SnT director Björn Ottersten, pictured at a Paperjam + Delano Club 10x6 event in November 2020, says the project outcomes “have tremendous potential allowing the design of solutions that leverage data across several stakeholders in a secure and compliant manner.” Simon Verjus / Maison Moderne

SnT director Björn Ottersten, pictured at a Paperjam + Delano Club 10x6 event in November 2020, says the project outcomes “have tremendous potential allowing the design of solutions that leverage data across several stakeholders in a secure and compliant manner.”  Simon Verjus / Maison Moderne

Fintech pioneer Luxhub and the University of Luxembourg’s Interdisciplinary Centre for Security, Reliability and Trust (SnT) have announced a strategic partnership that they say will implement groundbreaking technology while respecting safety and privacy concerns.

The initial phase of the new partnership between Luxhub and SnT will see the project participants design and manage a secure federated learning platform. The teams will be focusing on several key use-cases that, says Luxhub, will “benefit the entire financial services industry, such as fraud detection, anti-money laundering, loan risk prediction, and transaction categorisation.”

Leveraging collective intelligence

The crucial distinction between federated learning and most machine learning models, is that it is the algorithm, the training of which will be assumed by the Luxhub team in collaboration with SnT researchers, and not the data that travels. “Federated learning allows the training of a model with your own data but without sharing the data with anyone else; you just share updates to a global model,” explains Prof. Radu State, Principal Investigator of the project at SnT. “The data stays on each client’s premises--in the case of a bank, down to a single branch--to avoid any risks, but the system allows every participant to leverage the collective intelligence to train the global model. It’s a win-win: everyone is better off by collaborating, while ensuring data security and privacy at the same time.”

Leveraging federated learning in the financial sector also means lower latency and less power consumption, as well as a significant decrease in false positives and therefore an important decrease in operating costs, according to Luxhub. The fintech company's role will be to enable more interaction and innovation within the financial services industry.

No data sharing risk

“In the era of Open Finance--with financial services companies collaborating, co-creating new products and services by taking advantage of the API economy--it makes sense for them to opt for the federated learning model, and keep building the future of finance,” says Luxhub COO Claude Meurisse.

The partners hope that the model could eventually be extended to additional use cases, dealing notably with key compliance topics, and more.

“Leveraging data and the knowledge of SnT researchers, this project with Luxhub on federated machine learning is highly innovative, aiming at identifying illicit financial activity by enabling shared learning, but without any risk in sharing data,” says SnT director Björn Ottersten. “The project outcomes have tremendous potential allowing the design of solutions that leverage data across several stakeholders in a secure and compliant manner.”