Paper: arXiv 2303.09323

Authors: Shima Nabiee, Nader Bagherzadeh

Abstract

Market financial forecasting is a trending area in deep learning. Deep learning models are capable of tackling the classic challenges in stock market data, such as its extremely complicated dynamics as well as long-term temporal correlation. To capture the temporal relationship among these time series, recurrent neural networks are employed. However, it is difficult for recurrent models to learn to keep track of long-term information. Convolutional Neural Networks have been utilized to better capture the dynamics and extract features for both short- and long-term forecasting. However, semantic segmentation and its well-designed fully convolutional networks have never been studied for time-series dense classification. We present a novel approach to predict long-term daily stock price change trends with fully 2D-convolutional encoder-decoders. We generate input frames with daily prices for a time-frame of T days. The aim is to predict future trends by pixel-wise classification of the current price frame. We propose a hierarchical CNN structure to encode multiple price frames to multiscale latent representation in parallel using Atrous Spatial Pyramid Pooling blocks and take that temporal coarse feature stacks into account in the decoding stages. Our hierarchical structure of CNNs makes it capable of capturing both long and short-term temporal relationships effectively. The effect of increasing the input time horizon via incrementing parallel encoders has been studied with interesting and substantial changes in the output segmentation masks. We achieve overall accuracy and AUC of %78.18 and 0.88 for joint trend prediction over the next 20 days, surpassing other semantic segmentation approaches. We compared our proposed model with several deep models specifically designed for technical analysis and found that for different output horizons, our proposed models outperformed other models.

Complexity vs Empirical Score

  • Math Complexity: 4.5/10
  • Empirical Rigor: 6.0/10
  • Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper innovatively applies 2D computer vision techniques (semantic segmentation, ASPP) to 1D financial time-series data for dense trend prediction. While mathematically straightforward (relying on standard deep learning architectures), the empirical results show solid performance metrics, though practical trading execution details are somewhat limited.

Research Flowchart

  flowchart TD
    A["Research Goal: Long-term Daily Stock Trend Prediction using Semantic Segmentation"] --> B["Data Input: Price Frames for T days (Time-Series as 2D Frames)"]
    B --> C["Parallel Hierarchical Encoders with Atrous Spatial Pyramid Pooling (ASPP)"]
    C --> D["Multiscale Latent Feature Extraction (Short & Long-term Dynamics)"]
    D --> E["Fully Convolutional Decoder for Pixel-wise Dense Trend Classification"]
    E --> F["Outcomes: 78.18% Accuracy & 0.88 AUC for 20-day Trend Prediction (Outperforms Baselines)"]