Difficult access to credit and repayment problems are due in large part to the unavailability of reliable information on the financial situation of borrowers and their level of indebtedness. Banks receive hundreds and requests for loans from businesses and they find themselves with a lot of financial documents to analyze, this situation is neither favorable for the banks because it can grant a loan which will never be repaid in addition to very long deadlines, and this waste of time is also harmful for the company. In this regard, to meet the increase in demand for credit and to reduce defaults, in short to overcome the drawbacks of the credit management systems and response to the increase in its clientele banks, lenders must be quick, effective and efficient in the process of processing loan files. The main question that arises here is: How to make bank risk management more efficient?
Our application automates the process of Data Entry that saves Enormous Time because automating data entry saves a significant amount of time, thereby slashing down the turnaround time of a project.In addition, it makes Data Entry Effortless owing to the fact that data entry automation effectively eliminates the daunting task of making manual entries.One of the most important objectives is the elimination of human errors for the reason that being an advanced technology, automated data entry is incredibly accurate leaving no scope for manual errors. This application aims to automate Credit -Scoring processing by providing a summary of the financial situation and solvency and restitution of interactive dashboards for decision making, also by classifying a company into vulnerable or not and reducing costs and errors. All of these business objectives speed up loan approvals therefore increase the number of approved loans.
The data analytics objectives of this application are Collecting data concerning the companies from websites through web scraping which is a technique for extracting content from websites, via a script or program also extracting financial informations from financial documents (pdf,...) to build our dataset by using Text mining and regular expressions then implementing a credit-scoring system that will allow us to decide whether to grant credit or not to the company based on its financial state and solvency by using statistical methods (financial formulas...) and machine learning algorithms for classification. Finally, creating dynamic dashboards.