PALO ALTO, Calif. and SÃO PAULO, Brazil, May 4, 2022 — Itaú Unibanco, the largest bank in Latin America, and QC Ware, a leading quantum software and services company, today announced the first results of a collaboration that is exploring quantum computing algorithms for the banking industry.
The goal of the four-month joint project was to investigate whether quantum computing can help customer retention. QC Ware developed quantum machine learning algorithms that improve the accuracy of the models currently used to predict customer churn. During the collaboration the two teams developed novel methods that run on today’s classical computers and can already improve the prediction models, achieving a substantial increase in the previously tested customer retention model. Moreover, these algorithms will also run even faster on future quantum computers using the inherent ability of quantum computers to perform complex linear algebra tasks.
The ongoing objective of the collaboration is to understand the power of quantum algorithms and help prepare Itaú Unibanco to fully deploy quantum solutions in banking.
“Keeping our customers satisfied is a top priority at Itaú Unibanco and we will continue to stay at the forefront of implementing innovative technologies” according to Moisés Nascimento, Chief Data Officer at Itaú Unibanco. “We see in quantum computing the potential to greatly improve customer interactions and we have already benefited from QC Ware’s insights with existing customer retention algorithms.”
Itaú Unibanco provided QC Ware with two years’ worth of anonymized user data and approximately 180,000 data points, with the goal of better understanding which customers were likely to leave the bank in the next three months. QC Ware developed quantum methods for training a customer retention model based on determinant sampling techniques. The quantum methods have improved accuracy and decreased run times compared to classical techniques. Furthermore, QC Ware found a way to deploy a variant of these methods on today’s classical computers,that improved Itaú Unibanco’s model, increasing the amount of withdrawals captured by 2%, and increasing the overall model’s precision from 71% to 77.5%. The algorithm can continue to run on classical computers for the time being and it is ready to run on future quantum hardware.
The initial collaboration between the two companies is aligned with Itaú Unibanco’s goal to build quantum expertise within the company and prepare it for the imminent deployment of quantum computing throughout the financial services industry. This initiative combines Itaú Unibanco’s expertise in banking, with QC Ware’s leading edge in both classical and quantum algorithms.
“This has been an insightful project for us, and a novel use of both quantum and quantum inspired determinant sampling techniques to enhance machine learning models,” said Iordanis Kerenidis, Head of Quantum Algorithms at QC Ware. “We are thrilled to have developed powerful quantum methods and also find ways to improve both performance and efficiency today. We’re excited about the prospects of quantum computing in financial services.”
About QC Ware
QC Ware is a quantum software and services company focused on ensuring enterprises are prepared for the emerging quantum computing disruption. QC Ware specializes in the development of applications for near-term quantum computing hardware with a team composed of some of the industry’s foremost experts in quantum computing. Its growing network of customers includes AFRL, Aisin Group, Airbus, BMW Group, Itau Unibanco, Covestro, Equinor, Goldman Sachs, and Total. QC Ware Forge, the company’s flagship quantum computing cloud service, is built for data scientists with no quantum computing background. It provides unique, performant, turnkey quantum computing algorithms. QC Ware is headquartered in Palo Alto, California, and supports its European customers through its subsidiary in Paris. QC Ware also organizes Q2B, the largest annual gathering of the international quantum computing community.
Source: QC Ware Corp.