Paper: arXiv 2305.04811

Authors: Cheng Zhang, Nilam Nur Amir Sjarif, Roslina Ibrahim

Abstract

Accurately predicting the prices of financial time series is essential and challenging for the financial sector. Owing to recent advancements in deep learning techniques, deep learning models are gradually replacing traditional statistical and machine learning models as the first choice for price forecasting tasks. This shift in model selection has led to a notable rise in research related to applying deep learning models to price forecasting, resulting in a rapid accumulation of new knowledge. Therefore, we conducted a literature review of relevant studies over the past three years with a view to aiding researchers and practitioners in the field. This review delves deeply into deep learning-based forecasting models, presenting information on model architectures, practical applications, and their respective advantages and disadvantages. In particular, detailed information is provided on advanced models for price forecasting, such as Transformers, generative adversarial networks (GANs), graph neural networks (GNNs), and deep quantum neural networks (DQNNs). The present contribution also includes potential directions for future research, such as examining the effectiveness of deep learning models with complex structures for price forecasting, extending from point prediction to interval prediction using deep learning models, scrutinising the reliability and validity of decomposition ensembles, and exploring the influence of data volume on model performance.

Complexity vs Empirical Score

  • Math Complexity: 3.0/10
  • Empirical Rigor: 4.5/10
  • Quadrant: Philosophers — conceptual discussion, limited math and data

Why this score: As a survey paper covering deep learning models from 2020-2022, it provides a strong, clear, and comprehensive overview of recent architectures like Transformers and GANs in finance. However, it lacks original mathematical proofs or fresh empirical backtesting, serving primarily as a reference catalog rather than novel research.

Research Flowchart

  flowchart TD
    A[Research Goal: Review Deep Learning Models for Financial Price Forecasting 2020-2022] --> B[Data Inputs: Literature on Financial Time Series & Advanced DL Models]
    B --> C[Methodology: Systematic Review & Categorization of Advanced Architectures]
    C --> D[Analysis: Comparative Evaluation of Transformers, GANs, GNNs & DQNNs]
    D --> E[Outcomes: Advantages, Disadvantages & Shift from Statistical to DL Models]
    E --> F[Future Directions: Complex Models, Interval Prediction & Data Volume Impact]