Paper: arXiv 2412.07223
Authors: Zong Ke, Jingyu Xu, Zizhou Zhang, Yu Cheng, Wenjun Wu
Abstract
This paper provides a unique approach with AI algorithms to predict emerging stock markets volatility. Traditionally, stock volatility is derived from historical volatility,Monte Carlo simulation and implied volatility as well. In this paper, the writer designs a consolidated model with back-propagation neural network and genetic algorithm to predict future volatility of emerging stock markets and found that the results are quite accurate with low errors.
Complexity vs Empirical Score
- Math Complexity: 4.0/10
- Empirical Rigor: 6.5/10
- Quadrant: Street Traders — empirical and applied, lower math complexity
Why this score: The paper applies a standard GA-BP neural network architecture without deep mathematical derivations or novel theory, but it includes detailed empirical implementation using a specific 10-year dataset, data preprocessing steps, and references to real financial databases like Wind.
Research Flowchart
flowchart TD
A["Research Goal: Predict Volatility<br>in Emerging Markets"] --> B["Data Inputs:<br>Historical Market Data"]
B --> C["Key Methodology:<br>Back-Propagation Neural Network<br>and Genetic Algorithm"]
C --> D{"Computational Process:<br>Model Training & Optimization"}
D --> E["Key Finding:<br>Accurate Volatility Prediction<br>with Low Error Rates"]
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 consolidated model that combines a back‑propagation neural network with a genetic algorithm to predict volatility of emerging stock markets.
Source sentence
In this paper, the writer designs a consolidated model with back‑propagation neural network and genetic algorithm to predict future volatility of emerging stock markets and found that the results are quite accurate with low errors.
Assumes 4
- The GA provides global search capability that avoids local optima and overfitting. model
Source sentence
global search and regularization term of GA avoids local optima and overfitting
- BP neural networks can effectively handle nonlinear problems in volatility prediction. model
Source sentence
strong non‑linear mapping capability enables BP neural network to process nonlinear problems
- Missing values and outliers are treated by interpolation and normalization before analysis. data
Source sentence
Preprocessing has been conducted before further analysis, including treatment of missing values and outliers using interpolation and normalization respectively.
- Logarithmic returns calculated from daily closing prices adequately represent price dynamics for volatility modeling. data
Source sentence
using the price2ret function and the daily closing price data of the CSI 300 Index, we calculated the logarithmic returns
Data
- CSI 300 Index market-prices commercial
Source sentence
We selected the sample period as the past ten years, from May 6, 2014, to May 26, 2024. Index data were fetched from the Wind database
Costs
Not applicable
Finds 2
- The proposed GA‑BP model predicts volatility very well with insignificant prediction errors. predictive-accuracy
Source sentence
we can see, that our designed model can predict very well and predicted errors are pretty insignificant.
- Genetic algorithms improve the prediction accuracy of the original BP neural network. performance
Source sentence
genetic algorithms can improve the accuracy of prediction for the original BP neural network.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 42 related papers). Coverage is partial, so this is neither replication nor refutation.
1 paper in the archive
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.