Stock market prediction using Altruistic Dragonfly Algorithm.

Journal: PloS one
Published Date:

Abstract

Stock market prediction is the process of determining the value of a company's shares and other financial assets in the future. This paper proposes a new model where Altruistic Dragonfly Algorithm (ADA) is combined with Least Squares Support Vector Machine (LS-SVM) for stock market prediction. ADA is a meta-heuristic algorithm which optimizes the parameters of LS-SVM to avoid local minima and overfitting, resulting in better prediction performance. Experiments have been performed on 12 datasets and the obtained results are compared with other popular meta-heuristic algorithms. The results show that the proposed model provides a better predictive ability and demonstrate the effectiveness of ADA in optimizing the parameters of LS-SVM.

Authors

  • Bitanu Chatterjee
    Department of Computer Science and Engineering, Jadavpur University, Kolkata, West Bengal, India.
  • Sayan Acharya
    Department of Computer Science and Engineering, Jadavpur University, Kolkata, West Bengal, India.
  • Trinav Bhattacharyya
    Department of Computer Science and Engineering, Jadavpur University, Kolkata, West Bengal, India.
  • Seyedali Mirjalili
    Centre for Artificial Intelligence Research and Optimisation, Torrens University Australia, Fortitude Valley, Brisbane, QLD, 4006, Australia; Yonsei Frontier Lab, Yonsei University, Seoul, South Korea; King Abdulaziz University, Jeddah, Saudi Arabia. Electronic address: ali.mirjalili@gmail.com.
  • Ram Sarkar
    Department of Computer Science and Engineering, Jadavpur University, Kolkata, 700032, India.