Navigating the Stock Market: The Role of State-of-the-Art Deep Learning Techniques

Authors

DOI:

https://doi.org/10.35875/vvf5k957

Keywords:

Deep learning, CuDNNGRU, CNN , Stock price prediction, Time series data

Abstract

Objectives: Certainty in investment decisions are the main tools for evaluation of stock markets. Every investor will have to identify the future stock prices before developing investment strategy so that their returns will be boosted. Due to the nonlinear, complicated, volatile, and dynamic character of stock data, forecasting stock prices is challenging. This study aims to address these challenges and improve prediction accuracy through advanced modelling techniques.

Methodology: We proposed a hybrid neural network that combines Bidirectional Gated Recurrent Units (BiGRU) with one-dimensional Convolutional Neural Networks (CNNs). Experiments were conducted on five stock price datasets, including three individual stock items and two performance indices of stock markets. The evaluation metrics included Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE).

Findings: The proposed hybrid model achieved the lowest MAE for individual datasets, ranging from 1.747 to 0.357. Additionally, our experiments demonstrated a 42–91% reduction in RMSE compared to standard CNN and GRU-based approaches, reflecting significantly improved prediction precision.

Implications: The results indicate that the hybrid Bidirectional GRU and CNN model is effective for precise stock price prediction, offering enhanced reliability for investment decision-making. This model can support investors and analysts in navigating the complexities of the stock market.

Conclusions: The hybrid Bidirectional GRU and CNN model demonstrates superior performance in stock price prediction compared to traditional methods. It holds promise for advanc- ing  predictive  analytics  in  financial  markets,  contributing to  better  investment  strategies  and  reduced  market  risks.

Author Biographies

  • Dr. Anika Kanwal, Swinburne University of Technology

    Anika Kanwal earned her PhD in 2023, specializing in stock price prediction using neural networks. Since 2019, she has been serving as a sessional academic in the School of Science, Computing, and Engineering Technologies at Swinburne University of Technology, Melbourne, Australia. Her research primarily focuses on developing and optimizing machine learning and deep learning-based predictive models. She is particularly interested in exploring advanced neural network architectures and large language models (LLMs) to enhance predictive accuracy and improve interpretability in financial forecasting.

  • Dr. Man Fai Lau , Swinburne University of Technology

    Man Fai Lau received his BSc(Hons) from The University of Hong Kong and PhD from The University of Melbourne. He joined Swinburne University of Technology in 2000. He received 2 ARC DP research grants in 2005 (a 3-year ARC DP project) and 2007 (a 5-year ARC DP project). His currently research interests are on Data Mining and Testing Prediction Models. Currently, he is working on a Big Data project on testing Optimal Oil Drilling Prediction Models based on past 15+ years of oil drilling data.

     

  • Dr. Ahmad Sami, Al-Ahliyya Amman University

    Ahmad Sami Al-Shamayleh received the master’s degree in Information Systems from The University of Jordan, Jordan, in 2014, and the Ph.D. degree in Artificial intelligence from University of Malaya, Malaysia, in 2020. He is currently an Assistant Professor with the Faculty of Information Technology, Al-Ahliyya Amman University, Jordan. His research interests include: Artificial Intelligence, Human Computer Interaction, IoT, Arabic NLP, Arabic sign language recognition, language resources production, the design and evaluation of interactive applications for handicapped people, multimodality, and software engineering.

  • Dr. Adnan Akhunzada , University of Doha for Science and Technology

    Adnan Akhunzada, a distinguished Senior Member of IEEE and Professional Member of ACM, brings 15 years of expertise in Research and Development (R&D) at the nexus of the ICT industry and academia. Renowned for his high impact publications, US patents, and commercial products, Dr. Akhunzada's patented innovations in cybersecurity and AI have secured multi-million-dollar projects with global entities such as Vinnova and EU Horizon. In 2023, Stanford University recognized him as one of the top 2% scientists globally for his outstanding scholarly contributions. Leveraging his robust cybersecurity skills and advanced technological knowledge, Prof. Akhunzada excels in solving industrial challenges and developing state-of-the-art security tools and frameworks. His expertise spans Cybersecurity & AI, Secure Future Internet, Secure & Dependable Software Defined Networks, and Large-Scale Distributed Systems (including Cloud, Fog, Edge, IoT, IoE, IIoT, CPS). Additionally, his work on Lightweight Cryptographic Communication Protocols, QoS/QoE, and Adversarial Machine Learning is shaping the future of secure and dependable systems.

  • Siva Chandrasekaran , Swinburne University of Technology

    Siva Chandrasekaran is a Senior Lecturer in Computer and Software Engineering at Swinburne University of Technology. He is an elected member of the Academic Senate for 2021-2022 and 2023-2024 and serves as the Major Discipline Coordinator for Software Engineering. He holds the title of Fellow of the Institution of Engineers Australia and is a Chartered Professional Engineer in various areas. Siva Chandrasekaran has been bestowed as a senior member (SMIEEE) of the Institution of Electrical and Electronics Engineers (IEEE) and a member of the Australian Computer Society (ACS). Siva is an Associate Editor of the IEEE Education Society IEEE Access Section. He is the lead of the Internet of Things (IoT) Training Academy at Swinburne. Siva has made significant contributions to engineering education research and published more than 140 scholarly articles in national/international peer-reviewed journals and conference proceedings. His research focuses on AI, ML, cybersecurity and Industrial IoT. 

  • Dr. Sebastian P.H. Ng, Swinburne University of Technology

    NG S.P.H. is an associate professor at Swinburne, specializing in Computer Science and Software Engineering. His research centres on Software Engineering Education and Software Testing. He’s well-qualified with a PhD, Master’s, PG Diploma, and bachelor’s degrees spanning Information Technology, Computing, Science, and Education. He also holds senior membership in the Australian Computer Society. 

  • Dr. Kwan Yong Sim, Swinburne University of Technology

    Kwan Yong Sim is Deputy Pro Vice-Chancellor (Academic), Professor at Swinburne University of Technology Sarawak Campus, Malaysia. is Deputy Pro Vice Chancellor (Aca- demic) at Swinburne University of Technology Sarawak Campus. His previous appointments include Executive Dean (Academic) – Interim, Head of School for School of Engineering, Associate Dean at the Faculty of Engineering, Computing and Science, Swinburne Sarawak, Malaysia Re- search Assessment (MyRA) Lead Auditor, Engineering Accreditation Council Panel of Evaluator. He is a registered Professional Engineer (P.Eng.) with the Board of Engineer Malaysia (BEM), Chartered Engineer (CEng) with the U.K. Engineering Council. His current research interests include Data Mining and Testing Prediction Models. 

  •  89
  • 50

Downloads

Published

2024-12-31

Issue

Vol. 27 No. 4 (2024)

Section

Articles

Categories

How to Cite

Kanwal, A., Lau, M., Sami, A., Akhunzada, A., Chandrasekaran, S., P.H. Ng, S., & Sim, K. (2024). Navigating the Stock Market: The Role of State-of-the-Art Deep Learning Techniques. Al-Balqa Journal for Research and Studies, 27(4), 79-105. https://doi.org/10.35875/vvf5k957