Paper: arXiv 2502.17493

Abstract

Making consistently profitable financial decisions in a continuously evolving and volatile stock market has always been a difficult task. Professionals from different disciplines have developed foundational theories to anticipate price movement and evaluate securities such as the famed Capital Asset Pricing Model (CAPM). In recent years, the role of artificial intelligence (AI) in asset pricing has been growing. Although the black-box nature of deep learning models lacks interpretability, they have continued to solidify their position in the financial industry. We aim to further enhance AI’s potential and utility by introducing a return-weighted loss function that will drive top growth while providing the ML models a limited amount of information. Using only publicly accessible stock data (open/close/high/low, trading volume, sector information) and several technical indicators constructed from them, we propose an efficient daily trading system that detects top growth opportunities. Our best models achieve 61.73% annual return on daily rebalancing with an annualized Sharpe Ratio of 1.18 over 1340 testing days from 2019 to 2024, and 37.61% annual return with an annualized Sharpe Ratio of 0.97 over 1360 testing days from 2005 to 2010. The main drivers for success, especially independent of any domain knowledge, are the novel return-weighted loss function, the integration of categorical and continuous data, and the ML model architecture. We also demonstrate the superiority of our novel loss function over traditional loss functions via several performance metrics and statistical evidence.

Complexity vs Empirical Score

  • Math Complexity: 3.5/10
  • Empirical Rigor: 6.0/10 (capped from 7.5: transaction costs not modelled; see penalty flags)
  • Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The mathematical complexity is moderate, primarily involving standard ML components like cross-entropy and embedding layers, without heavy advanced theory or derivations; the empirical rigor is high, as the paper presents detailed backtesting results over two distinct time periods (2019-2024 and 2005-2010) with specific performance metrics (annual return, Sharpe ratio) using publicly available data, demonstrating a practical, implementation-focused trading system.

Research Flowchart

  flowchart TD
  A["Research Goal: <br>Develop High-Return Daily Stock Trading System"] --> B["Data Input: <br>OHLCV, Sector Info, Technical Indicators"]
  B --> C["Methodology: <br>Novel Return-Weighted Loss Function"]
  C --> D["Computational Process: <br>Deep Learning Model Training"]
  D --> E["Key Finding 1: <br>61.73% Annual Return (2019-2024)"]
  D --> F["Key Finding 2: <br>37.61% Annual Return (2005-2010)"]
  E --> G["Outcome: <br>Superior Performance vs Traditional Loss Functions"]
  F --> G

Cited References (46)

  1. Attention is All you Need (2017) — link
  2. Empirical asset pricing via machine learning (2020)
  3. Gradient-based learning applied to document recognition (1998)
  4. U-net: Convolutional networks for biomedical image segmentation (2015)
  5. Capital asset prices: A theory of market equilibrium under conditions of risk (1964)
  6. Efficient capital markets (1970)
  7. Common risk factors in the returns on stocks and bonds (1993)
  8. On persistence in mutual fund performance (1997)
and 38 more
  1. A five-factor asset pricing model (2015)
  2. Glove: Global vectors for word representation (2014)
  3. Bert: Pre-training of deep bidirectional transformers for language understanding (2018) — link
  4. Profitability context and the cross-section of stock returns (2024)
  5. Time series analysis: forecasting and control (2015)
  6. CNNpred: CNN-based stock market prediction using a diverse set of variables (2019)
  7. Technical analysis and sentiment embeddings for market trend prediction (2019)
  8. Deep Learning techniques for stock market forecasting: Recent trends and challenges (2023)
  9. News-based intelligent prediction of financial markets using text mining and machine learning: A systematic literature review (2023) — link
  10. A novel trading system for the stock market using Deep Q-Network action and instance selection (2024)
  11. Stock price prediction using CNN and LSTM-based deep learning models (2020)
  12. Stock price prediction using CNN-BiLSTM-Attention model (2023)
  13. A mathematical theory of communication (1948)
  14. Technical Analysis Library in Python (2018) — link
  15. Deep transformer-based asset price and direction prediction (2024)
  16. Transformer-based attention network for stock movement prediction (2022)
  17. Factors affecting text mining based stock prediction: Text feature representations, machine learning models, and news platforms (2022)
  18. Stock trend prediction using deep learning approach on technical indicator and industrial specific information (2021)
  19. Open source cross-sectional asset pricing (2021)
  20. Deep learning using risk-reward function for stock market prediction (2018)
  21. Generalized loss-based cnn-bilstm for stock market prediction (2024)
  22. A CNN-LSTM-based model to forecast stock prices (2020)
  23. Short-term stock correlation forecasting based on CNN-BiLSTM enhanced by attention mechanism (2024)
  24. A Stock Prediction Model Based on CNN-BiLSTM and Multiple Attention Mechanisms (2023)
  25. Adam: A Method for Stochastic Optimization (2017) — link
  26. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (2015) — link
  27. Dropout: a simple way to prevent neural networks from overfitting (2014)
  28. Cryptocurrency portfolio management with deep reinforcement learning (2017) — link
  29. Predicting Stock Prices Based on Machine Learning to Build Self-adaptive Trading Strategy (2025) — link
  30. Machine learning in business and finance: a literature review and research opportunities (2024) — link
  31. A convolutional neural network based approach to financial time series prediction (2022) — link
  32. Financial Time Series Forecasting using CNN and Transformer — → 2304.04912
  33. Financial Time Series Forecasting – A Deep Learning Approach (2017) — link
  34. Deep residual learning for image recognition (2016)
  35. Enhancing neural network predictions with finetuned numeric embeddings for stock trend forecasting (2025)
  36. A comprehensive survey of loss functions and metrics in deep learning (2025)
  37. A comprehensive survey of loss functions in machine learning (2022)
  38. Focal loss for dense object detection (2017)

1 of 46 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.