News

European Conference on Quality in Official Statistics 2026

We will be at the European Conference on Quality in Official Statistics (Q2026), which will take place from Wednesday 3rd to Friday 5th June 2026 in Šibenik, Croatia.

Session 21, Thursday, 14:15 - A session on the AIML4OS project, with presentations from Eimear Crowley (WP1, Coordination), Olivier Meslin (WP3, AI/ML Lab), Luis Sanguiao (WP5 and MLUtils), and Remco Paulussen (WP7).
Session 16, Thursday, 11:00 - This is a special session on our workpackage on ‘Standards, Methodology & Implementation’ (WP5). The speakers here will be Jean-Marc Museux (Eurostat), Florian Dumpert (Destatis), Jakob Engdahl (Statistics Sweden) and Marco Puts (Statistics Netherlands).
Session 31, Friday, 09:00 - This special session focuses on our ‘Text to Code’ workpackage (WP10). The speakers on this session will be Ariane Lestrade (Destatis), Yu-Lin Huang (Université du Luxembourg), Andrés Jurado Prieto (Statistics Spain) and Ewelina Niewiadomska (Statistics Poland).

Session 3, Wednesday, 11:00 - Luis Ferreira will be presenting on Unlocking Legacy Statistics with Large Language Models, based on work carried out by WP12.
Speed Talk Session 3, Wednesday, 13:15 - This session will have a number of presentations from members of AIML4OS, including Alexander Kowarik, Johannes Gussenbauer, Elena Rosa-Perez and Pedro Sousa.
Session 8, Wednesday, 14:15 - Sónia Quaresma will present on the work of the Ecosystem Monitoring workpackage (WP4), with a talk titled No one is without knowledge except he who asks no questions. Klaudia Peszat will also present in this session with a talk on The usefulness of good old ML models in real estate statistics.
Session 13, Wednesday, 16:30 - Nina Niederhametner who works with WP10 will present on Using AI for Automatic Data Extraction and Classification in Official Statistics. Giulio Massacci will also present in this session with a talk titled: Who Works in the Green Transition? A Patent-Based Analysis of Occupational Change Using Large Language Models. The session also includes Luis Sanguiao again, speaking on High frequency time series imputation with auxiliary data: a deep learning approach.

Our first newsletter, highlighting the project launch, upcoming datalab presentation, and planned participation at NTTS 2025.
The second newsletter has info on three in-person meetings that took place, as well as more details on individual workpackages.
Our third newsletter was released after the first year of the project. It looked at plans across all of the workpackages, as well as an update following NTTS 2025.
Newsletter number four reports on an in-person meeting of WP12, more details on WP10, as well as a template for training materials.
Our fifth newsletter has details on a deliverable on citizen-in-the-loop, news on text classification, and progress on reconstruction of supply-chain networks.
The sixth newsletter has details on a deliverable on citizen-in-the-loop, news on text classification, and progress on reconstruction of supply-chain networks.