Paper: arXiv 2502.09625

Authors: Shuozhe Li, Zachery B Schulwol, Risto Miikkulainen

Abstract

To the naked eye, stock prices are considered chaotic, dynamic, and unpredictable. Indeed, it is one of the most difficult forecasting tasks that hundreds of millions of retail traders and professional traders around the world try to do every second even before the market opens. With recent advances in the development of machine learning and the amount of data the market generated over years, applying machine learning techniques such as deep learning neural networks is unavoidable. In this work, we modeled the task as a multivariate forecasting problem, instead of a naive autoregression problem. The multivariate analysis is done using the attention mechanism via applying a mutated version of the Transformer, “Stockformer”, which we created.

Complexity vs Empirical Score

  • Math Complexity: 7.0/10
  • Empirical Rigor: 4.0/10
  • Quadrant: Lab Rats — high math complexity, limited empirical testing

Why this score: The paper uses advanced deep learning architecture (Transformer/attention) and multivariate time-series modeling, indicating high math complexity. However, the excerpt focuses on problem formulation, data sourcing, and conceptual design without showing actual implementation code, backtest results, or statistical metrics, placing it in the theoretical ‘Lab Rats’ quadrant.

Research Flowchart

  flowchart TD
  A["Research Goal<br>Forecast Stock Prices<br>Using Multivariate Analysis"] --> B["Data Collection<br>Market Data & External Factors"]
  B --> C["Data Preprocessing<br>Normalization & Feature Engineering"]
  C --> D["Model Architecture<br>Custom 'Stockformer' Transformer"]
  D --> E["Attention Mechanism<br>Multivariate Time-Series Processing"]
  E --> F["Training & Validation<br>Deep Learning Neural Networks"]
  F --> G["Key Findings<br>Transformer models effectively<br>capture chaotic market patterns"]

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Proposes

The paper proposes a mutated Transformer model called Stockformer for multivariate stock price forecasting.

Source sentence
the multivariate analysis is done using the attention mechanism via applying a mutated version of the Transformer, ”Stockformer”, which we created.

Assumes 1

  • The market is inefficient, allowing relationships among stock prices to be exploited. market
    Source sentence
    By assuming the inefficiency of the market and taking the advantage of the relationships among the stock prices, the trader can make advantageous decisions to beat the market.

Data

No dataset named in the text.

Costs

Unclear The classifier was not confident.

Finds

No quantified findings extracted.

Checked by others

No other paper in the archive has been found to support or contradict these findings. Coverage is partial, so this is neither replication nor refutation.

Code

No repository by the authors found in the paper.

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.

Cited References (22)

  1. \href http://ijr.sagepub.com/content/9/2/62.abstract Passive Dynamic Walking (1990) — link
  2. A new approach to linear filtering and prediction problems (1960)
  3. Stock market prediction performance of neural networks: A literature review (2017)
  4. Simple technical trading rules and the stochastic properties of stock returns (1992)
  5. Persuasive evidence of market inefficiency (1998)
  6. A comparison of artificial neural network and time series models for forecasting commodity prices (1996) — link
  7. Informer: Beyond efficient transformer for long sequence time-series forecasting (2021)
  8. A study on fundamental and technical analysis (2013)
and 14 more
  1. Stock market prediction using different neural network classification architectures (1996) — link
  2. Integrating Fundamental and Technical Analysis of Stock Market through Multi-layer Perceptron (2018) — link
  3. Deep learning for time series classification: a review (2019)
  4. Time series classification from scratch with deep neural networks: A strong baseline (2017)
  5. Gradient-based learning applied to document recognition (1998) — link
  6. Empirical evaluation of gated recurrent neural networks on sequence modeling (2014) — link
  7. Long short-term memory (1997)
  8. CNNpred: CNN-based stock market prediction using a diverse set of variables (2019) — link
  9. Recurrent Neural Networks in Time Series Prediction
  10. A CNN-LSTM-based model to forecast stock prices (2020)
  11. Attention is all you need (2017)
  12. Gradient flow in recurrent nets: the difficulty of learning long-term dependencies (2001)
  13. A new statistic and practical guidelines for nonparametric Granger causality testing (2006)
  14. Time2vec: Learning a vector representation of time (2019) — link

0 of 22 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.