A dynamic interest rate adjusting mechanism for online social lending

ABSTRACT

Social lending is a dynamic trading mechanism that can directly match one consumer with another consumer. Most manual transaction processes conducted by traditional financial institutions can be done automatically and tailored to each consumer in social lending. In this paper, we focus on an automatic interest adjustment and incentive mechanism for borrowers because they are crucial for dynamic social lending since they could help increase worth and reduce payment delays. First, we propose a Bayesian updating method for interest rate adjustment that considers the influence of their social groups on borrowers. Our method determines an accurate rate because the borrower's delay history is dynamically reflected in the rate decision. Second, we propose an incentive mechanism that improves a borrower's payment delay score. The mechanism offers incentives for payment with rewards (penalties) to borrowers. We demonstrate the efficiency on our proposed methods by conducting agent simulations.

REFERENCES

• 1: J. Falkinger, E. Fehr, S. Gachter, and R. Winter-Ebmer. A simple mechanism for the efficient provision of public goods: Experimental evidence. The American Economic Review, 90(1):247--264, 2000.
• 2: M. Ghatak. Group lending, local information and peer selection. Journal of Development Economics, 60:27--50, 1999.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
        I.2.11 Distributed Artificial Intelligence

General Terms:
Algorithms, Design, Experimentation

Keywords:
Bayesian estimation, incentive mechanisms, interest rate adjustment, social lending