Optimal Scoring for Dynamic Information Acquisition

Résumé 0

A principal seeks to learn about a binary state and can do so by enlisting an agent to acquire information over time using a Poisson information arrival technology. The agent learns about this state privately, and his effort choices are unobserved by the principal. The principal can reward the agent with a prize of fixed value as a function of the agent's sequence of reports and the realized state. We identify conditions that each individually ensure that the principal cannot do better than by eliciting a single report from the agent after all information has been acquired. We also show that such a static contract is suboptimal under sufficiently strong violations of these conditions. We contrast our solution to the case where the agent acquires information "all at once;" notably, the optimal contract in the dynamic environment may provide strictly positive base rewards to the agent even if his prediction about the state is incorrect.