Advertisement

A Markov decision model for consumer term-loan collections

  • Zhixin Liu
  • Ping He
  • Bo Chen
Original Research

Abstract

We examine how to efficiently schedule collection actions for consumer term-loan accounts over time using a Markov decision model. A consumer loan account at each age can be classified into different account states, including current, delinquent, early payoff, default, and bankrupt. We model state transitions of loan accounts using a Markov transition matrix, and develop an optimization method to determine the collection action at each state and age for each consumer type to maximize the lender’s expected value. The optimization approach incorporates default risk and operational cost, and also addresses the time value of money, the tradeoff between interest revenue and borrowing cost, time consistency in optimization, competing risks between different account states, and penalty for late payment. Compared with a static collection policy, our method is demonstrably more valuable for accounts with high interest rates and medium to high loan amount, especially with stronger collection effects. We also demonstrate how the collection actions implemented under an optimal collection policy are affected by interest rate, loan amount, and collection effects.

Keywords

Dynamic programming Collection Markov process Optimization 

JEL Classification

G21 G23 

Notes

Acknowledgements

We sincerely thank the two anonymous reviewers for their valuable comments, which have significantly improved the quality of this work. The work of the second author is partly supported by the National Natural Science Foundation of China (No. 71571159).

References

  1. Altman EI (1989) Measuring corporate bond mortality and performance. J Finance 44:909–922CrossRefGoogle Scholar
  2. Altman EI, Saunders A (1998) Credit risk measurement: developments over the last 20 years. J Bank Finance 21:1721–1742CrossRefGoogle Scholar
  3. Asquith P, Mullins DW, Wolff ED (1989) Original issue high yield bonds: aging analysis of defaults, exchanges, and calls. J Finance 44:923–953CrossRefGoogle Scholar
  4. Betancourt L (1999) Using Markov chains to estimate losses from a portfolio of mortgages. Rev Quant Finance Account 12:303–318CrossRefGoogle Scholar
  5. Bierman H, Hausman WH (1970) The credit granting decision. Manag Sci 16:519–532CrossRefGoogle Scholar
  6. Briat P (2005) A Markovian approach to the analysis and optimization of a portfolio of credit card accounts. Master’s degree thesis, Department of Industrial and Systems Engineering, National University of SingaporeGoogle Scholar
  7. Butera G, Faff R (2006) An integrated multi-model credit rating system for private firms. Rev Quant Finance Account 27:311–340CrossRefGoogle Scholar
  8. Capon N (1982) Credit scoring systems: a critical analysis. J Mark 46:82–91CrossRefGoogle Scholar
  9. Chen LH, Chiou TW (1999) A fuzzy credit-rating approach for commercial loans: a Taiwan case. Omega Int J Manag S 27:407–419CrossRefGoogle Scholar
  10. Cunningham DF, Capone CA (1990) The relative termination experience of adjustable to fixed rate mortgages. J Finance 45:1687–1703CrossRefGoogle Scholar
  11. Curnow G, Kochman G, Meester S, Sarkar D, Wilton K (1997) Automating credit and collections decisions at AT&T capital corporation. Interfaces 27:29–52CrossRefGoogle Scholar
  12. Cyert RM, Davidson HJ, Thompson GL (1962) Estimation of the allowance for doubtful accounts by Markov chains. Manag Sci 8:287–303CrossRefGoogle Scholar
  13. De Almeida Filho AT, Mues C, Thomas LC (2010) Optimizing the collections process in consumer credit. Prod Oper Manag 19:698–708CrossRefGoogle Scholar
  14. Desai VS, Convay DG, Crook JN, Overstreet GA (1997) Credit scoring models in the credit union environment using neural networks and genetic algorithms. IMA J Math Appl Bus Ind 8:323–346Google Scholar
  15. federalreserve.gov (2018) Consumer Credit. http://www.federalreserve.gov/releases/g19/Current/. Accessed 2 Jan 2018
  16. Grimshaw SD, Alexander WP (2011) Markov chain models for delinquency: Transition matrix estimation and forecasting. Appl Stoch Model Bus 27:267–279CrossRefGoogle Scholar
  17. He P, Hua Z, Liu Z (2015) A quantification method for collection effects on consumer term loans. J Bank Finance 57:17–26CrossRefGoogle Scholar
  18. Kallberg JG, Saunders A (1983) Markov chain approaches to the analysis of payment behavior of retail credit customers. Financ Manag 12:5–14CrossRefGoogle Scholar
  19. Kang P, Zenios S (1992) Complete prepayment models for mortgage-backed securities. Manag Sci 38:1665–1685CrossRefGoogle Scholar
  20. Kukuk M, Rönnberg M (2013) Corporate credit default models: a mixed logit approach. Rev Quant Finance Account 40:467–483CrossRefGoogle Scholar
  21. Lawrence EC, Smith LD, Rhoades M (1992) An analysis of default risk in mobile home credit. J Bank Finance 16:299–312CrossRefGoogle Scholar
  22. Lee TS, Chiu CC, Lu CJ, Chen IF (2002) Credit scoring using the hybrid neural discriminant technique. Expert Syst Appl 23:245–254CrossRefGoogle Scholar
  23. Liebman LH (1972) A Markov decision model for selecting optimal credit control policies. Manag Sci 18:519–525CrossRefGoogle Scholar
  24. Makuch WM, Dodge JL, Ecker JG, Granfors DC, Hahn GJ (1992) Managing consumer credit delinquency in the US economy: a multi-billion dollar management science application. Interfaces 22:90–109CrossRefGoogle Scholar
  25. Malhotra R, Malhotra DK (2003) Evaluating consumer loans using neural networks. Omega Int J Manag S 31:83–96CrossRefGoogle Scholar
  26. Mehta D (1968) The formulation of credit policy models. Manag Sci 15:30–50CrossRefGoogle Scholar
  27. Min JH, Lee YC (2008) A practical approach to credit scoring. Expert Syst Appl 35:1762–1770CrossRefGoogle Scholar
  28. Ong CS, Huang JJ, Tzeng GH (2005) Building credit scoring models using genetic programming. Expert Syst Appl 29:41–47CrossRefGoogle Scholar
  29. Rosenberg E, Gleit A (1994) Quantitative methods in credit management: a survey. Opre Res 42:589–613CrossRefGoogle Scholar
  30. Smith LD, Jin B (2007) Modeling exposure to losses on automobile leases. Rev Quant Finance Account 29:241–266CrossRefGoogle Scholar
  31. Smith LD, Sanchez SM, Lawrence EC (1996) A comprehensive model for managing risk on home mortgage portfolios. Decis Sci 27:291–317CrossRefGoogle Scholar
  32. Smith LD, Bilir C, Huang VM, Hung KY, Kaplan M (2005) Citibank models credit risk on hybrid mortgage loans in Taiwan. Interfaces 35:215–229CrossRefGoogle Scholar
  33. Thomas LC (2000) A survey of credit and behavioural scoring: forecasting financial risk of lending to consumers. Int J Forecast 16:149–172CrossRefGoogle Scholar
  34. Thomas LC (2009) Consumer credit models: pricing profit and portfolios. Oxford University Press, New YorkCrossRefGoogle Scholar
  35. Thomas LC, Edelman DB, Crook JN (2002) Credit scoring and its applications. Society for Industrial and Applied Mathematics, PhiladelphiaCrossRefGoogle Scholar
  36. Thomas LC, Oliver RM, Hand DJ (2005) A survey of the issues in consumer credit modelling research. J Oper Res Soc 56:1006–1015CrossRefGoogle Scholar
  37. Trench MS, Pederson SP, Lau ET, Ma L, Wang H, Nair SK (2003) Managing credit lines and prices for bank one credit cards. Interfaces 33:4–21CrossRefGoogle Scholar
  38. West D (2000) Neural network credit scoring models. Comput Oper Res 27:1131–1152CrossRefGoogle Scholar
  39. Yobas MB, Crook JN, Ross P (2000) Credit scoring using neural and evolutionary techniques. IMA J Math Appl Bus Ind 11:111–125Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Management Studies, College of BusinessUniversity of Michigan–DearbornDearbornUSA
  2. 2.School of Business AdministrationSouth China University of TechnologyGuangzhouPeople’s Republic of China
  3. 3.School of ManagementHefei University of TechnologyHefeiPeople’s Republic of China

Personalised recommendations