Scoring Guides

Name (required)

E-mail (required)

Learn more on improving risk management processes with power of advanced analytics.

5 Hidden Mistakes in Scorecard Development and How to Avoid Them

Make sure to avoid these hidden pitfalls and build the most efficient scoring models.

Statistical forecasting models are being used extensively to guide decision processes associated with credit risk management, loan application processing, customer lifecycle management, fraud detection and more. This paper provides recommendations to help you approach scorecard development in the most disciplined way.

Retail Lending: How to Build and Maintain a Generic Scoring Model

Description of the generic scoring model for retail lending and recommendations on how to use it.

Many lenders are still using outdated and labor intensive methods to process loan applications and qualify borrowers. This results in extensive lead times in making a decision on a loan, missed opportunities in customer satisfaction and profitability, and in some cases, minimal profits and/or excessive risk in an organizations loan portfolio.

This document describes the generic scoring model for retail lending and provides recommendations on how to take the maximum advantage of the scoring model.

Automated Loan Application Processing for Microfinance Organizations

This paper shows how you can set up and operate robust and efficient lending mechanism even if your staff has no relevant experience, you have never used any software and the entire branch network or certain points of sale have no Internet connection.

Manual data input and application handling is prone to human subjectivity and mistakes, and is not optimal for standard decisions.

Read this paper to learn to formalize lending decisions and apply decision automation where it works best, while using a more manual approach to capture new opportunities.

Credit Risk Modeling. Reject Inference Methods.

Capture new growth opportunities and improve scorecard accuracy by enhancing scorecards using data on rejected accounts.Developing a solid and sound forecasting model using a reject inference can substantially increase the size, and quality of a customer base or portfolio. This white paper explores the use and development of reject inferences for the purpose of raising profits and increasing market share.
Name (required)

E-mail (required)