Abstract
Credit scoring models become a key role for lending institutions to distinguish good applicants (likely to repay) from bad applicants (likely to default), and attracting significant attention from researchers and market participants. Many standard statistical and machine learning techniques are used in the literature to build credit scoring models from training sets consisting of people in their records who were given loans in the past.
Online peer-to-peer (P2P) lending is a new financing channel which is based on electronic business platform and electronic commerce credit. In P2P lending, borrowers and lenders can use the internet platform to achieve online transactions. There is lower transaction cost, while the loan process is simple and easy to operate. Small and micro enterprises and individual borrowers that are difficult to get loans from the bank do not need loan guarantor and collateral in P2P, so they can get financing more easily. But it means higher credit risk to lenders.
Many classification methods such as neural networks, support vector machines and random forests, have been suggested in the literature to improve credit scoring models in terms of their statistical performance. But there execution time can grow exponentially with the size of the instances, especially with the grow of Big Data sources like mobile phone data and social network data for credit scoring applications [18]. For these cases, metaheuristics like Hidden Markov Model (HMM) present a good alternative solution technique. A limitation of HMM is that it only supports one observed random variable. In case of the credit scoring, there are more variables that are relevant to the estimation. Multi dimensional Hidden Markov Model (MDHMM) extends hidden Markov model by supporting multiple observed variables. The iterative procedure of MDHMM greatly simplifies parallelized implementation and computations of innovative Big Data sources in credit scoring.
The aim of this paper is to investigate the performance of MDHMM to addresses the credit scoring problem in Peer-To-Peer (P2P) lending. The performance of the proposed MDHMM method is validated on Lending Club (Peer-to-peer lending) credit dataset.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Baesens, B., Van Gestel, T., Viaene, S., Stepanova, M., Suykens, J., Vanthienen, J.: Benchmarking state-of-the-art classification algorithms for credit scoring. J. Oper. Res. Soc. 54(6), 627–635 (2003)
Henley, W.E., Hand, D.J.: Construction of a k-nearest neighbour credit-scoring system. IMA J. Math. Appl. Bus Ind. 8, 305–321 (1997)
Sahin, Y., Bulkan, S., Duman, E.: A cost-sensitive decision tree approach for fraud detection. Expert. Syst. Appl. 40, 5916–5923 (2013)
West, D.: Neural network credit scoring models. Comput. Oper. Res. 27, 1131–1152 (2000)
Huang, C.L., Chen, M.C., Wang, C.J.: Credit scoring with a data mining approach based on support vector machines. Expert. Syst. Appl. 33, 847–856 (2007)
Teng, G.-E., He, C.-Z., Xiao, J., Jiang, X.-Y.: Customer credit scoring based on HMM/GMDH hybrid model. Knowl. Inf. Syst. 36(3), 731–747 (2013)
Rabiner, L.R.: A tutorial on Hidden Markov Models and selected applications in speech recognition. Proc. IEEE 77, 257–286 (1989)
Chen, M.-Y., Kundu, A., et al.: Off-line handwritten word recognition using a hidden Markov model type stochastic network. IEEE Trans. Pattern Anal. Mach. Intell. 16(5), 481–496 (1994). ISSN 0162-8828
Khadr, M.: Forecasting of meteorological drought using Hidden Markov Model (case study: the upper Blue Nile river basin, Ethiopia). Ain Shams Eng. J. 7(1), 47–56 (2016). ISSN 2090-4479
Baum, L.E., Petrie, T., Soules, G., Weiss, N.: A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains. Ann. Math. Stat. 41(1), 164–171 (1970)
Bilmes J.A.: A gentle tutorial of the EM algorithm and its application to parameter estimation for Gaussian mixture and Hidden Markov Models, U.C. Berkeley, TR- 97-021 (1998). http://citeseer.ist.psu.edu/1570.html
Li, X., Parizeau, M., Plamondon, R.: Training Hidden Markov Models with multiple observations-a combinatorial method? IEEE Trans. Pattern Anal. Mach. Intell. 22(4), 371–377 (2000)
Ye, F., Yi, N., Wang, Y.: EM algorithm for training high-order Hidden Markov Model with multiple observation sequences. J. Inf. Comput. Sci. 8(10), 1761–1777 (2011)
Hadar, U., Messer, H.: High-order Hidden Markov Models? Estimation and implementation. In: Proceedings of the IEEE/SP 15th Workshop on Statistical Signal Processing, pp. 249–252 (2009)
Badreddine, B., Souad, B., Abdelhak, Z., Ismail, E.: Classification with Hidden Markov Model. Appl. Math. Sci. 8(50), 2483–2496 (2014)
UCI machine learning repository. http://archive.ics.uci.edu/ml
Óskarsdóttir, M., et al.: The value of big data for credit scoring: enhancing financial inclusion using mobile phone data and social network analytics. Appl. Soft Comput. J. (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Monir, E.A., Ouzineb, M., Benyacoub, B. (2020). Multi Dimensional Hidden Markov Model for Credit Scoring Systems in Peer-To-Peer (P2P) Lending. In: Farhaoui, Y. (eds) Big Data and Networks Technologies. BDNT 2019. Lecture Notes in Networks and Systems, vol 81. Springer, Cham. https://doi.org/10.1007/978-3-030-23672-4_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-23672-4_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-23671-7
Online ISBN: 978-3-030-23672-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)