Paper: arXiv 2409.17392

Abstract

Earnings release is a key economic event in the financial markets and crucial for predicting stock movements. Earnings data gives a glimpse into how a company is doing financially and can hint at where its stock might go next. However, the irregularity of its release cycle makes it a challenge to incorporate this data in a medium-frequency algorithmic trading model and the usefulness of this data fades fast after it is released, making it tough for models to stay accurate over time. Addressing this challenge, we introduce the Contrastive Earnings Transformer (CET) model, a self-supervised learning approach rooted in Contrastive Predictive Coding (CPC), aiming to optimise the utilisation of earnings data. To ascertain its effectiveness, we conduct a comparative study of CET against benchmark models across diverse sectors. Our research delves deep into the intricacies of stock data, evaluating how various models, and notably CET, handle the rapidly changing relevance of earnings data over time and over different sectors. The research outcomes shed light on CET’s distinct advantage in extrapolating the inherent value of earnings data over time. Its foundation on CPC allows for a nuanced understanding, facilitating consistent stock predictions even as the earnings data ages. This finding about CET presents a fresh approach to better use earnings data in algorithmic trading for predicting stock price trends.

Complexity vs Empirical Score

  • Math Complexity: 7.5/10
  • Empirical Rigor: 8.0/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper employs advanced machine learning concepts like Transformers and Contrastive Predictive Coding, requiring significant mathematical understanding, yet the research is grounded in a practical trading problem with a detailed comparative study across sectors, suggesting strong empirical implementation.

Research Flowchart

  flowchart TD
  A["Research Goal<br>How to optimise earnings data<br>for medium-frequency trading?"] --> B
  
  subgraph B ["Methodology & Data"]
      direction LR
      B1["Dataset<br>Historical Stock & Earnings Data"] --> B2["Preprocessing<br>Time-series & Event Alignment"]
      B2 --> B3["Model: Contrastive Earnings Transformer<br>Self-Supervised Contrastive Learning"]
  end

  B3 --> C["Computational Process<br>Contrastive Predictive Coding<br>Learning latent representations<br>maximising mutual information"]

  C --> D
  
  subgraph D ["Key Findings/Outcomes"]
      D1["CET outperforms benchmarks<br>in predictive accuracy"]
      D2["Robust to data aging<br>Maintains relevance over time"]
      D3["Sector-agnostic advantage<br>Consistent across industries"]
  end

  D --> E["Conclusion<br>Novel approach for leveraging<br>earnings data in algorithmic trading"]

Cited References (96)

  1. Unsupervised Pre-training of a Deep LSTM-based Stacked Autoencoder for Multivariate Time Series Forecasting Problems (2019)
  2. A review of unsupervised feature learning and deep learning for time-series modeling (2014)
  3. Time Series Forecasting of Petroleum Production using Deep LSTM Recurrent Networks (2018)
  4. A Review on Neural Networks with Random Weights (2017)
  5. Solving the linear interval tolerance problem for weight initialization of neural networks (2014)
  6. Learning Complex, Extended Sequences Using the Principle of History Compression (1992)
  7. Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion (2010)
  8. Time-Series Forecasting of Indoor Temperature Using Pre-trained Deep Neural Networks (2013)
and 88 more
  1. Time series forecasting using a deep belief network with restricted Boltzmann machines (2014)
  2. A Cycle Deep Belief Network Model for Multivariate Time Series Classification (2017)
  3. TimeNet: Pre-trained deep recurrent neural network for time series classification (2017)
  4. An Empirical Study on Unsupervised Pre-training Approaches in Regression Problems (2018)
  5. Time Series Forecasting using Artificial Neural Networks Methodologies: A Systematic Review (2018)
  6. Evolution of Neural Networks for Classifi cation and Regression (2007)
  7. A hybrid algorithm for artificial neural network training (2013)
  8. Why Does Unsupervised Pre-Training Help Deep Learning? (2010)
  9. An Analysis of Unsupervised Pre-training in Light of Recent Advances (2015)
  10. Knowledge Transfer Pre-training (2015)
  11. Multi-Transformer: A New Neural Network-Based Architecture for Forecasting S&P Volatility (2021)
  12. A Transformer-Based Framework for Multivariate Time Series Representation Learning (2021)
  13. Learning representations of multivariate time series with missing data (2019)
  14. Deep Residual Learning for Image Recognition (2016)
  15. ImageNet Classification with Deep Convolutional Neural Networks (2012)
  16. Deep Speech 2: End-to-End Speech Recognition in English and Mandarin (2016)
  17. Speech Recognition with Deep Recurrent Neural Networks (2013)
  18. BERT : Pre-training of Deep Bidirectional Transformers for Language Understanding (2019)
  19. Protecting Sensory Data against Sensitive Inferences (2018)
  20. On the Role of Features in Human Activity Recognition (2019)
  21. Feature Learning for Activity Recognition in Ubiquitous Computing (2011)
  22. Multi-Task Self-Supervised Learning for Human Activity Detection (2019)
  23. Deep Auto-Set: A Deep Auto-Encoder-Set Network for Activity Recognition Using Wearables (2018)
  24. Masked Reconstruction Based Self-Supervision for Human Activity Recognition (2020)
  25. Representation Learning with Contrastive Predictive Coding (2018)
  26. Noise-contrastive estimation: A new estimation principle for unnormalized statistical models (2010)
  27. Self-Supervised Video Representation Learning with Odd-One-Out Networks (2017)
  28. Shuffle and Learn: Unsupervised Learning Using Temporal Order Verification (2016)
  29. Learning and Using the Arrow of Time (2018)
  30. Distributed Representations of Words and Phrases and their Compositionality (2013)
  31. Glove: Global Vectors for Word Representation (2014)
  32. Universal Sentence Encoder (2018)
  33. Attention Is All You Need (2017)
  34. Improving Language Understanding by Generative Pre-Training (2018)
  35. Contrastive Predictive Coding for Human Activity Recognition (2020)
  36. Self-Supervised Time Series Classification Based on LSTM and Contrastive Transformer (2023)
  37. Greedy InfoMax for Biologically Plausible Self-Supervised Representation Learning (2019)
  38. Time-Series Representation Learning via Temporal and Contextual Contrasting (2021)
  39. Lbl - Lstm : Log Bilinear And Long Short Term Memory Based Efficient Stock Forecasting Model Considering External Fluctuating Factor (2020)
  40. Coupling Macro-Sector-Micro Financial Indicators for Learning Stock Representations with Less Uncertainty (2021)
  41. Genetic Algorithms and Investment Strategies (1994)
  42. Economic prediction using neural networks: the case of IBM daily stock returns (1988)
  43. Forecasting leading industry stock prices based on a hybrid time-series forecast model (2019)
  44. Machine learning techniques and data for stock market forecasting: A literature review (2022)
  45. Financial Trading as a Game: A Deep Reinforcement Learning Approach (2018)
  46. Double Deep Q-Learning for Optimal Execution (2021)
  47. Deep Stock Representation Learning: From Candlestick Charts to Investment Decisions (2018)
  48. Monetary policy uncertainty and the market reaction to macroeconomic news (2018)
  49. Do financial markets respond to macroeconomic surprises? Evidence from the UK (2022)
  50. No Stock is an Island: Learning Internal and Relational Attributes of Stocks with Contrastive Learning (2022)
  51. Accurate Stock Movement Prediction with Self-supervised Learning from Sparse Noisy Tweets (2022)
  52. CLVSA : A Convolutional LSTM Based Variational Sequence-to-Sequence Model with Attention for Predicting Trends of Financial Markets (2019)
  53. The Impact of Earnings Announcements on the Share Price Behaviour of Similar Type Firms (1976)
  54. What Triggers Stock Market Jumps? (2021)
  55. Common risk factors in the returns on stocks and bonds (1993)
  56. An Empirical Evaluation of Accounting Income Numbers (1968)
  57. Capturing dynamics of post-earnings-announcement drift using a genetic algorithm-optimized XGBoost (2021)
  58. Deep learning with stock indicators and two-dimensional principal component analysis for closing price prediction system (2016)
  59. Financial Time Series Forecasting - A Machine Learning Approach (2017)
  60. Deep learning with long short-term memory networks for financial market predictions (2018)
  61. Stock market index prediction using deep Transformer model (2022)
  62. Transformer-Based Deep Learning Model for Stock Price Prediction: A Case Study on Bangladesh Stock Market (2023)
  63. Deep Learning for Stock Market Prediction Using Event Embedding and Technical Indicators (2018)
  64. A Binary Stock Event Model for stock trends forecasting: Forecasting stock trends via a simple and accurate approach with machine learning (2011)
  65. Neural Network Forecasts of Canadian Stock Returns using Accounting Ratios. International Journal of Forecasting (2003)
  66. A bat-neural network multi-agent system (BNNMAS) for stock price prediction: Case study of DAX stock price (2015)
  67. A Comparison between Regression, Artificial Neural Networks and Support Vector Machines for Predicting Stock Market Index (2015)
  68. The predictive power of earnings conference calls : predicting stock price movement with earnings call transcripts (2018)
  69. An Exploratory Study of Stock Price Movements from Earnings Calls (2022)
  70. Language Models are Few-Shot Learners (2020)
  71. Wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations (2020)
  72. A Simple Framework for Contrastive Learning of Visual Representations (2020)
  73. TimeCLR: A Self-Supervised Contrastive Learning Framework for Univariate Time Series Representation (2022)
  74. An analysis on the use of autoencoders for representation learning: Fundamentals, learning task case studies, explainability and challenges (2020)
  75. An efficient stock market prediction model using hybrid feature reduction method based on variational autoencoders and recursive feature elimination (2021)
  76. Efficient Capital Markets: A Review of Theory and Empirical Work (1970)
  77. Efficient Capital Markets II (1991)
  78. Investors Exchange API (2023)
  79. Adam: A Method for Stochastic Optimization (2014)
  80. Deep Robust Reinforcement Learning for Practical Algorithmic Trading (2019)
  81. Forward Forecast of Stock Price Using Sliding-Window Metaheuristic-Optimized Machine-Learning Regression (2018)
  82. Human-aligned trading by imitative multi-loss reinforcement learning (2023)
  83. Deep Direct Reinforcement Learning for Financial Signal Representation and Trading (2017)
  84. Adaptive Quantitative Trading: An Imitative Deep Reinforcement Learning Approach (2020)
  85. Multi-DQN: an Ensemble of Deep Q-Learning Agents for Stock Market Forecasting (2021)
  86. Price Trailing for Financial Trading Using Deep Reinforcement Learning (2021)
  87. Deep learning models for price forecasting of financial time series: A review of recent advancements: 2020–2022 (2023)
  88. Financial Market Forecasting using RNN, LSTM, BiLSTM, GRU and Transformer-Based Deep Learning Algorithms (2023)

0 of 96 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.