Lunch is available beginning at 12 PM

Speaker to begin promptly at 12:30 PM

Abstract: How predictable are life trajectories? How much can predictability be improved with more data and better algorithms?  What are the sources of inherent unpredictability that seem impossible to overcome in the foreseeable future?  In this talk, I’ll present a series of studies addressing these questions including: 1) a scientific mass collaboration involving hundreds of researchers; 2) an in-depth qualitative study of about 40 specially selected families; and 3) our award-winning submission to an international data science challenge that involved fine-tuning an open weight LLMs with complete population-scale data.  The talk will highlight opportunities for collaboration and open questions, especially those related to life trajectories, precision health, and LLMs.

Contributions to and/or sponsorship of any event does not constitute departmental or institutional endorsement of the specific program, speakers or views presented.