BIG DATA PROCESSING ON THE EXAMPLE OF CREDIT SCORING

Journal of problem in computer science and information technologies, 2023

Full text Open access: Gold Metadata (CSL-JSON)
DOI 10.26577/1i32jpcsit2307
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

The article contains the results of research on the development of a model of a Big Data processing system, analysis and forecasting using Data Mining and machine learning methods in solving the problem of mortgage lending, specifically for analysing, forecasting and determining the solvency of individuals receiving a mortgage loan. The article considers the solution of one of the urgent problems of the banking system - mortgage lending. The main problem is to predict the solvency of mortgage borrowers for a long time using the data mining method. The main task is to implement the process of processing big data based on the developed system that determines the solvency of mortgage borrowers. Currently, the pace of long-term mortgage lending is growing annually, as a result, the timeliness of the research carried out in the article on the development of a model of the mortgage lending system, which clearly predicts the solvency of anyone who wants to get housing and makes appropriate decisions, is very relevant.