Paper Image

Using quantum computing to enhance stock return predictions

Published on:

11 October 2023

Primary Category:

Machine Learning

Paper Authors:

Zhengmeng Xu,

Hai Lin


Key Details

Proposes Quantum Gramian Angular Field (QGAF) to convert time series data into images using quantum circuits

Eliminates normalization and arccosine calculations compared to classical GAF

Trains convolutional neural networks on QGAF images for stock return forecasting

Reduces MAE error by 25% and MSE error by 48% versus classical GAF

Validates benefits of combining quantum computing and deep learning

AI generated summary

Using quantum computing to enhance stock return predictions

This paper proposes a new method called Quantum Gramian Angular Field (QGAF) that combines quantum computing with deep learning for improved time series forecasting. It transforms stock return data into 2D images using quantum circuits, then trains convolutional neural networks on these images to predict future returns. Experiments show QGAF reduces errors by 25% for MAE and 48% for MSE versus classical methods, demonstrating the promise of quantum machine learning for financial analysis.

Answers from this paper


No comments yet, be the first to start the conversation...

Sign up to comment on this paper

Sign Up