This paper builds a dynamic programming model to optimize the collections process in consumer credit. It determines which collections actions should be undertaken and how long they should be performed, including theoretical results about the form of the optimal policy under certain conditions. Finally, a case study is described based on data from the collections department of a European bank.
AndersonR.2007. The Credit Scoring Toolkit Theory and Practice for Retail Credit Risk Management and Decision Automation. Oxford University Press, Oxford.
3.
BennettR. L.CatarineuE.MoralG.. 2005. Loss given default validation, studies on the validation of internal rating systems. Working paper no. 14, Basel Committee on Banking Supervision, Basel, pp. 60–76.
4.
BertsekasD. P.2007. Dynamic Programming and Optimal Control. 3rd edn, Vol. I. Athena Scientific, Nashua, NH.
5.
ChinA. G.KotakH.. 2006. Improving the debt collection process using rule‐based decision engines: A case study of capital one. Int. J. Infor. Manage. 26: 81–88.
LucasA.2006. Basel II problem solving. Available athttp://www3.imperial.ac.uk/portal/pls/portallive/docs/1/7287866.PDF(accessed May 5, 2008).
8.
MakuchW. M.DodgeJ. L.EckerJ. G.GranforsD. C.HahnG. J.. 1992. Managing consumer credit delinquency in the US economy: A multi-billion dollar management science application. Interfaces 22(1): 90–109.
9.
MatuszykA.MuesC.ThomasL. C.. 2010. Modelling LGD for unsecured personal loans: Decision tree approach. J. Oper. Res. Soc. 61: 393–398.
10.
McNabH.WynnA.. 2000. Principles and Practice of Consumer Credit Risk Management. CIB Publishing, Canterbury.
11.
PutermanM. L.1994. Markov Decision Processes. Wiley, New York.
12.
YuJ.‐Y.GittinsJ. C.. 2008. Models and software for improving the profitability of pharmaceutical research. Eur. J. Oper. Res.189: 459–475.
