Case Studies Effective Credit Scoring with Self-Developed Decision Support

Edit This Case Study Record

	Effective Credit Scoring with Self-Developed Decision Support

Effective Credit Scoring with Self-Developed Decision Support

Technology Category	Analytics & Modeling - Data Mining Analytics & Modeling - Predictive Analytics Analytics & Modeling - Real Time Analytics
Applicable Industries	Finance & Insurance
Applicable Functions	Business Operation
Use Cases	Fraud Detection
Services	Software Design & Engineering Services System Integration
Challenge	Folkia, a company providing short-term loans, faced the challenge of accurately selecting customers to minimize credit risk. The company needed a robust credit decision support system to improve its credit scoring model. The existing methods were not sufficient to discriminate effectively between good and bad customers, leading to potential financial risks. Additionally, maintaining and updating the system was cumbersome, requiring manual changes and extensive data structuring. Folkia aimed to develop a more efficient, accurate, and easy-to-maintain system to enhance its credit decision-making process. Read More
About Customer	Folkia, established in Norway in 2006, operates in Sweden, Finland, Denmark, and Estonia. The company specializes in providing short-term loans and aims to offer economical and effective financial services to its customers. Folkia's primary focus is on selecting the right customers to minimize credit risk and ensure financial stability. The company collaborates with consulting firms and utilizes advanced software tools to develop customized solutions for its credit scoring needs. With a commitment to innovation and efficiency, Folkia continuously seeks to improve its decision-making processes and maintain a competitive edge in the financial services industry. Read More
Solution	Folkia developed a customized credit decision support system in collaboration with the consulting firm Aregab, utilizing STATISTICA software from StatSoft. The software's powerful data management and analytical capabilities, including data mining, enabled the creation of multiple models using different statistical methods such as logistic regression, MARSplines, and boosted-trees. These models were tested against each other to determine the most effective one. The system's graphical presentation at every step, from selection to testing, simplified the process and enhanced efficiency. The completed score model effectively rated customers by credit risk, allowing Folkia to make informed decisions and treat high-risk customers differently. The system's easy maintenance and quick development, facilitated by the alliance with Aregab, further contributed to its success. Read More Log in to view content
Contents

Technology Category

Analytics & Modeling - Data Mining

Analytics & Modeling - Predictive Analytics

Analytics & Modeling - Real Time Analytics

Applicable Industries

Finance & Insurance

Applicable Functions

Business Operation

Use Cases

Fraud Detection

Services

Software Design & Engineering Services

System Integration

Challenge

Folkia, a company providing short-term loans, faced the challenge of accurately selecting customers to minimize credit risk. The company needed a robust credit decision support system to improve its credit scoring model. The existing methods were not sufficient to discriminate effectively between good and bad customers, leading to potential financial risks. Additionally, maintaining and updating the system was cumbersome, requiring manual changes and extensive data structuring. Folkia aimed to develop a more efficient, accurate, and easy-to-maintain system to enhance its credit decision-making process.

About Customer

Folkia, established in Norway in 2006, operates in Sweden, Finland, Denmark, and Estonia. The company specializes in providing short-term loans and aims to offer economical and effective financial services to its customers. Folkia's primary focus is on selecting the right customers to minimize credit risk and ensure financial stability. The company collaborates with consulting firms and utilizes advanced software tools to develop customized solutions for its credit scoring needs. With a commitment to innovation and efficiency, Folkia continuously seeks to improve its decision-making processes and maintain a competitive edge in the financial services industry.

Solution

Folkia developed a customized credit decision support system in collaboration with the consulting firm Aregab, utilizing STATISTICA software from StatSoft. The software's powerful data management and analytical capabilities, including data mining, enabled the creation of multiple models using different statistical methods such as logistic regression, MARSplines, and boosted-trees. These models were tested against each other to determine the most effective one. The system's graphical presentation at every step, from selection to testing, simplified the process and enhanced efficiency. The completed score model effectively rated customers by credit risk, allowing Folkia to make informed decisions and treat high-risk customers differently. The system's easy maintenance and quick development, facilitated by the alliance with Aregab, further contributed to its success.

Impact #1	The new credit decision support system significantly improved the discrimination capability between good and bad customers, allowing Folkia to make more informed decisions.
Impact #2	The system's easy maintenance ensured that updates could be implemented quickly and efficiently, without the need for manual changes.
Impact #3	The development of the system was rapid, with data collection starting in April and the new system being operational by June.

Impact #1

The new credit decision support system significantly improved the discrimination capability between good and bad customers, allowing Folkia to make more informed decisions.

Impact #2

The system's easy maintenance ensured that updates could be implemented quickly and efficiently, without the need for manual changes.

Impact #3

The development of the system was rapid, with data collection starting in April and the new system being operational by June.

Benefit #1	The new system reduced the risks of extending credit to customers that would default by approximately 40%.
Benefit #2	Other turnover was only reduced by 3-4%.

Benefit #1

The new system reduced the risks of extending credit to customers that would default by approximately 40%.

Benefit #2

Other turnover was only reduced by 3-4%.

Download PDF Version

Overview

Effective Credit Scoring with Self-Developed Decision Support

Operational Impact

Quantitative Benefit