{"id":7037,"date":"2017-06-02T14:19:56","date_gmt":"2017-06-02T14:19:56","guid":{"rendered":"http:\/\/bulletins.bfconsulting.com\/?p=7037"},"modified":"2017-11-19T11:04:23","modified_gmt":"2017-11-19T11:04:23","slug":"credit-scoring-using-big-data","status":"publish","type":"post","link":"https:\/\/bulletins.bfconsulting.com\/en\/credit-scoring-using-big-data\/","title":{"rendered":"Credit scoring using Big Data"},"content":{"rendered":"

Credit institutions are constantly developing their scoring system to better prevent bad loans. To assess the solvency of potential borrowers, banks look at things such as age, social status, level of education, income and even Big Data. Big Data is obtained from services such as mobile operators, Yandex Taxi, Uber and even delivery services. This Big Data is used for such things as determining the actual domicile of an individual, analyzing the amount of time spent on specific sections of a credit application and even checking whether or not SMS messages sent by collections agencies arrive. To avoid subjectivity, the analysis of Big Data takes into account the whole image created from all factors and does not emphasize any one specific factor. For example, a potential borrower\u2019s social media might contain fake stories or exaggerated accounts; thus, more factors are taken into account.<\/p>\n

The new methods of credit scoring using Big Data have not only decreased delinquency levels but have actually increased savings at credit institutions. For example, VTB 24 earned RUB 19 billion of net interest income in 2016 due to the proper analysis of customer data. Credit institutions are also adopting methods of data mining and in-depth analysis of texts (text mining) in order to find information in hidden patterns, relationships and trends as well as other useful information on potential borrowers.<\/p>\n

\n\n