SMU SOE Seminar Series (April 9, 2024): Applications of Deep Learning-Based Probabilistic Approach to "Combinatorial" Problems in Economics

Please click here if you are unable to view this page.

ABSTRACT Many “combinatorial” problems in economics arise from the static or discrete timing assumption that condenses a series of simple binary choices scattered randomly over time into a single instance. Leaning on this insight, we transform combinatorial choices into a sequence of binary choices in continuous time. The complexity of combinatorial choices turns into the dimensionality problem of dynamic optimization, which is overcome by applying a deep learning-based probabilistic approach. Two examples are provided for demonstration: 1) an exporting firm sporadically selects destinations among 100 potential interdependent markets; 2) a dynamic input-output network formation model involving 37 sectors. Keywords:Combinatorial choice, network formation, the curse of dimensionality, backward stochastic differential equation, deep learning. JEL Codes: C63, C67, D85, F23 Click here to view the CV. Click here to view the paper.
		PRESENTER Ji Huang The Chinese University of Hong Kong
		RESEARCH FIELDS Macro-finance Banking Numerical solutions of high-dimensional dynamic models
		DATE: 9 April 2024 (Tuesday)
		TIME: 4pm - 5.30pm
		VENUE: Meeting Room 5.1, Level 5 School of Economics Singapore Management University 90 Stamford Road Singapore 178903