Importance The article addresses the need to develop an integrated approach to creditworthiness assessment based on performance indicators of small businesses that characterize all aspects of their operations. Objectives The purpose of the study is to develop an algorithm to evaluate the borrowing power and to build a logical model of creditworthiness of small businesses that would consider every facet of their operations and a low degree of financial stability. Methods Using the methods of comparison and analogy, we review existing approaches to evaluation of small business creditworthiness. Results The developed methodology rests on machine learning techniques, which make it sufficiently complete and detailed. The techniques imply finding, revealing and analyzing indicators that comprehensively describe the operations of small business entities. We propose a systematization of factors of creditworthiness, which will enable a straightforward and efficient assessment. Conclusions The existing methods to assess small business creditworthiness mainly focus on business analysis. However, to provide an adequate assessment, the methodology should take into account not only financial performance, but also business reputation, efficiency of basic resource utilization, level of competitiveness, and market position.
Keywords: creditworthiness, small business, scoring, risk, machine learning
References:
Altman E. Financial Ratios, Discriminant Analysis and the Prediction of Corporate Bankruptcy. Journal of Finance, 1968, vol. 23, no. 4, pp. 589–609.
Beaver W.H. Financial ratios as predictors of failure. Journal of Accounting Research, 1966, vol. 4, pp. 71–111.
Chesser D. Predicting loan noncompliance. The Journal of Commercial Bank Lending, 1974, no. 56(12), pp. 28–38.
Dimitriu M., Oprea I.A. Modeling Credit Scoring. Metalurgia International, 2010, no. 5, Special Issue, pp. 62–67.
Cox D.R., Snell E.J. Analysis of Binary Data. London, Chapman and Hall, 1989, 240 p.
Bhatia S., Sharma P., Burman R., Hazari S. et al. Credit Scoring Using Machine Learning Techniques. International Journal of Computer Applications, 2017, vol. 161, no. 11, pp. 1–4.
Hosmer D., Lemeshow S. Applied Logistic Regression. John Wiley & Sons, Inc., 2000. doi: 10.1002/0471722146
Mortazavi E., Ahmadzadeh M. A Hybrid Approach for Automatic Credit Approval. International Journal of Scientific & Engineering Research, 2014, vol. 5, iss. 8, pp. 614–619.
Sorokin A.S. [Building a scorecard using a logistic regression model]. Naukovedenie, 2014, no. 2. (In Russ.) URL: Link
Yatsko V.A. [Development of credit scoring model using soft computations]. Biznes. Obrazovanie. Pravo. Byulleten' Volgogradskogo instituta biznesa = Business. Education. Law. Bulletin of Volgograd Business Institute, 2015, no. 2, pp. 251–255. (In Russ.)
Bazmara A., Donighi S.S. Bank Customer Credit Scoring by Using Fuzzy Expert System. International Journal of Intelligent Systems and Applications, 2014, vol. 11, pp. 29–35. doi: 10.5815/ijisa.2014.11.04
Hoffmann F., Baesens B., Martens J. et al. Comparing a genetic fuzzy and a neurofuzzy classifier for credit scoring. International Journal of Intelligent Systems, 2002, vol. 17, iss. 11, pp. 1067–1083. doi: 10.1002/int.10052
Malhotra R., Malhotra D.K. Differentiating between good credits and bad credits using neuro-fuzzy systems. European Journal of Operational Research, 2002, vol. 136, iss. 1, pp. 190–211. URL: Link00052-2
Nosratabadi H.E., Nadali A., Pourdarab S. Credit Assessment of Bank Customers by a Fuzzy Expert System Based on Rules Extracted from Association Rules. International Journal of Machine Learning and Computing, 2012, vol. 2, no. 5, pp. 662–666.
Sampath S., Kalaichelvi V. Assessment of Mortgage Applications Using Fuzzy Logic. International Journal of Social, Behavioral, Educational, Economic, Business and Industrial Engineering, 2014, vol. 8, no. 11, pp. 3487–3491.
Lai K.K., Yu L., Zhou L.G., Wang S.Y. Neural Network Metalearning for Credit Scoring. URL: Link
Lee T.-S., Chen I.-F. A two-stage hybrid credit scoring model using artificial neural networks and multivariate adaptive regression splines. Expert Systems with Applications, 2005, vol. 28, iss. 4, pp. 743–752. URL: Link
Malhotra R., Malhotra D.K. Evaluating consumer loans using neural networks. Omega, 2003, vol. 31, iss. 2, pp. 83–96. URL: Link00016-1
Pacelli V., Azzollini M. An Artificial Neural Network Approach for Credit Risk Management. Journal of Intelligent Learning Systems and Applications, 2011, vol. 3, pp. 103–112. doi: 10.4236/jilsa.2011.32012
West D. Neural network credit scoring models. Computers & Operations Research, 2000, no. 27, pp. 1131–1152.
Vorontsov K.V. Matematicheskie metody obucheniya mashin po pretsedentam (teoriya obucheniya mashin) [Mathematical methods of case-based machine learning (machine learning theory)]. URL: Link (In Russ.)
Jarrow R.A., Turnbull S. Pricing derivatives on financial securities subject to credit risk. The Journal of Finance, 1995, vol. 50, iss. 1, pp. 53–85. doi: 10.1111/j.1540-6261.1995.tb05167.x