A paper written by Associate Professor Takayuki Sakuma of the Faculty Faculty of Economics, titled "Quantum Differential Machine Learning," has been published in the international academic journal Quantum Economics and Finance.

A paper written by Associate Professor Takayuki Sakuma of the Faculty Faculty of Economics, titled "Quantum Differential Machine Learning," has been published in the international academic journal Quantum Economics and Finance.

This journal is an international peer-reviewed journal covering interdisciplinary research into the application of quantum mechanics-based formalisms and methods to economics and finance, and covers a wide range of areas in quantum social science, including applications of quantum algorithms to finance and quantum decision theory.

In this paper, we propose a new machine learning approach that incorporates gradient-based optimization techniques in quantum computing. We verify the accuracy of estimating the prices and sensitivities (delta vega) of financial derivatives through numerical experiments, and demonstrate the possibility of applying this approach to financial risk management.

This research will contribute to the practical extension of quantum machine learning by incorporating quantum algorithms into classical differential machine learning. Please see the paper below.

Associate Professor

Takayuki Sakuma

​

Specialized Field

finance

Research theme

Quantification of financial risks, pricing of financial derivatives