Automatisation of the Applicant’s Solvency Assessment Using Data Mining Tools

Bank lending is based on the principle of interest income generation for loaning their funds. Therefore, bankers receive their profit only when the money is returned by reliable borrowers. The more credible clients a credit organization has, the higher its income is. Credit scoring is a fundamental tool for the applicant’s solvency assessment. Therefore, the main objective of this work is to automate the process of the applicant’s solvency assessment using data mining tools in order to reduce the influence of the human factor on this process and improve credit scoring existing algorithms. This research contains a review of current technical solutions for automated customer data processing systems. To achieve the goal of the research, the next data analysis methods are considered in the work: Decision Trees, Gradient Boosting, Random Forest, Logistic Regression and Extra Trees. As a result of the analysis, I suppose to get a graphical representation of the outcome of each of the methods and build a credit scoring model using them.