Insights
Analytiqal shares its insights, experience and thought-leadership through frequent posts on this page to help organizations thrive and expand their thinking. Our content is targeted to those business leaders looking for hands-on discussions and solutions to challenges in data science, AI, financial crime, and regulatory domains. Feel free to contact us if you want to discuss any of these in more detail.
Featured insight
Local LLMs for AML: do they work in practice in 2026?
Three years on from our initial LLM AI benchmark for Financial Economic Crime, we return with a more operationally grounded test. Using 55,000+ sanctions entries across 12 sources, we evaluate whether local LLMs can reliably handle sanctions and transaction monitoring alert work in 2026. Tested models show meaningful variation in accuracy (51–81%), conclusion quality (71–93%), and speed. With the right tuning, the industry-standard 95% accuracy threshold appears within reach. Prerequisites inclu…
Read MoreDive into our thoughtware
Explainable AI: unlocking value in FEC operations
Adherence to AML regulations within the EU has ensured that financial institutions generate a constant stream of financial crime risk signals from various processes (e.g. Transaction Monitoring, client due diligence reviews). Contrary to industry standard black box models, Explainable predictive models can help to streamline the operational processes to address these risk signals by allowing insig…
Read More
Benchmarking AI solutions for FEC challenges
We tested the use of some Large-Language models (Artificial Intelligence) in the Financial Economic Crime context We found that given the requirements on AI processing power, the trial-and-error nature of prompt engineering for LLMs, and results from this analysis showing false-negative conclusions are very feasible with LLM outputs, companies facing AML, Sanctions and KYC challenges should think …
Read MoreCommunications on Analytiqal.nl contain general information only and are intended solely for informational purposes. Analytiqal and its related entities do not, through this communication, provide professional advice or services. Before making any financial, risk-related, or business decisions, it is advisable to seek the guidance of a qualified professional adviser contracted for such purposes. This website contains links to third-party sites that are not under the control of Analytiqal or its affiliates. Reference to such information does not imply association with, endorsement of, approval of the site or its operators, as Analytiqal or its affiliates are not responsible for the products, services, or other content hosted therein.