Paper: arXiv 2309.16196

Authors: Wenting Liu, Zhaozhong Gui, Guilin Jiang, Lihua Tang, Lichun Zhou, Wan Leng, Xulong Zhang, Yujiang Liu

Abstract

With the increasing volume of high-frequency data in the information age, both challenges and opportunities arise in the prediction of stock volatility. On one hand, the outcome of prediction using tradition method combining stock technical and macroeconomic indicators still leaves room for improvement; on the other hand, macroeconomic indicators and peoples’ search record on those search engines affecting their interested topics will intuitively have an impact on the stock volatility. For the convenience of assessment of the influence of these indicators, macroeconomic indicators and stock technical indicators are then grouped into objective factors, while Baidu search indices implying people’s interested topics are defined as subjective factors. To align different frequency data, we introduce GARCH-MIDAS model. After mixing all the above data, we then feed them into Transformer model as part of the training data. Our experiments show that this model outperforms the baselines in terms of mean square error. The adaption of both types of data under Transformer model significantly reduces the mean square error from 1.00 to 0.86.

Complexity vs Empirical Score

  • Math Complexity: 5.0/10
  • Empirical Rigor: 6.0/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper incorporates a mix of advanced statistical modeling (GARCH-MIDAS) and modern deep learning (Transformers), reflecting moderate mathematical complexity, and provides empirical results with specific error metrics (MSE reduction from 1.00 to 0.86) on real-world financial data, indicating practical implementation and testing.

Research Flowchart

  flowchart TD
  A["Research Goal:<br>Predict Stock Volatility<br>with Mixed-Frequency Data"] --> B{"Data Collection"}
  
  B --> C["Objective Factors<br>Technical & Macro Indicators"]
  B --> D["Subjective Factors<br>Baidu Search Indices"]
  
  C --> E["GARCH-MIDAS Model<br>for Data Alignment"]
  D --> E
  
  E --> F["Transformer Model<br>Input: Mixed-Frequency Data"]
  
  F --> G["Key Finding: Model Outperforms Baselines<br>MSE: 1.00 → 0.86<br>Significant reduction with hybrid data"]

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 Transformer model for stock volatility prediction that incorporates mixed‑frequency macroeconomic data and investor attention indicators via a GARCH‑MIDAS preprocessing step.

Source sentence
The outputs of the GARCH-MIDAS model are deployed to train the Transformer model, which is one of the innovations of this paper.

Assumes 5

  • The conditional mathematical expectation of the return at the (i‑1)‑th moment is µ and the short‑term component follows a GARCH(1,1) process. model
    Source sentence
    Assuming that the conditional mathematical expectation of ri,t at the (i-1)-th moment is µ and that the short-term component of the returns follows a GARCH(1, 1) process
  • The lag period K of the GARCH‑MIDAS model is set to 12 after repeated trials. model
    Source sentence
    The optimal value of the lag period K of the GARCH-MIDAS model is decided to be 12 after repeated trials.
  • Data are split into training and testing sets with a 9:1 ratio. data
    Source sentence
    To prove the validity of model construction, the prepared data is split into training and testing data with a 9:1 ratio.
  • Ten macroeconomic indicators are selected via grey correlation analysis to avoid subjective selection and redundancy. data
    Source sentence
    ten representative indicators are finally selected through grey correlation analysis to eliminate the influence of subjective selection and information redundancy
Show 1 more
  • Missing values are filled and data are normalized before model construction. data
    Source sentence
    pre-processing of all data is required before model construction for later use and analysis. The pre-processing mainly includes two aspects: missing value filling and data normalization.

Data

  • Macro‑economic indicators macro unknown
    Jan 2011 to Sep 2021
    Source sentence
    The data to be fed into the GARCH-MIDAS model contains macroeconomic indicators and returns of CSI300, which are collected from Jan 2011 to Sep 2021 on a monthly and daily basis, respectively.
  • CSI300 daily returns market-prices unknown
    Jan 2011 to Sep 2021 · CSI300 index
    Source sentence
    The data to be fed into the GARCH-MIDAS model contains macroeconomic indicators and returns of CSI300, which are collected from Jan 2011 to Sep 2021 on a monthly and daily basis, respectively.
  • Baidu search indices (CSI300, CSI500, SSE50) · Baidu alternative unknown
    Source sentence
    Subjective Factors Attention Indicators “CSI300” Baidu Search Index CSI300 “CSI500” Baidu Search Index CSI500 “SSE50” Baidu Search Index SSE50

Recognised sources: Refinitiv / LSEG (Datastream, Eikon, Tick History)

Costs

Not applicable The paper reports no trading or execution result.

Finds 3

  • Incorporating both macroeconomic and subjective attention indicators reduces the mean square error from 1.00 to 0.86. predictive-accuracy
    Source sentence
    The adaption of both types of data under Transformer model significantly reduces the mean square error from 1.00 to 0.86.
  • The full indicator set (macro, attention, and technical) achieves the lowest MSE (0.8624) among tested groups. performance
    Source sentence
    G4 0.8624 0.4460 0.5871 0.4787 1.3620 0.1710
  • The Transformer model outperforms LSTM, CNN, XGBoost, and GRU on most loss functions, achieving the best MSE (0.8624). performance
    Source sentence
    According to the results in Table 6, the Transformer model performs better than others commonly used for volatility prediction. It has the best results in terms of MSE, HMSE and MAPE loss functions

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 22 related papers). Coverage is partial, so this is neither replication nor refutation.

Cited by 1 paper in the archive (1 by independent authors)

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.