Hi friends, I am Toshi, This is my weekly letter. This week’s topic is “how banks rate you when you borrow money from banks”. When we want bank loans, it is good that we can borrow the amount of money we need, with a lower interest. Then I am wondering how banks decide who can borrow the amount of money requested with lower interests. In other words, how banks assess customer’s credit worthiness. The answer is “Classification”. Let me explain more details. To make the story simple, I take an example of unsecured loans, loans without collateral.
1. “Credit risk model” makes judgements to lend
Now many banks prepare their own risk models to assess credit worthiness of customers. Especially global banks are required to prepare the models by regulators, such as BIS, FSA and central banks. Major regional banks are also promoted to have risk models to assess credit worthiness. Regulations may differ from countries to countries, by size of banks. But it is generally said that banks should have their risk models to enhance credit risk management. When I used to be a credit risk manager of the Japanese consumer finance company, which is one of the group companies in the biggest financial group in Japan, each customer is rated by credit risk models. Good rating means you can borrow money with lower interest. On the other hand, bad rating means you can borrow only limited amount of money with higher interest rate or may be rejected to borrow. From the standpoint of management of banks, it is good because banks can keep consistency of the lending judgements to customers among the all branches. The less human judgement exists, the more consistency banks keep. Even though business models may be different according to strategies of banks, the basic idea of the assessment of credit worthiness is the same.
2. “Loan application form” is a starting point of the rating process
So you understand credit risk models play an important role. Next, you may wonder how rating of each customer is provided. Here “classification” works. Let me explain about this. When we try to borrow money, It is required to fill “application forms”. Even though the details of forms are different according to banks, we are usually asked to fill “age” “job title” “industry” “company name” “annual income” “owned assets and liabilities” and so on. These data are input into risk models as “features”. So each customer has a different value of “features”. For example, someone’s income is high while others income is low. Then I can say “Features”of each customer can explain credit worthiness of each customer. In other words, credit risk model can “classify” customers with high credit worthiness and customers with low credit worthiness by using “features”.
3. Rating of each customer are provided based on “probability of default”
Then let us see how models can classify customers in more details. Each customer has values of “features” in the application form. Based on the values of “features”, each customer obtains his/her own “one value”. For example, Tom obtains “-4.9” and Susum obtains “0.9” by adding “features” multiplied with “its weight”. Then we can obtain “probability of default” for each customer. “Probability of default” means the likelihood where the customer will be in default in certain period, such as one year. Let us see Tom’s case. According to the graph below, Tom’s probability of default, which is shown in y-axis, is close to 0. Tom has a low “probability of default”. It means that he is less likely to be in default in the near term. In such a case, banks provide a good rating to Tom. This curve below is called “logistic curve” which I explained last week. Please look at my week letter on 23 April.
Let us see Susumu’s case. According to the graph below, Susumu’s probability of default, which is shown in y-axis, is around 0.7, 70%. Susumu has a high probability of default. It means that he is likely to be in default in the near term. In such a case, banks provide a bad rating to Susumu. In summary, the lower probability of default is, the better rating is provided to customers.
Although there are other methods of “classification”, logistic curve is widely used in the financial industry as far as I know. In theory, the probability of default can be obtained for many customers from individuals to big company and sovereigns, such as “Greeks”. In practice, however, more data are available in loans to individuals and small and medium size enterprises (SME) than loans to big companies. The more data are available, the more accurately banks can assess credit worthiness. If there are few data about defaults of customers in the past, it is difficult to develop credit risk models effectively. Therefore, risk models of individuals and SMEs might be easier than risk models of big companies as more data are usually available in loans to individuals and SMEs.
I hope you can understand the process to rate customers in banks. Data can explain our credit worthiness, maybe better than we do. Data about us is very important when we try to borrow money from banks.