Scientific Presentations

LabTalks­@DCD

Department of Digital and Computational Demography
Max Planck Institute for Demographic Research (MPIDR), Rostock, Germany, January 29, 2025

Germans Savcisens, Computational Social Scientist at Northeastern University in Boston gives a talk on “Life-trajectories in high-dimensional spaces”.

Abstract

We represent human lives in a way that shares structural similarity to language, and we exploit this similarity to adapt natural language processing techniques to examine the evolution and predictability of human lives based on detailed event sequences. We do this by drawing on a comprehensive registry dataset, which is available for Denmark across several years, and that includes information about life-events related to health, education, occupation, income, address, and working hours, recorded with day-to-day resolution. We create embeddings of life-events in a single vector space, showing that this embedding space is robust and highly structured. Our models allow us to predict diverse outcomes ranging from early mortality to personality nuances, outperforming state-of-the-art models by a wide margin.

About

Germans Savcisens is a postdoctoral research associate in the Khoury College of Computer Sciences at Northeastern University, based in Boston. He is also a member of the Network Science Institute.  Savcisens’ research focuses on enhancing the transparency and fairness of machine learning algorithms, such as those used in network science and natural language processing. He is particularly interested in mitigating biases in algorithms that model human behavior and social interactions, and in the impact of black-box technology on daily life. 

Prior to joining Khoury College, Savcisens was a doctoral student at the Technical University of Denmark and a guest researcher at the University of Copenhagen. He started as a human–computer interaction student, then, as he progressed through his undergraduate studies, his interest shifted to statistics and its application to quantifying outcomes. He became concerned with how developers and companies leverage statistical theory to infer user behavior and influence decisions through manipulation.

Register to Take Part

You would like to attend the Seminar Talk online? You are very welcome. Please register by using this link: survey.demogr.mpg.de

LabTalks­@DCD January 29th from 11 a.m. to 12 p.m. (Rostock time)