Advertisement

Machine Learning Analysis of Mortgage Credit Risk

  • Sivakumar G. PillaiEmail author
  • Jennifer Woodbury
  • Nikhil Dikshit
  • Avery Leider
  • Charles C. Tappert
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1069)

Abstract

In 2008, the US experienced the worst financial crisis since the Great Depression of the 1930s. The 2008 recession was fueled by poorly underwritten mortgages in which a high percentage of less-credit-worthy borrowers defaulted on their mortgage payments. Although the market has recovered from that collapse, we must avoid the pitfalls of another market meltdown. Greed and overzealous assumptions fueled that crisis and it is imperative that bank underwriters properly assess risks with the assistance of the latest technologies. In this paper, machine learning techniques are utilized to predict the approval or denial of mortgage applicants using predicted risks due to external factors. The mortgage decision is determined by a two-tier machine learning model that examines micro and macro risk exposures. In addition a comparative analysis on approved and declined credit decisions was performed using logistic regression, random forest, adaboost, and deep learning. Throughout this paper multiple models are tested with different machine learning algorithms, but time is the key driver for the final candidate model decision. The results of this study are fascinating and we believe that this technology will offer a unique perspective and add value to banking risk models to reduce mortgage default percentages.

Keywords

Machine Learning Model Mortgages Credit risk Logistic Regression Random Forest Classifier Deep Neural Network Classification and regression trees 

References

  1. 1.
    Arthur, B.: Housing and economic recovery act of 2008. Harv. J. Legis. 46, 585 (2009)Google Scholar
  2. 2.
    Calcagnini, G., Cole, R., Giombini, G., Grandicelli, G.: Hierarchy of bank loan approval and loan performance. Economia Politica, 1–20 (2018)Google Scholar
  3. 3.
    Critchfield, T., Dey, J., Mota, N., Patrabansh, S., et al.: Mortgage experiences of rural borrowers in the united states: insights from the national survey of mortgage originations. Technical report, Federal Housing Finance Agency (2018)Google Scholar
  4. 4.
    Denison, D.G.T., Mallick, B.K., Smith, A.F.M.: A Bayesian cart algorithm. Biometrika 85(2), 363–377 (1998)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Federal Financial Institutions Examination of Council: Home Mortgage Disclosure Act (2018)Google Scholar
  6. 6.
    Federal Home Loan Bank: Fhfa.gov, Federal Home Loan Bank Member Data | Federal Housing Finance Agency (2018). https://www.fhfa.gov/DataTools/Downloads/Pages/Federal-Home-Loan-Bank-Member-Data.aspx
  7. 7.
    Guiso, L., Pozzi, A., Tsoy, A., Gambacorta, L., Mistrulli, P.E.: The cost of distorted financial advice: evidence from the mortgage market (2018)Google Scholar
  8. 8.
    Hippler, W.J., Hossain, S., Kabir Hassan, M.: Financial crisis spillover from wall street to main street: further evidence. Empirical Econ., 1–46 (2018)Google Scholar
  9. 9.
    Inekwe, J.N., Jin, Y., Valenzuela, M.R.: The effects of financial distress: evidence from US GDP growth. Econ. Model. 72, 8–21 (2018)CrossRefGoogle Scholar
  10. 10.
    Kaplan, R.S., et al.: Discussion of economic conditions and key challenges facing the us economy. Technical report, Federal Reserve Bank of Dallas (2018)Google Scholar
  11. 11.
    Fieldhouse, A.J., Mertens, K., Ravn, M.O.: The macroeconomic effects of government asset purchases: evidence from postwar US housing credit policy. Q. J. Econ. 1, 58 (2018)Google Scholar
  12. 12.
    Ramya, R.S., Kumaresan, S.: Analysis of feature selection techniques in credit risk assessment. In: 2015 International Conference on Advanced Computing and Communication Systems, pp. 1–6. IEEE (2015)Google Scholar
  13. 13.
    SEC Emblem: Implementing the Dodd-Frank Wall Street Reform and Consumer Protection Act (2018). https://www.sec.gov/spotlight/dodd-frank.shtml
  14. 14.
    Turkson, R.E., Baagyere, E.Y., Wenya, G.E.: A machine learning approach for predicting bank credit worthiness. In: International Conference on Artificial Intelligence and Pattern Recognition (AIPR), pp. 1–7. IEEE (2016)Google Scholar
  15. 15.
    United States Census Bureau: FIPS Codes for the States and the District of Columbia (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Sivakumar G. Pillai
    • 1
    Email author
  • Jennifer Woodbury
    • 1
  • Nikhil Dikshit
    • 1
  • Avery Leider
    • 1
  • Charles C. Tappert
    • 1
  1. 1.Department of Computer SciencePace UniversityPleasantvilleUSA

Personalised recommendations