Reinforcement Learning for Household Finance: Designing Policy via Responsiveness

45 Pages Posted: 20 Sep 2022 Last revised: 16 Jan 2024

Date Written: August 16, 2022

Abstract

We use model-free reinforcement learning (RL) to investigate how a mortgage servicer can optimize her actions towards a borrower. Our methodology differs from the conventional heuristic approach, since we do not use subjective and qualitative judgments of industry and legal experts. We are the first to exploit the borrower's soft information post-securitization and her responsiveness to the servicer, to estimate an RL-policy rule. When maximizing her reward, the servicer learns the borrower's type dynamically. By doing so, the servicer can preempt the borrower's adversarial behavior, thereby increasing the borrower's cooperation.

Keywords: Reinforcement Learning, Household Finance, Soft Information, Moral Hazard, Experience Learning

undefined

JEL Classification: G2, G3, G4, G5, R2

Suggested Citation

Bandyopadhyay, Arka Prava and Maliar, Lilia, Reinforcement Learning for Household Finance: Designing Policy via Responsiveness (August 16, 2022). Available at SSRN: https://ssrn.com/abstract=4191586 or http://dx.doi.org/10.2139/ssrn.4191586

Arka Prava Bandyopadhyay (Contact Author)

New York University ( email )

New York
United States

Lilia Maliar

Professor of Economics ( email )

New York, NY
United States

0 References

    0 Citations

      Do you have a job opening that you would like to promote on SSRN?

      Paper statistics

      Downloads
      514
      Abstract Views
      1,001
      Rank
      111,511
      PlumX Metrics