The search is on for near term applicable quantum algorithms. The financial sector is one field where improvements to computationally challenging tasks could be highly beneficial. We have explored...Show moreThe search is on for near term applicable quantum algorithms. The financial sector is one field where improvements to computationally challenging tasks could be highly beneficial. We have explored the use of quantum machine learning for one such task, the generation of synthetic financial data. Building on the current classical state of the art, we have implemented a Wasserstein generative adversarial network with gradient penalty for the generation of synthetic time series. We have expanded this classical framework using a parametrised quantum generator circuit. By using Pauli string expectation values, we can generate multi-dimensional continuous samples. This approach has allowed for the generation of small scale synthetic time series samples, based on the S&P 500 index, that show characteristic signs of the same temporal properties present in real financial data.Show less