Credit Risk Scoring Engine

Objective

Build, Deploy and Productionize a combination of models for instantaneous loan qualification across Storefront and Online Channels

Business Problem

Risk Management unit of a Retail Lending business needed seamless solution for loan application underwriting of pay-day loan & short term (installments) consumer loan products for returning customers via omni channel touchpoints

Solution Overview

  • Customers can now apply installment loan/payday loan through web/physical branch
  • Credit Scoring Engine developed in collaboration with Risk unit generates PD (Probability of Default) score for internal teams and Denial response for customers, by processing loan parameters like Age, GMI, Previous Loan History, et.al 
  • Further scores are run through set of business rules to decide the final loan amount for approved for applications 

Output/Value Add

  • Improved efficiency and quicker turnaround in credit appraisal process
  • Risk based loan limit setting
  • Approval/Denial reasons are provided driving customer trust

Solution Architecture

Solution Brief

Our solution for credit scoring was using more data to provide an individualized credit score based on factors including current income, employment opportunity, recent credit history, and ability to earn in addition to older credit history. This Solution can also adapt to new problems, like credit card churners, who might have a high credit score. This Solution can also satisfy regulatory requirements to provide reason codes for credit decisions that explain the key factors in credit decisions.

Application Flow

  •  Seamless integration across lifecycle of customers applying loan for both secured and unsecured products
  •  Integrate the loan application for each customer to corresponding product and loan type
  •  Enable Mashery to trigger API calls real-time
  •  BW to process and queue the requests to Statistica
  •  Statistica to score the loan application and return PD and Plausible denial reasons