This was part of Decision Making under Uncertainty

Time-Constrained Sequential Neural Decision Procedures in Multialternative Choice Problems

Fabio Maccheroni, Bocconi University
Monday, May 2, 2022


We introduce an algorithmic decision process for multialternative choice, the Neural Metropolis Algorithm, that combines binary comparisons and Markovian exploration. We show that a stochastic version of transitivity, a basic tenet of rationality, makes this algorithm value-based. In so doing, we extend to decision procedures some classic stochastic choice notions.