1. MMC
  2. All Volumes and Issues
  3. Volume 11, Number 1, 2024
  4. A hybrid variable neighborhood search with bootstrap resampling technique for credit scoring problem

A hybrid variable neighborhood search with bootstrap resampling technique for credit scoring problem

MMC.
2024;
Volume 11, Number 1
: pp. 109–119
https://doi.org/10.23939/mmc2024.01.109
Received: June 27, 2023
Revised: February 02, 2024
Accepted: February 13, 2024

Barhdadi M., Benyacoub B., Ouzineb M. A hybrid variable neighborhood search with bootstrap resampling technique for credit scoring problem. Mathematical Modeling and Computing. Vol. 11, No. 1, pp. 109–119 (2024)

Authors:
  1. M. Barhdadi
  2. B. Benyacoub
  3. M. Ouzineb
1
National Institute for Statistics and Applied Economics, Rabat, Morocco
2
National Institute for Statistics and Applied Economics, Rabat, Morocco
3
National Institute for Statistics and Applied Economics, Rabat, Morocco

Credit scoring models have played a vitally important role in the granting credit by lenders and financial institutions.  Recently, these have gained more attention related to the risk management practice.  Many modeling techniques have been developed to evaluate the worthiness of borrowers.  This paper presents a credit scoring model via one of local search methods – variable neighborhood search (VNS) algorithm.  The optimizing VNS neighborhood structure is a useful method applied to solve credit scoring problems.  By simultaneously tuning the neighborhood structure, the proposed algorithm generates optimized weights which are used to build a linear discriminant function.  The experimental results obtained by applying this model on simulated and real datasets prove its high efficiency and  evaluate its significant value on credit scoring.

credit scoring
mathematical modeling
variable neighborhood search algorithm
linear classification
resampling technique
  1. Crook J. N., Edelman D. B., Thomas L. C.  Recent developments in consumer credit risk assessment.  European Journal of Operational Research.  183 (3), 1447–1465 (2007).
  2. Lee T.-S., Chiu C.-C., Chou Y.-C., Lu C.-J.  Mining the customer credit using classification and regression tree and multivariate adaptive regression splines.  Computational Statistics & Data Analysis.  50 (4), 1113–1130 (2006).
  3. Thomas L. C.  A survey of credit and behavioural scoring: forecasting financial risk of lending to consumers.  International Journal of Forecasting.  16 (2), 149–172 (2000).
  4. Westgaard S., van der Wijst N.  Default probabilities in a corporate bank portfolio: a logistic model approach.  European Journal of Operational Research.  135 (2), 338–349 (2001).
  5. Henley W. E., Hand D. j.  Construction of a k-nearest-neighbour credit-scoring system.  IMA Journal of Management Mathematics.  8 (4), 305–321 (1997).
  6. Khashman A.  Neural networks for credit risk evaluation: investigation of different neural models and learning schemes.  Expert Systems with Applications.  37 (9), 6233–6239 (2010).
  7. Rosenberg E., Gleit A.  Quantitative methods in credit management: a survey.  Operations Research.  42 (4), 589–613 (1994).
  8. Baesens B., Van Gestel T., Viaene S., Stepanova M., Suykens J., Vanthienen J.  Benchmarking state-of-the-art classification algorithms for credit scoring.  Journal of the Operational Research Society.  54 (6), 627–635 (2003).
  9. Mladenović N., Hansen P.  Variable neighborhood search.  Computers & Operations Research.  24 (11), 1097–1100 (1997).
  10. Hansen P., Mladenović N.  Variable neighborhood search: principles and applications.  European Journal of Operational Research.  130 (3), 449–467 (2001).
  11. Bickel P. J., Götze F., van Zwet W. R.  Resampling fewer than n observations: Gains, losses, and remedies for losses.  Statistica Sinica.  7 (1), 1–31 (1997).
  12. Politis D., Romano J., Wolf M.  Subsampling.  Springer, New York (1999).
  13. Bickel P. J., Sakov A.  Extrapolation and the bootstrap.  Sankhya: The Indian Journal of Statistics, Series A.  64 (3), 640–652 (2002).
  14. Bickel P. J., Sakov A.  On the choice of $m$ in the $m$ out of $n$ bootstrap and confidence bounds for extrema.  Statistica Sinica.  18, 967–985 (2008).
  15. Kleiner A., Talwalkar A., Sarkar P., Jordan M. I.  The big data bootstrap. Preprint arXiv:1206.6415 (2012).
  16. Kleiner A., Talwalkar A., Sarkar P., Jordan M. I.  A scalable bootstrap for massive data.  Journal of the Royal Statistical Society: Series B (Statistical Methodology).  76 (4), 795–816 (2014).
  17. Sengupta S., Volgushev S., Shao X.  A Subsampled Double Bootstrap for Massive Data.  Journal of the American Statistical Association.  111 (515), 1222–1232 (2016).
  18. Caravagna G., Ramazzotti D.  Learning the structure of Bayesian Networks via the bootstrap.  Neurocomputing.  448, 48–59 (2021).
  19. Magasarian O. L.  Linear and non linear separation of patterns by linear programming.  Operations Research.  13 (3), 444–452 (1965).
  20. Freed N., Glover F.  Simple but powerful goal programming models for discriminant problems.  European Journal of Operational Research.  7 (1), 44–60 (1981).
  21. Freed N., Glover F.  Evaluating alternative linear, programming models to solve the twogroup discriminant problem.  Decision Science.  17 (2), 151–162 (1986).
  22. Bequé A., Lessmann S.  Extreme learning machines for credit scoring: An empirical evaluation.  Expert Systems with Applications.  86, 42–53 (2017).
  23. Teng G.-E., He C.-Z., Xiao J., Jiang X.-Y.  Customer credit scoring based on HMM/GMDH hybrid model.  Knowledge and Information Systems.  36 (3), 731–747 (2013).