19/09/2025–20/09/2025)

2026

Abstract

Stock price prediction

closing price

sequential data

Neural Networks

Long Short-Term Memory (LSTM)

Market Analysis

Predictive Analytics

Linear Regression

Temporal Convolutional Network

TCN

Accurate stock price forecasting remains a challenging yet crucial task in the financial industry due to the non-linear relationships, noisy, and time-dependent nature of the market data. This study presents a deep learning approach known as long-short-term memory (LSTM) for predicting the closing prices of stock using historical data. The model is designed to capture the complex temporal dependencies inherent in stock market sequences, addressing the limitations of traditional statistical models such as ARIMA and linear regression. Using key key characteristics such as past closing prices, the LSTM model achieved high predictive performance with a Mean Squared Error (MSE) of 0.00036, a mean absolute error (MAE) of 0.0096, and a coefficient of determination (R²) of 0.9941, indicating strong generalization and accuracy. The results demonstrate the effectiveness of LSTM architectures in time series forecasting for financial applications. This research contributes to the development of robust and automated decision support tools for investors and sets a performance benchmark for future deep learning models in stock market prediction.

Files and links (2)

pdf

Deep Learning Approach for Stock Closing Price Prediction A Hybrid Approach Using RNN–LSTM Architecture650.80 kB

url

Link to Published ProceedingsView

Published (Version of record)Publisher may require payment for access Restricted

Metrics

32 Record Views

Details

Title: Deep learning approach for stock closing price prediction
Creators - without role: Collins Lemeke - University of Greater Manchester
Negin Aboutorabi - University of Greater Manchester
Farnoud Amiri - University of Greater Manchester
Salome Enoshi Uwah - University of Greater Manchester
Babatope Makinde - University of Greater Manchester
Professor Celestine Iwendi - University of Greater Manchester, Computing
Publication Details: Innovative Engineering and Scientific Approaches for Sustainable Economy and Ecotechnology : Proceedings of ICATEST 2025
Conference: ICATEST 2025 (Nashik, India, 19/09/2025–20/09/2025)
Publisher: Springer Nature Switzerland
Identifiers: 9960551608841; 9783032150608
Copyright: This version of the contribution has been accepted for publication, after peer review (when applicable) but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record will be available online at: https://link.springer.com/book/9783032150608. Use of this Accepted Version is subject to the publisher’s Accepted Manuscript terms of use https://www.springernature.com/gp/open-research/policies/accepted- manuscript-terms”
Academic Unit: Computing
Language: English
Resource Type: Conference proceeding
Date accepted: 18/08/2025

Deep learning approach for stock closing price prediction: A hybrid approach using RNN–LSTM architecture

Abstract

Files and links (2)

Metrics

Details

University of Greater Manchester Social media

Usage Policy