Benchmarking Quantum Models for Time-series Forecasting

TL;DR

This paper benchmarks various quantum models against classical methods for time-series forecasting, finding classical models generally outperform quantum ones, but some quantum models perform comparably or better on specific datasets.

Contribution

It provides the first comprehensive benchmarking of quantum forecasting models against classical approaches using real-world data.

Findings

Classical models outperform quantum models overall.

Some quantum models achieve comparable results to classical models.

Two quantum models outperform ARIMA on a specific dataset.

Abstract

Time series forecasting is a valuable tool for many applications, such as stock price predictions, demand forecasting or logistical optimization. There are many well-established statistical and machine learning models that are used for this purpose. Recently in the field of quantum machine learning many candidate models for forecasting have been proposed, however in the absence of theoretical grounds for advantage thorough benchmarking is essential for scientific evaluation. To this end, we performed a benchmarking study using real data of various quantum models, both gate-based and annealing-based, comparing them to the state-of-the-art classical approaches, including extensive hyperparameter optimization. Overall we found that the best classical models outperformed the best quantum models. Most of the quantum models were able to achieve comparable results and for one data set two quantum models outperformed the classical ARIMA model. These results serve as a useful point of comparison for the field of forecasting with quantum machine learning.