English

CNN-DRL with Shuffled Features in Finance

Computational Finance 2024-02-07 v1 Machine Learning

Abstract

In prior methods, it was observed that the application of Convolutional Neural Networks agent in Deep Reinforcement Learning to financial data resulted in an enhanced reward. In this study, a specific permutation was applied to the feature vector, thereby generating a CNN matrix that strategically positions more pertinent features in close proximity. Our comprehensive experimental evaluations unequivocally demonstrate a substantial enhancement in reward attainment.

Keywords

Cite

@article{arxiv.2402.03338,
  title  = {CNN-DRL with Shuffled Features in Finance},
  author = {Sina Montazeri and Akram Mirzaeinia and Amir Mirzaeinia},
  journal= {arXiv preprint arXiv:2402.03338},
  year   = {2024}
}

Comments

10th Annual Conf. on Computational Science & Computational Intelligence (CSCI'23). arXiv admin note: substantial text overlap with arXiv:2401.06179

R2 v1 2026-06-28T14:39:03.632Z