Publications

Distance between occupations and job transitions of job seekers after training (with Damien Mayaux, Yagan Hazard, Thomas Zuber)

[Forthcoming, Economie et Statistique / Economics and Statistics] [Working paper version (French)]

Does vocational training help reduce structural imbalances in the labor market? We construct a new measure of the skills gap between occupations by fine-tuning a language model on a large sample of job offers. Using this measure, we show that the difference in return to employment between trained and untrained workers is driven by reallocations to occupations that are far removed in terms of skills from the last job held. From a purely reallocative perspective, however, the difference in return to employment linked to vocational training does not appear to be driven by more redirections to occupations in high demand.

Working papers

Convergence to collusion in algorithmic pricing

[Revise & Resubmit, International Journal of Industrial Organization] [SSRN]

Artificial intelligence algorithms are increasingly used by firms to set prices. Previous research shows that they can exhibit collusive behavior, but how quickly they can do so has so far remained an open question. I show that a modern deep reinforcement learning model deployed to price goods in a repeated oligopolistic competition game with continuous prices converges to a collusive outcome in an amount of time that matches empirical observations, under reasonable assumptions on the length of a time step. This model reliably shows cooperative behavior supported by reward-punishment schemes that discourage deviations.

Work in progress

Selection and Productivity in the Public Sector: Evidence from Italian Teachers

R packages

  • MST-based k-means clustering (code, CRAN)
  • Principal curves of oriented points, as introduced in Delicado and Huerta (2003) (code, CRAN)