services

Credit scoring
This is a model of customers reliability and credibility evaluation, which helps to identify customers with high risk of default. This means we collect as many as possible attributes, calculate their significance and range and group all the customers by their risk score.

Effort and duration
350

days

Tech stack

SQL

Python

Microstrategy

Oracle Databases

Spark

PL/SQL

Hadoop

Who is our client

life:)

the third largest mobile operator in Belarus
Basic moments
  • As much as possible sources integration
  • Risk of default criterion calculation and evaluation
  • Descriptive analysis of customer interactions full history
  • Strategy development
  • Modelling and attribute evaluation, model tuning
  • Deploy
  • Effectiveness measurement and re-train of model if necessary
Project overview

Why customer scoring?

Simply: because every business contact deserves a bespoke approach. Do you treat a customer who has contributed to your turnover for a number of years in the same way as a customer who only places an occasional order? The answer is obvious.
Thanks to scoring you will get a clear picture of the profitability of all your customers.
Business value
We have developed a model of customer’s reliability and credibility evaluation which helps to identify customers with high risk of failure to pay.Collecting as many as possible attributes referring to payments, we get the behavioral patterns of every client. Similar patterns could be found and used for client’s categorization and classification. Customer’s social-demographic indicators help us to form customer groups and improve model quality. So after evaluation of attributes significance and model tuning, we can range and group all the customers by their risk score.
Contact us.

Your name

Your e-mail

Your message

max size is 15 MB; allowed extension: jpg,jpeg, png, txt, pdf, doc, docx, xls, xlsx,ppt, pptx
I agree to the processing of my personal data