Paper: arXiv 2502.05210

Abstract

This paper analyses the investment returns of three stock sectors, Manuf, Hitec, and Other, in the U.S. stock market, based on the Fama-French three-factor model, the Carhart four-factor model, and the Fama-French five-factor model, in order to test the validity of the Fama-French three-factor model, the Carhart four-factor model, and the Fama-French five-factor model for the three sectors of the market. French five-factor model for the three sectors of the market. Also, the LSTM model is used to explore the additional factors affecting stock returns. The empirical results show that the Fama-French five-factor model has better validity for the three segments of the market under study, and the LSTM model has the ability to capture the factors affecting the returns of certain industries, and can better regress and predict the stock returns of the relevant industries. Keywords- Fama-French model; Carhart model; Factor model; LSTM model.

Complexity vs Empirical Score

  • Math Complexity: 6.5/10
  • Empirical Rigor: 7.0/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper employs established finance factor models (Fama-French, Carhart) and advanced neural network architectures (LSTM) with significant mathematical formulation, while also detailing empirical procedures including data sourcing from major U.S. exchanges, data cleaning, and the use of standard statistical metrics (R-squared, RMSE, MAE) for backtest-ready validation.

Research Flowchart

  flowchart TD
  A["Research Goal<br/>Test Factor Models & Forecast Stock Returns"] --> B["Data Inputs<br/>(U.S. Stock Sectors: Manuf, Hitec, Other)"]
  B --> C["Methodology<br/>1. Factor Models (Fama-French 3/5, Carhart 4)<br/>2. LSTM Regression & Forecasting"]
  C --> D["Computational Process<br/>Regress sector returns vs. factors<br/>Train LSTM on historical data"]
  D --> E["Outcome 1<br/>Fama-French Five-Factor model<br/>has best validity for all sectors"]
  D --> F["Outcome 2<br/>LSTM captures industry-specific factors<br/>and predicts returns effectively"]

Cited References (42)

  1. SigCan: Toward Reliable ToF Estimation Leveraging Multipath Signal Cancellation on Commodity WiFi Devices (2025) — link
  2. Credit Risk Identification in Supply Chains Using Generative Adversarial Networks (2025) — link
  3. Detection of AI Deepfake and Fraud in Online Payments Using GAN-Based Models (2025) — link
  4. Identifying Money Laundering Risks in Digital Asset Transactions Based on AI Algorithms (2024) — link
  5. Developing Cryptocurrency Trading Strategy Based on Autoencoder-CNN-GANs Algorithms — → 2412.18202
  6. Attentive Eraser: Unleashing Diffusion Model’s Object Removal Potential via Self-Attention Redirection Guidance (2024) — link
  7. A Consolidated Volatility Prediction with Back Propagation Neural Network and Genetic Algorithm — → 2412.07223
  8. Tail Risk Alert Based on Conditional Autoregressive VaR by Regression Quantiles and Machine Learning Algorithms — → 2412.06193
and 34 more
  1. Deep Learning for Cross-Border Transaction Anomaly Detection in Anti-Money Laundering Systems — → 2412.07027
  2. A Multifrequency Data Fusion Deep Learning Model for Carbon Price Prediction (2024) — link
  3. Enhancing the accuracy of stock return movement prediction in Indonesia through recent fundamental value incorporation in multilayer perceptron (2024) — link
  4. MT2ST: Adaptive Multi-Task to Single-Task Learning (2024) — link
  5. TextSquare: Scaling up Text-Centric Visual Instruction Tuning (2024) — link
  6. P-values and confidence intervals for weighted log-rank tests under truncated binomial design based on clustered medical data (2024) — link
  7. Measuring digitalization capabilities using machine learning (2024) — link
  8. Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization (2024) — link
  9. Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives (2024) — link
  10. Approach Advancing Stock Market Forecasting with Joint RMSE Loss LSTM-CNN Model (2023) — link
  11. WiCross: I Can Know When You Cross Using COTS WiFi Devices (2023) — link
  12. Local and Overall Deviance R-Squared Measures for Mixtures of Generalized Linear Models (2023) — link
  13. Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning (2022) — link
  14. ReLAX: Reinforcement Learning Agent Explainer for Arbitrary Predictive Models (2021) — link
  15. Predicting stock returns of Tehran exchange using LSTM neural network and feature engineering technique (2021) — link
  16. Costly Features Classification using Monte Carlo Tree Search (2021) — link
  17. Forecasting directional movements of stock prices for intraday trading using LSTM and random forests (2020) — link
  18. Stock Market Price Prediction Using LSTM RNN (2018) — link
  19. Testing a Multi-factor Capital Asset Pricing Model in the Jordanian Stock Market (2018) — link
  20. Deep learning with long short-term memory networks for financial market predictions (2017) — link
  21. Empirical Test of Single Factor and Multi-Factor Asset Pricing Models: Evidence from Non Financial Firms on the Ghana Stock Exchange (GSE) (2015) — link
  22. Optimal shipment decisions for an airfreight forwarder: Formulation and solution methods (2012) — link
  23. A Multifactor Model of Banking Industry Stock Returns: An Emerging Market Perspective (2011) — link
  24. Regression Modeling Strategies (2003) — link
  25. Forecasting S&P 500 stock index futures with a hybrid AI system (1998) — link
  26. GraphSnapShot: Graph Machine Learning Acceleration with Fast Storage and Retrieval (2024) — link
  27. Confusion-Resistant Federated Learning via Diffusion-Based Data Harmonization on Non-IID Data (2024) — link
  28. Knowledge Graph Embedding and Few-Shot Relational Learning Methods for Digital Assets in USA (2024)
  29. Distance recomputator and topology reconstructor for graph neural networks (2024)
  30. Algorithms and Applications of Explainable Machine Learning (2023)
  31. On stock return prediction with LSTM networks (2017)
  32. A five-factor asset pricing model (2013) — link
  33. Local Regression Models (2010) — link
  34. CNML 2025, February 21–23, 2025, Nanjing,

4 of 42 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.