Quantum generative modeling for financial time series with temporal correlations
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914480880877568 |
|---|---|
| author | Dechant, David Schwander, Eliot van Drooge, Lucas Moussa, Charles Garlaschelli, Diego Dunjko, Vedran Tura, Jordi |
| author_facet | Dechant, David Schwander, Eliot van Drooge, Lucas Moussa, Charles Garlaschelli, Diego Dunjko, Vedran Tura, Jordi |
| contents | Quantum generative adversarial networks (QGANs) have been investigated as a method for generating synthetic data with the goal of augmenting training data sets for neural networks. This is especially relevant for financial time series, since we only ever observe one realization of the process, namely the historical evolution of the market, which is further limited by data availability and the age of the market. However, for classical generative adversarial networks it has been shown that generated data may (often) not exhibit desired properties (also called stylized facts), such as matching a certain distribution or showing specific temporal correlations. Here, we investigate whether quantum correlations in quantum inspired models of QGANs can help in the generation of financial time series. We train QGANs, composed of a quantum generator and a classical discriminator, and investigate two approaches for simulating the quantum generator: a full simulation of the quantum circuits, and an approximate simulation using tensor network methods. We tested how the choice of hyperparameters, such as the circuit depth and bond dimensions, influenced the quality of the generated time series. The QGAN that we trained generate synthetic financial time series that not only match the target distribution but also exhibit the desired temporal correlations, with the quality of each property depending on the hyperparameters and simulation method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_22035 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Quantum generative modeling for financial time series with temporal correlations Dechant, David Schwander, Eliot van Drooge, Lucas Moussa, Charles Garlaschelli, Diego Dunjko, Vedran Tura, Jordi Quantum Physics Disordered Systems and Neural Networks Data Analysis, Statistics and Probability Computational Finance Statistical Finance Quantum generative adversarial networks (QGANs) have been investigated as a method for generating synthetic data with the goal of augmenting training data sets for neural networks. This is especially relevant for financial time series, since we only ever observe one realization of the process, namely the historical evolution of the market, which is further limited by data availability and the age of the market. However, for classical generative adversarial networks it has been shown that generated data may (often) not exhibit desired properties (also called stylized facts), such as matching a certain distribution or showing specific temporal correlations. Here, we investigate whether quantum correlations in quantum inspired models of QGANs can help in the generation of financial time series. We train QGANs, composed of a quantum generator and a classical discriminator, and investigate two approaches for simulating the quantum generator: a full simulation of the quantum circuits, and an approximate simulation using tensor network methods. We tested how the choice of hyperparameters, such as the circuit depth and bond dimensions, influenced the quality of the generated time series. The QGAN that we trained generate synthetic financial time series that not only match the target distribution but also exhibit the desired temporal correlations, with the quality of each property depending on the hyperparameters and simulation method. |
| title | Quantum generative modeling for financial time series with temporal correlations |
| topic | Quantum Physics Disordered Systems and Neural Networks Data Analysis, Statistics and Probability Computational Finance Statistical Finance |
| url | https://arxiv.org/abs/2507.22035 |