Predicting Stock Price Movement as an Image Classification Problem

Paper: arXiv 2303.01111

Authors: Matej Steinbacher

Abstract

The paper studies intraday price movement of stocks that is considered as an image classification problem. Using a CNN-based model we make a compelling case for the high-level relationship between the first hour of trading and the close. The algorithm managed to adequately separate between the two opposing classes and investing according to the algorithm’s predictions outperformed all alternative constructs but the theoretical maximum. To support the thesis, we ran several additional tests. The findings in the paper highlight the suitability of computer vision techniques for studying financial markets and in particular prediction of stock price movements.

Complexity vs Empirical Score

• Math Complexity: 3.5/10
• Empirical Rigor: 6.0/10 (capped from 6.5: transaction costs not modelled; no out-of-sample test; see penalty flags)
• Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper presents an innovative framing of intraday stock prediction as a computer vision problem using Convolutional Neural Networks. While mathematical formulation is minimal, the empirical setup demonstrates promising outperformance against standard benchmarks, backed by practical testing.

Research Flowchart

  flowchart TD
    A[Research Goal: Predict Intraday Stock Movement via Image Classification] --> B[Data Input: Convert Stock Charts into Images]
    B --> C[Methodology: Train Convolutional Neural Network]
    C --> D[Model Processing: Analyze First Hour Trading vs. Close]
    D --> E[Outcome: Successfully Separates Opposing Classes]
    D --> F[Outcome: Trading Strategy Outperforms Alternative Constructs]
    E & F --> G[Key Finding: Computer Vision is Highly Suitable for Financial Prediction]