Quantum Credit Scoring

The objective of the project is to attempt to build a predictive machine learning model implemented on a quantum computer and a simulated quantum computer which has the potential to improve credit scoring accuracy. Credit scoring provides lenders and counterparties better transparency of the credit risk they are taking when dealing with a counterparty. For large companies, this transparency is provided by public credit ratings. Small companies are not covered by rating agencies and are suffering from reduced availability of credit. Machine learning approaches allow for automated credit scoring feasible for a broad coverage of small companies. The current approaches rely on classical machine learning algorithms applied to broad datasets that combine company, accounting, and socio-economic information. Improving the learning algorithms is thus an important element to providing credit risk transparency. This project will use quantum algorithms which cannot be implemented on today’s classical machines.