CaixaBank uses hybrid of conventional and quantum computers to classify risk

CaixaBank has used quantum computing technology to develop a machine learning algorithm to calculate customer credit risk as part of its analysis of the technology’s application in banking. This follows the Spanish bank’s tests of quantum computing during the latest financial year.

Quantum computers will be used alongside conventional computers in a hybrid model that sees each used at different points in the calculation of customer credit risk. The technology makes the machine learning more effective in huge data sets.

The technology will be able to make calculations that traditional computers are fundamentally unable to do. If practical, they would mark a leap forward in computing capability far greater than that from the abacus to a modern computer.

It uses quantum mechanics to process huge amounts of data through its ability to be in multiple states, and perform computations in powerful new ways not possible with today. This could, in theory, allow researchers to quickly solve problems involving different combinations of variables.

CaixaBank used public data corresponding to 1,000 artificial users to test the technology for risk analysis, and is one of several banks testing out the technology in different banking scenarios.

The results of this test demonstrated that “hybrid computing can achieve results comparable to those offered by the conventional solution in less time”, said Caixabank.

The bank said that it has been improving its skills in deploying quantum versions of classical algorithms for the past year. “For CaixaBank, it is essential to invest in exploring the potential of quantum computing for various areas of the financial sector, although the first commercial applications may take a while,” it said.

It is not alone. Dutch bank ABN Amro is working with researchers to explore how the technology can be used to secure online banking. It is working with Delft University of Technology and the Netherlands Organisation for Applied Scientific Research, to prove that quantum key distribution can be used to secure data traffic.

In the future, quantum computers will be able to crack encryption methods, and today’s security systems for internet and mobile banking will no longer be sufficient.

The five application areas for quantum computing are:

1. Drug and materials discovery: Untangling the complexity of molecular and chemical interactions leading to the discovery of medicines and materials.
2. Supply chain and logistics: Finding the optimal path across global systems for ultra-efficient logistics and supply chains, such as optimising fleet operations for deliveries during the holiday season.
3. Financial services: Finding ways to model financial data and isolating key global risk factors to make better investments.
4. Artificial intelligence (AI): Making facets of AI, such as machine learning, much more powerful when datasets can be too big, such as searching images or video.
5. Cloud security: Making cloud computing more secure by using the laws of quantum physics to enhance private data safety.