CaixaBank is stepping up its experimental application of quantum computing in financial services, developing a machine learning algorithm to classify customers according to their credit risk.
The Spanish bank last year reported on its tests of IBM's Framework Opensource Qiskit, to implement a quantum algorithm to assess the financial risk of a mortgage portfolio and treasury bills portfolio specifically created for the project using real data.
For its latest trials, the bank has applied a hybrid computing framework — which combines quantum computing and conventional computing in different phases of the calculation process — to classify credit risk profiles. To do this, CaixaBank used a public data set corresponding to 1,000 artificial users, with a similar profile to existing customers, but with information configured specifically for the test.
With the full results yet to be published, the bank's preliminary investigation reveals that a combined application of hybrid algorithms to risk analysis calculations can reach the same conclusions as the classical method in much less time
In conclusion, the bank states: "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."