Embeddings of Nation-Level Social Networks
For nation-scale networks, we present a layer-sensitive random walk, temporal alignment and partitioning techniques and evaluate them on 13 downstream tasks.
Births are difficult to predict even with rich survey and full-population register data
Major life events have proven difficult to predict. Does this reflect limits of theory, data, and algorithms, or the large role of chance? We examine one outcome - having a child within three years - through a near-ideal setting for prediction: a data …
The Equilibrium Effects of Workers’ Outside Employment Options: Evidence from a Labour Market Integration
We study a reform that eased cross-border commuting from France to the high-wage Swiss labor market. The results show that if labour supply is elastic enough, the local labour market can expand and absorb additional competition for workers.
Networks in the market for researchers
We study the role of collaboration networks for placing PhD students in the U.S. We observe a sizable citation premium for graduates placed through the advisor's network. However, when comparing graduates hired at the same university, the productivity premium …
Population-Scale Network Embeddings Expose Educational Divides in Network Structure Related to Right-Wing Populist Voting
Administrative registry data can be used to construct population-scale networks whose ties reflect shared social contexts between persons. With machine learning, such networks can be encoded into numerical representations -- embeddings -- that automatically …
Empirical Privacy Evaluations of Generative and Predictive Machine Learning Models -- A review and challenges for practice
Synthetic data generators, when trained using privacy-preserving techniques like differential privacy, promise to produce synthetic data with formal privacy guarantees, facilitating the sharing of sensitive data. However, it is crucial to empirically assess …