Data science modelling of the credit rating : case study of the German credit data

master's thesis

• Author: Adam Mandić
• Mentor: Mirjana Pejić Bach (mentor)
• Committee member: Mario Spremić (član povjerenstva)
• Committee member: Božidar Jaković (član povjerenstva)
• Granter: University of Zagreb; Faculty of Economics and Business; Zagreb
• Defense date and country: 2023-09-29, Croatia
• Scientific / art field, discipline and subdiscipline: SOCIAL SCIENCES; Economics; Business Informatics

Abstract

In recent years there has been an increased adoption of data science methods in numerous fields and industries. With usage of statistical analysis, machine learning, programming, but also domain expertise, it finds and identifies different patterns that allow experts to make certain predictions. It also allows experts to derive valuable insights from numerous datasets with high level of intricacy, complexity and size. In this paper we focus on how financial institutions utilize data science methods for various tasks. One of the main ways financial institutions make use of such methods is for determining credit score, which highlights good and bad candidates for loan. Credit scoring would be a numerical evaluation of an individual with goal to calculate the probability of concluding a contract, making a purchase decision, or in order to be able to measure the creditworthiness of a person that needs a loan. The primary aim of this paper is demonstrating the main characteristic of (German Credit Data) data set. By applying our analysis, we were able to determine whether the individual would be considered a good or a bad candidate for receiving credit. After gathering the number of correctly classified instances, an experiment was conducted to compare three different decision trees, and how reducing its size and the number of leaves would affect further correctly classified instances.

• Keywords: data science; credit rating; decision tree; classification tree; financial institutions
• Language: english
• URN:NBN: urn:nbn:hr:148:272581
• Study programme: Title: Master Degree in Business; specializations in: Marketing in english, Managerial informatics, Management, Marketing, Trade and international business, Leadership; Course: Managerial informatics; Study programme type: university; Study level: graduate; Academic / professional title: sveučilišni magistar ekonomije/sveučilišna magistra ekonomije (sveučilišni magistar ekonomije/sveučilišna magistra ekonomije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Access restricted to students and staff of home institution
• Created on: 2023-10-04 10:31:04