search

XanaduAI / QHack2021

Official repo for QHack—the quantum machine learning hackathon
https://qhack.ai
122 stars 94 forks source link

Using Quantum Generative Adversarial Networks for Portfolio Optimisation #70

Open calumholker opened 3 years ago

calumholker commented 3 years ago

Team Name:

QLords

Project Description:

We implement a quantum generative adversarial network on stock market data. The generator takes as an input 32 data points of stock market data for the previous days and predicts the following 8 days. Due to limitations in computing speed and time a limited application of this was implemented, using only 100 sequences and 1 epoch to fit within the time frame, but demonstrates how the model is scalable to increase accuracy with more epochs and data.

We further implement QAOA and VQE algorithms on historical stock market data in place of the data that we would get if we had a fully scaled up generator. This demonstrates how this data can be used to solve the mean variance portfolio optimisation problem, and is benchmarked against a classical solver for this example.

Presentation:

https://calumholker.medium.com/using-quantum-generative-adversarial-networks-for-portfolio-analysis-f8c56ac68fd2

Source code:

https://github.com/calumholker/quantum-portfolio-optimisation

co9olguy commented 3 years ago

Thanks for the submission! We hope you have enjoyed participating in QHack :smiley:

We will be assessing the entries and contacting the winners separately. Winners will be publicly announced sometime in the next month.

We will also be freezing the GitHub repo as we sort through the submitted projects, so you will not be able to update this submission.