Abstract: The aim of this paper is to compare and discuss better classifier algorithm options for credit risk assessment by applying different Machine Learning techniques. Using records from a Brazilian financial institution, this study uses a database of 5,432 companies that are clients of the bank, where 2,600 clients are classified as non-defaulters, 1,551 are classified as defaulters and 1,281 are temporarily defaulters, meaning that the clients are overdue on their payments for up 180 days. For each case, a total of 15 attributes was considered for a one-against-all assessment using four different techniques: Artificial Neural Networks Multilayer Perceptron (ANN-MLP), Artificial Neural Networks Radial Basis Functions (ANN-RBF), Logistic Regression (LR) and finally Support Vector Machines (SVM). For each method, different parameters were analyzed in order to obtain different results when the best of each technique was compared. Initially the data were coded in thermometer code (numerical attributes) or dummy coding (for nominal attributes). The methods were then evaluated for each parameter and the best result of each technique was compared in terms of accuracy, false positives, false negatives, true positives and true negatives. This comparison showed that the best method, in terms of accuracy, was ANN-RBF (79.20% for non-defaulter classification, 97.74% for defaulters and 75.37% for the temporarily defaulter classification). However, the best accuracy does not always represent the best technique. For instance, on the classification of temporarily defaulters, this technique, in terms of false positives, was surpassed by SVM, which had the lowest rate (0.07%) of false positive classifications. All these intrinsic details are discussed considering the results found, and an overview of what was presented is shown in the conclusion of this study.
Abstract: Generative Adversarial Net (GAN) has proved to be a powerful machine learning tool in image data analysis and generation. In this paper, we propose to use Conditional Generative Adversarial Net (CGAN) to learn and simulate time series data. The conditions include both categorical and continuous variables with different auxiliary information. Our simulation studies show that CGAN has the capability to learn different types of normal and heavy-tailed distributions, as well as dependent structures of different time series. It also has the capability to generate conditional predictive distributions consistent with training data distributions. We also provide an in-depth discussion on the rationale behind GAN and the neural networks as hierarchical splines to establish a clear connection with existing statistical methods of distribution generation. In practice, CGAN has a wide range of applications in market risk and counterparty risk analysis: it can be applied to learn historical data and generate scenarios for the calculation of Value-at-Risk (VaR) and Expected Shortfall (ES), and it can also predict the movement of the market risk factors. We present a real data analysis including a backtesting to demonstrate that CGAN can outperform Historical Simulation (HS), a popular method in market risk analysis to calculate VaR. CGAN can also be applied in economic time series modeling and forecasting. In this regard, we have included an example of hypothetical shock analysis for economic models and the generation of potential CCAR scenarios by CGAN at the end of the paper.
Abstract: The work proposes a decision support methodology
for the credit risk minimization in selection of investment projects.
The methodology provides two stages of projects’ evaluation.
Preliminary selection of projects with minor credit risks is made
using the Expertons Method. The second stage makes ranking of
chosen projects using the Possibilistic Discrimination Analysis
Method. The latter is a new modification of a well-known Method of
Fuzzy Discrimination Analysis.
Abstract: The aim of the present article is to determine the impact of the external and internal factors of bank performance on the profitability indicators of the CEE countries banks in the period from 2006 to 2012. On the basis of research conducted abroad on bank and macroeconomic profitability indicators, in order to obtain research results, the authors evaluated return on average assets (ROAA) and return on average equity (ROAE) indicators of the CEE countries banks. The authors analyzed profitability indicators of banks using descriptive methods, SPSS data analysis methods, as well as data correlation and linear regression analysis. The authors concluded that most internal and external indicators of bank performance have no direct influence the profitability of the banks in the CEE countries. The only exceptions are credit risk and bank size, which affect one of the measures of bank profitability – return on average equity.
Abstract: The banking sector poses a lot of problems in Nigeria in general and the non-oil export sector in particular. The banks' lack effectiveness in handling small, medium or long-term credit risk (lack of training of loan officers, lack of information on borrowers and absence of a reliable credit registry) results in non-oil exporters being burdened with high requirements, such as up to three years of financial statements, enough collateral to cover both the loan principal and interest (including a cash deposit that may be up to 30% of the loans' net present value), and to provide every detail of the international trade transaction in question. The stated problems triggered this research. Consequently, information on bank financing of non-oil exports was collected from 100 respondents from the 20 Deposit Money Banks (DMBs) in Nigeria. The data was analysed by the use of descriptive statistics correlation and regression. It is found that, Nigerian banks are participants in the financing of non-oil exports. Despite their participation, the rate of interest for credit extended to non-oil export is usually high, ranging between 15-20%. Small and medium sized non-oil export businesses lack the credit history for banks to judge them as reputable. Banks also consider the non-oil export sector very risky for investment. The banks actually do grant less credit than the exporters may require and therefore are not properly funded by banks. Banks grant very low volume of foreign currency loan in addition to, unfavorable exchange rate at which Naira is exchanged to the Dollar and other currencies in the country. This makes importation of inputs costly and negatively impacted on the non-oil export performance in Nigeria.
Abstract: This article analyses the relationship between
sovereign credit risk rating and gross domestic product for Central
and Eastern European Countries for the period 1996 – 2010. In order
to study the metioned relationship, we have used a numerical
transformation of the risk qualification, thus: we marked 0 the lowest
risk; then, we went on ascending, with a pace of 5, up to the score of
355 corresponding to the maximum risk. The used method of analysis
is that of econometric modelling with EViews 7.0. programme. This
software allows the analysis of data into a pannel type system,
involving a mix of periods of time and series of data for different
entities. The main conclusion of the work is the one confirming the
negative relationship between the sovereign credit risk and the gross
domestic product for the Central European and Eastern countries
during the reviewed period.
Abstract: While financial institutions have faced difficulties
over the years for a multitude of reasons, the major cause of serious
banking problems continues to be directly related to lax credit
standards for borrowers and counterparties, poor portfolio risk
management, or a lack of attention to changes in economic or other
circumstances that can lead to a deterioration in the credit standing of
a bank's counterparties. Credit risk is most simply defined as the
potential that a bank borrower or counterparty will fail to meet its
obligations in accordance with agreed terms. The goal of credit risk
management is to maximize a bank's risk-adjusted rate of return by
maintaining credit risk exposure within acceptable parameters. Banks
need to manage the credit risk inherent in the entire portfolio as well
as the risk in individual credits or transactions. Banks should also
consider the relationships between credit risk and other risks. The
effective management of credit risk is a critical component of a
comprehensive approach to risk management and essential to the
long-term success of any banking organization. In this research we
also study the relationship between credit risk indices and borrower-s
timely payback in Karafarin bank.
Abstract: This paper focuses on sovereign credit risk meaning a
hot topic related to the current Eurozone crisis. In the light of the
recent financial crisis, market perception of the creditworthiness of
individual sovereigns has changed significantly. Before the outbreak
of the financial crisis, market participants did not differentiate
between credit risk born by individual states despite different levels
of public indebtedness. In the proceeding of the financial crisis, the
market participants became aware of the worsening fiscal situation in
the European countries and started to discriminate among
government issuers. Concerns about the increasing sovereign risk
were reflected in surging sovereign risk premium. The main of this
paper is to shed light on the characteristics of the sovereign risk with
the special attention paid to the mutual relation between credit spread
and the CDS premium as the main measures of the sovereign risk
premium.
Abstract: In this paper, we discuss the paradigm shift in bank
capital from the “gone concern" to the “going concern" mindset. We
then propose a methodology for pricing a product of this shift called
Contingent Capital Notes (“CoCos"). The Merton Model can
determine a price for credit risk by using the firm-s equity value as a
call option on those assets. Our pricing methodology for CoCos also
uses the credit spread implied by the Merton Model in a subsequent
derivative form created by John Hull et al . Here, a market implied
asset volatility is calculated by using observed market CDS spreads.
This implied asset volatility is then used to estimate the probability of
triggering a predetermined “contingency event" given the distanceto-
trigger (DTT). The paper then investigates the effect of varying
DTTs and recovery assumptions on the CoCo yield. We conclude
with an investment rationale.
Abstract: This paper examines the relationship between financial
risks and profitability of the conventional and Islamic banks in
Malaysia for the period between 1996 and 2005. The measures of
profitability that have been used in the study are the return on equity
(ROE) and return on assets (ROA) while the financial risks are credit
risk, interest rate risk and liquidity risks. This study employs panel
data regression analysis of Generalised Least Squares of fixed effects
and random effects models. It was found that credit risk has a
significant impact on ROA and ROE for the conventional as well as
the Islamic banks. The relationship between interest rate risk and ROE
were found to be weakly significant for the conventional banks and
insignificant for the Islamic banks. The effect of interest rate risk on
ROA is significant for the conventional banks. Liquidity risk was
found to have an insignificant impact on both profitability measures.
Abstract: This conference paper discusses a risk allocation problem for subprime investing banks involving investment in subprime structured mortgage products (SMPs) and Treasuries. In order to solve this problem, we develop a L'evy process-based model of jump diffusion-type for investment choice in subprime SMPs and Treasuries. This model incorporates subprime SMP losses for which credit default insurance in the form of credit default swaps (CDSs) can be purchased. In essence, we solve a mean swap-at-risk (SaR) optimization problem for investment which determines optimal allocation between SMPs and Treasuries subject to credit risk protection via CDSs. In this regard, SaR is indicative of how much protection investors must purchase from swap protection sellers in order to cover possible losses from SMP default. Here, SaR is defined in terms of value-at-risk (VaR). Finally, we provide an analysis of the aforementioned optimization problem and its connections with the subprime mortgage crisis (SMC).