Credit Scoring / Credit Analysis

There are certain start-ups that every company will invest in or help with financial development. As a result of certain analyzes, the investor company determines the company to invest and acquire. In this way, taking the development into account, the amount of contribution to be provided in direct proportion to the return is calculated in advance. This kind of analysis method has been developed in banks among their customers by data scientist . In short, credit scoring transactions are carried out between the bank and the customer in the loan application. The purpose of doing this is basically evaluated with tests to see if people actually pay or will be able to pay the loan they will receive. This is called credit scoring in machine learning. After the transactions, a positive or negative feedback is made to the person applying for the loan. There are many metrics that evaluate in this direction. As an example to these; There are many features that will be examined in more detail, such as the amount of wages people get, their career history, their previous loan status, and so on. As a result of their evaluation, 1 and 0 values ​​that will be formed give us positive or negative meaning.
 

 
Banks do extensive research on this subject, as in most subjects, and after analyzing the data they have, they put them into machine learning processes. As a result of these processes, the final model is prepared by performing a few optimization operations on the logic testing steps. Then these situations are accelerated and tested for people who apply for almost every loan. Values ​​0 and 1 are assigned as values. As a result of the transactions, the output of 0 does not suggest us to give credit to this person, and vice versa, when the output of 1 comes, it makes the customer segmentation process for us by saying “you can give credit to this person”.After the last step is completed thanks to the data science staff, the last step for us is to return this information to the required departments, finalize the applications of the individuals according to the results and return. The importance of analysis is critical for a bank. Because the smallest mistakes made can cause the loss of large amounts. For this reason, every credit scoring transaction should return to the bank positively.
 

 
Credit scoring transactions are of great importance for every bank. The amount of money out of the safe and the failure of the person to be loaned to fully fulfill its responsibility will cause major financial problems. Therefore, the data science team working at the back should be experts in this field and evaluate the measures according to every circumstance. In addition, people’s personal information should be analyzed thoroughly and a logical return to their application should be made. After arranging the data pre-processing steps and performing the operations on the necessary variables, the process is about getting a little more data ready. Another critical issue in credit scoring is the data pre-processing steps and the analysis steps to be taken afterwards. The Data Science team should do the engineering of variables themselves and analyze the effects of variables and their correlations correctly. After these processes, it will be inevitable that a logical result will occur. To minimize the margin of error, it is all about adjusting the data almost perfectly and evaluating the necessary parameters.
 

 
It is necessary to create the machine learning algorithm at the very beginning of the processes required to perform credit scoring and the variables should be checked once more before the model. Because the transactions are completely related to variables. Therefore, the effect of categorical or numerical variables on the model differs. Also, while setting up this model, it must be adjusted carefully. If the parameters we will use are specifically using the Python programming language, the parameters can be tested thanks to the GridSearchCV () method, and then the most suitable parameters are integrated into the model. Thus, it can proceed more successfully in credit scoring. This increases the level of service provided, so that people can meet their expectations and provide a personalized service to suit them. People with a high level of satisfaction develop their bond with the bank. Additionally, they feel more confident psychologically. The most basic feature of people is to feel belonging or connected somewhere. Providing this can increase the customer potential owned. If you want your own advertisement to be made, you can keep a good bond with your customers and increase their loyalty to you. One of the things that directly affects this is undoubtedly credit scoring.
 

 
References :
-https://globalaihub.com/examples-of-artificial-intelligence-in-life/
-https://globalaihub.com/machine-learning-makine-ogrenimi/
-https://www.cgap.org/sites/default/files/publications/2019_07_Technical_Guide_CreditScore.pdf
-https://www.moodysanalytics.com/solutions-overview/credit-origination/credit-assessment
-https://corporatefinanceinstitute.com/resources/knowledge/credit/credit-analysis-process/