Paper: arXiv 2408.08483

Abstract

We open up the “black-box” to identify the predictive general price patterns in price chart images via the deep learning image analysis techniques. Our identified price patterns lead to the construction of image-induced importance (triple-I) weights, which are applied to weighted moving average the existing price trend trading signals according to their level of importance in predicting price movements. From an extensive empirical analysis on the Chinese stock market, we show that the triple-I weighting scheme can significantly enhance the price trend trading signals for proposing portfolios, with a thoughtful robustness study in terms of network specifications, image structures, and stock sizes. Moreover, we demonstrate that the triple-I weighting scheme is able to propose long-term portfolios from a time-scale transfer learning, enhance the news-based trading strategies through a non-technical transfer learning, and increase the overall strength of numerous trading rules for portfolio selection.

Complexity vs Empirical Score

  • Math Complexity: 6.5/10
  • Empirical Rigor: 6.0/10 (capped from 8.0: transaction costs not modelled; see penalty flags)
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper employs advanced deep learning techniques (ResNet, Grad-CAM) and transfer learning theory, but is heavily grounded in extensive backtesting, dataset availability, and specific portfolio metrics (Sharpe ratios, turnover).

Research Flowchart

  flowchart TD
  A["Research Goal<br>Identify predictive price patterns<br>from chart images"] --> B["Data Input<br>Chinese stock market data &<br>Price chart images"]
  B --> C["Methodology<br>Deep Learning Image Analysis"]
  C --> D["Process<br>Extract patterns &<br>Generate Image-Induced Importance Triple-I Weights"]
  D --> E["Application<br>Weighted Moving Average<br>on trading signals"]
  E --> F["Outcomes<br>Enhanced Trend Trading Strategies<br>& Portfolio Construction"]
  F --> G["Findings<br>Significant enhancement demonstrated<br>via transfer learning & robustness study"]

Cited References (50)

  1. (Re-)Imag(in)ing price trends (2023)
  2. Dividend yields and expected stock returns (1988)
  3. Market expectations in the cross-Section of present values (2013)
  4. Data-Snooping, technical trading rule performance, and the bootstrap (1999)
  5. The Extreme Value Method for Estimating the Variance of the Rate of Return (1980)
  6. Learning long-term dependencies with gradient descent is difficult (1994)
  7. Deep residual learning for image recognition (2016)
  8. Smooth grad-cam++: An enhanced inference level visualization technique for deep convolutional neural network models (2019) — link
and 42 more
  1. TorchCAM: class activation explorer (2020)
  2. Grad-cam: Visual explanations from deep networks via gradient-based localization (2017)
  3. Learning deep features for discriminative localization (2016)
  4. Score-CAM: Score-weighted visual explanations for convolutional neural networks (2020)
  5. Adam: A method for stochastic optimization (2015)
  6. Grad-CAM++: Generalized gradient-based visual explanations for deep convolutional networks (2018) — link
  7. A trend factor: Any economic gains from using information over investment horizons? (2016) — link
  8. 101 formulaic alphas (2016)
  9. Autoencoder asset pricing models (2021)
  10. Empirical asset pricing via machine learning (2020)
  11. Capturing volatility from large price moves: generalized range theory and applications (2007)
  12. Returns to buying winners and selling losers: Implications for stock market efficiency (1993)
  13. Evidence of predictable behavior of security returns (1990)
  14. Psychology-based models of asset prices and trading volume (2018)
  15. Deep learning (2016)
  16. Foundations of technical analysis: Computational algorithms, statistical inference, and empirical implementation (2000)
  17. The Heretics of Finance: Conversations with Leading Practitioners of Technical Analysis (2010) — link
  18. On technical analysis (1989)
  19. Trade and the revelation of information through prices and direct disclosure (1989)
  20. Market statistics and technical analysis: The role of volume (1994)
  21. A model of investor sentiment (1998)
  22. Technical analysis: An asset allocation perspective on the use of moving averages (2009)
  23. Forecasting the equity risk premium: the role of technical indicators (2014)
  24. Learning and predictability via technical analysis: Evidence from Bitcoin and stocks with hard-to-value fundamentals (2021)
  25. Charting by machines (2024)
  26. Technical trading revisited: False discoveries, persistence tests, and transaction Costs (2012)
  27. Forecasting stock prices with a feature fusion LSTM-CNN model using different representations of the same data (2019)
  28. Global Stock Market Prediction Based on Stock Chart Images Using Deep Q-Network (2019) — link
  29. CNNpred: CNN-based stock market prediction using a diverse set of variables (2019)
  30. Forecasting the overnight return direction of stock market index combining global market indices: A multiple-branch deep learning approach (2022) — link
  31. Effects of the validation set on stock returns forecasting (2020) — link
  32. When are contrarian profits due to stock market overreaction? (1990)
  33. Simple technical trading rules and the stochastic properties of stock returns (1992)
  34. Asset pricing via the conditional quantile variational autoencoder (2024)
  35. SmoothGrad: Removing noise by adding noise (2017)
  36. How much can machines learn finance from chinese text data? (2024) — link
  37. The adaptive lasso and its oracle properties (2006) — link
  38. Attention is All you Need (2017)
  39. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (2021) — link
  40. Densely Connected Convolutional Networks (2017)
  41. Going Deeper With Convolutions (2015)
  42. A ConvNet for the 2020s (2022)

0 of 50 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.