Application of time-series quantum generative model to financial data

TL;DR

This paper applies a quantum time-series generative model to actual financial data, demonstrating its effectiveness in generating future data, filling missing values, and requiring fewer parameters than classical methods.

Contribution

It adapts and evaluates a quantum generative model for real financial data, showing advantages over classical models in parameter efficiency and versatility.

Findings

Fewer parameters needed compared to classical methods

Effective for both stationary and nonstationary data

Successful generation of future financial data

Abstract

Despite proposing a quantum generative model for time series that successfully learns correlated series with multiple Brownian motions, the model has not been adapted and evaluated for financial problems. In this study, a time-series generative model was applied as a quantum generative model to actual financial data. Future data for two correlated time series were generated and compared with classical methods such as long short-term memory and vector autoregression. Furthermore, numerical experiments were performed to complete missing values. Based on the results, we evaluated the practical applications of the time-series quantum generation model. It was observed that fewer parameter values were required compared with the classical method. In addition, the quantum time-series generation model was feasible for both stationary and nonstationary data. These results suggest that several parameters can be applied to various types of time-series data.