Using Causal ML to select articles for promotion on the homepage and optimise article performanceRegister here
Felix Hagemeister joined the SZ data science team in September 2023. After receiving his PhD in Economics from LMU Munich in 2021, he held positions at the Technical University of Munich (TUM) and Stanford University. Inspired by econometrics, his main focus is to leverage causal inference techniques, often married with machine learning strategies, to gain actionable insights and help drive the subscriber business of SZ.
Cristina works in cross-functional teams (UX/UI, data, tech, editorial) to develop data products for the end-users (e.g. recommender systems in the app) and the NZZ’s internal users (e.g. decision support systems for journalists) and bring business value by leveraging AI technology (e.g. NLP techniques, supervised ML, causal ML). As product owner, her work ranges from educating about the opportunities and limitations of AI, defining vision, OKRs and business metrics, translating those metrics into detailed requirements (ML models, technical metrics, API specifications, etc.), planning, and working closely with the data scientists/ML engineers and data engineers to develop, deploy and continuously improve them in production. As the technical lead of the Data Science & Machine Learning area within the central Data team, Cristina defines the strategy and technical roadmap for NZZ’s MLOps platform, mentor and coach all Data Scientists & ML Engineers around all operational topics (algorithms, code, architecture, requirements, stakeholders, etc.)
Joel Persson is a research associate and PhD candidate at the Chair of Technology Marketing, ETH Zurich. He received dual masters and bachelors degrees in Statistics and Business & Economics from Lund University, Sweden.
His research interests are causal inference and statistical machine learning with marketing, operations, and economics applications. I am particularly interested in the use of algorithms and digital technologies and the implications this has for the efficiency, fairness, and explainability of data-driven decision-making. My research has explored these topics for targeting, personalization, and policy interventions in online platforms and marketplaces, digital marketing, and public health.
Joel is part of Algorithm Audit, a non-profit organization that builds and shares knowledge about ethical AI. I contribute to our software tools and policy reports. Previously, I interned as Machine Learning Scientist at Booking.com and consulted as a data scientist for the market intelligence company GfK. I have also held analytical and operational roles at leading companies in digital advertising and educational technology in Scandinavia.