Paper: arXiv 2310.07427
Authors: Zhengmeng Xu, Yujie Wang, Xiaotong Feng, Yilin Wang, Yanli Li, Hai Lin
Abstract
We propose a time series forecasting method named Quantum Gramian Angular Field (QGAF). This approach merges the advantages of quantum computing technology with deep learning, aiming to enhance the precision of time series classification and forecasting. We successfully transformed stock return time series data into two-dimensional images suitable for Convolutional Neural Network (CNN) training by designing specific quantum circuits. Distinct from the classical Gramian Angular Field (GAF) approach, QGAF’s uniqueness lies in eliminating the need for data normalization and inverse cosine calculations, simplifying the transformation process from time series data to two-dimensional images. To validate the effectiveness of this method, we conducted experiments on datasets from three major stock markets: the China A-share market, the Hong Kong stock market, and the US stock market. Experimental results revealed that compared to the classical GAF method, the QGAF approach significantly improved time series prediction accuracy, reducing prediction errors by an average of 25% for Mean Absolute Error (MAE) and 48% for Mean Squared Error (MSE). This research confirms the potential and promising prospects of integrating quantum computing with deep learning techniques in financial time series forecasting.
Complexity vs Empirical Score
- Math Complexity: 8.5/10
- Empirical Rigor: 7.0/10
- Quadrant: Holy Grail — high math complexity, high empirical rigor
Why this score: The paper employs advanced quantum circuit design and deep learning (CNN) with specific mathematical transformations (QGAF), resulting in high mathematical complexity; it is backtest-ready with experiments on real financial data from three major markets and specific error metrics (MAE, MSE).
Research Flowchart
flowchart TD A["Research Goal: Enhance Stock Return Prediction Accuracy"] --> B["Data: Stock Return Series<br>China A-share, Hong Kong, US Markets"] B --> C["Methodology: Quantum Gramian Angular Field<br>Circuit Design without Normalization/Inverse Cosine"] C --> D["Computational Process: Transform Time Series to 2D Images"] D --> E["Training: Convolutional Neural Networks CNNs"] E --> F["Forecasting: Time Series Classification & Prediction"] F --> G["Outcome: 25% Reduction in MAE & 48% Reduction in MSE<br>vs. Classical GAF Method"]
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 time series forecasting method named Quantum Gramian Angular Field (QGAF).
Source sentence
We propose a time series forecasting method named Quantum Gramian Angular Field (QGAF).
Assumes
No explicit assumptions found in the text.
Data
- Daily return time series of selected blue‑chip stocks market-prices public
Source sentence
We used daily return time series of multiple stocks from the China A‑share market (600030. SH, 600036. SH, 600519. SH, 601166. SH, and 601318. SH), the Hong Kong stock market (0005. HK, 0700. HK, 0939. HK, 0941. HK, and 1299. HK), and the U.S. stock market (Boeing, Dow Chemical, IBM, JPMorgan Chase, and Procter & Gambl
- Data acquisition via yfinance and Tushare market-prices public
Source sentence
The data acquisition was done using Python libraries: the yfinance library from Yahoo Finance for U.S. stocks and the Tushare library for both the China A‑share and the Hong Kong stock markets.
Costs
Not applicable
Finds 2
- QGAF reduces prediction errors compared to classical GAF, decreasing MAE by an average of 25% and MSE by an average of 48% across three stock markets. predictive-accuracy
Source sentence
In total, MAE decreased by an average of 25%, and MSE decreased by an average of 48% in these three stock markets.
- The QGASF method outperforms the traditional GASF in predictive performance. performance
Source sentence
The QGASF method outperforms the traditional GASF.
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.
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.