Recent years see more and more importance of the management of credit risk for investors, especially institutional investors having large portfolio of corporate bonds, loans or other credit products. Questions like how to evaluate the credit value-at-risk given large amount of information (like different ratings and multiple credit metrics issued by different rating companies), how to build an efficient credit portfolio (having the highest expected return under certain level of credit risk) become increasingly difficult to solve using traditional methods and models. Especially for the second question, the rising dimension of the portfolio under limited computational speed call for leveraging some more robust algorithms for the large portfolio optimization.
In this paper, we will choose JP Morgan’s credit metrics model to evaluate the portfolio’s credit value-at-risk for the elaboration of our thesis and try to solve the problem of how to leverage multiple credit metrics (as a major input for the model) issued by different rating firms to largely reduce the negative impact of variation of different sources, for the slightest difference among the metrics might result in a huge deviation in the evaluation of the credit risk. At last we will introduce and exploit an increasingly popular and robust algorithm in today’s Large Scale Linear Planning Problem---Simulated Annealing to optimize our credit portfolio.
In recent years, large attention has been put on credit risk analysis and control not only in academy but also in industry. What is credit risk? Credit risk is the risk of losses that a creditor may have when the obligator cannot pay back all or part of the debt. This kind of risk could exist in bonds, loans, or account receivables. Nowadays, credit risk evaluation models are mainly fall into two groups: single factor models like KMV model based on option theory, JPMorgan’s Credit Metrics, CSFP’s CreditRisk+ and CreditPortfolioView by Mckinsey as well as multiple factor model like Altman’s Z-score, Zeta model, etc.
Multiple factor models are based on financial statements and give rates in a statistical way while single factor models are based on Brown and Poisson process and describe credit risk by simulating Markov process. Both ways of rating risk have their strength and weakness. Financial data is a reflection of the past performance but is not a good indication for the future. Single factor model can well predict the future but too much rely on the credit information provided by rating agency and pay little attention on the market movement as a whole.
In order to alleviate the confliction and negative impact on portfolio decisions brought by multiple rating metrics from different sources, we propose a method that borrows the idea of pessimistic decision to largely reduce the uncertainty. By optimizing the portfolio under this method, that is choose the lowest rating (worst case) as it is and optimize the portfolio given that rating, we can at least secure our position and set us free from worrying about which source of rating is more creditable.
The following paper will cover general introduction a few popular credit risk evaluation models and a step by step demonstration of JP Morgan’s CreditMetrics, our method of dealing with multiple Credit Transition Metrics, general introduction of Simulated Annealing Algorithm and a step by step demonstration of our portfolio’s optimization process with SA. At last we discuss about the problems what could affect the effectiveness of this method.
Download
Credit Portfolio Optimization under Condition of Multiple Credit Transition Metrics
