no code implementations • 13 Feb 2024 • Andrea Coletta, Kshama Dwarakanath, Penghang Liu, Svitlana Vyetrenko, Tucker Balch
We make an assumption that LLMs can be used as implicit computational models of humans, and propose a framework to use synthetic demonstrations derived from LLMs to model subrational behaviors that are characteristic of humans (e. g., myopic behavior or preference for risk aversion).
1 code implementation • 19 Jun 2023 • Penghang Liu, A. Erdem Sarıyüce
In this work, we develop a practical temporal graph generator, Motif Transition Model (MTM), to generate synthetic temporal networks with realistic global and local features.
no code implementations • 18 Jan 2023 • Penghang Liu, Rupam Acharyya, Robert E. Tillman, Shunya Kimura, Naoki Masuda, Ahmet Erdem Sarıyüce
For the Venmo network, we investigate the interplay between financial and social relations on three tasks: friendship prediction, vendor identification, and analysis of temporal cycles.
no code implementations • 16 Oct 2022 • Penghang Liu, Kshama Dwarakanath, Svitlana S Vyetrenko, Tucker Balch
We evaluate the behavior of sub-rational human investors using hand-crafted market scenarios and SHAP value analysis, showing that our model accurately reproduces the observations in the previous studies and reveals insights of the driving factors of human behavior.