ARLINGTON, Va. – In recent bank trials, FinTech innovator Consilient demonstrated successful federated machine learning for the detection of financial crime. Traditionally, financial institutions silo their efforts to combat financial crime due to regulatory, privacy, technology, and competitive burdens. Consilient’s Dozer™ technology platform recently overcame these obstacles by using federated machine learning, a technique that trains algorithms to be shared across multiple financial institutions. Dozer leapfrogs the current systems for anti-money laundering and countering the financing of terrorism (AML/CFT) systems by sharing the algorithms and not the data. Dozer increased the effectiveness and efficiency in one study, reducing false positives from above 90% down to 12% while increasing the true positive discovery rate. Detailed measurements from the bank trials can be found here.
For future phases of the Dozer rollout, Consilient entered into partnership with Intel to provide confidential computing through the use of Intel’s Software Guard Extensions (Intel® SGX) technology, which uses a hardware-based trusted execution environment to help isolate and protect data.
Consilient was publicly launched on 29 October 2020, by founder and CEO Gary M. Shiffman, Ph.D. (founder and CEO of Giant Oak and creator of GOST®), and Juan Zarate, global co-managing partner and chief strategy officer at K2 Integrity.
According to Juan, “This revolutionary federated learning approach begins to solve the fundamental challenges we see in the current AML/CFT system, and when scaled, will form the basis for a new design for compliance risk management for financial institutions and regulators globally. Financial institutions allocate large budgets for financial crime compliance and fraud detection. Consilient’s design provides a solution that helps decrease the cost and increases the efficiency needed to discover and manage real risk in their enterprises.”
Read the full press release.