Abstract—Credit risk is the possibility of a loss resulting from
a borrower’s failure to repay a loan or meet contractual
obligations. With the growing number of customers and
expansion of businesses, it’s not possible or at least feasible for
banks to assess each customer individually in order to minimize
this risk. Machine learning can leverage available user data to
model a behavior and automatically estimate a credit score for
each customer. In this research, we propose a novel approach
based on state machines to model this problem into a classical
supervised machine learning task. The proposed state machine is
used to convert historical user data to a credit score which
generates a data-set for training supervised models. We have
explored several classification models in our experiments and
illustrated the effectiveness of our modeling approach.
Index Terms—State machine, machine learning, classification,
credit risk, financial regulation.
Behnam Sabeti, Hossein Abedi Firouzjaee, Reza Fahmi are with Miras
Technologies International, Number 92, Movahed Danesh St., Tehran, Iran
(email: behnam@miras-tech.com, hossein@miras-tech.com,
reza@miras-tech.com).
Saeid Safavi, Wenwu Wang, and Mark D. Plumbley are with CVSSP,
University of Surrey, Guildford, Surrey GU2 7XH, UK (email:
s.safavi@surrey.ac.uk, w.wang@surrey.ac.uk, m.plumbley@surrey.ac.uk).
[PDF]
Cite: Behnam Sabeti, Hossein Abedi Firouzjaee, Reza Fahmi, Saeid Safavi, Wenwu Wang, and Mark D. Plumbley, "Credit Risk Rating Using State Machines and Machine Learning," International Journal of Trade, Economics and Finance vol.11, no.6, pp. 163-168, 2020.
Copyright © 2020 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).