Skip to main navigation Skip to search Skip to main content

Loan default prediction model improvement through comprehensive preprocessing and features selection

  • Zarqa University
  • Princess Sumaya University for Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

21 Scopus citations

Abstract

For financial institutions and the banking industry, it is very crucial to have predictive models for their financial activities, as they play a major role in risk management. Predicting loan default is one of the critical issues that they focus on, as huge revenue loss could be prevented by predicting customer's ability to pay back on time. In this paper, different classification methods (Naïve Bayes, Decision Tree, and Random Forest) are being used for prediction, comprehensive different pre-processing techniques are being applied on the dataset, and three different feature extractions algorithms are used to enhance the accuracy and the performance. Results are compared using F1 accuracy measure, and an improvement of over 3% has been obtained.

Original languageEnglish
Title of host publicationProceedings - 2019 International Arab Conference on Information Technology, ACIT 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages235-240
Number of pages6
ISBN (Electronic)9781728130101
DOIs
StatePublished - Dec 2019
Externally publishedYes
Event2019 International Arab Conference on Information Technology, ACIT 2019 - Al Ain, United Arab Emirates
Duration: 3 Dec 20195 Dec 2019

Publication series

NameProceedings - 2019 International Arab Conference on Information Technology, ACIT 2019

Conference

Conference2019 International Arab Conference on Information Technology, ACIT 2019
Country/TerritoryUnited Arab Emirates
CityAl Ain
Period3/12/195/12/19

Keywords

  • Classification
  • Decision tree
  • Features selection
  • Generic algorithm
  • Naïve Bayes
  • PSO algorithm
  • Pre-processing
  • Prediction
  • Random Forest
  • SVM

Fingerprint

Dive into the research topics of 'Loan default prediction model improvement through comprehensive preprocessing and features selection'. Together they form a unique fingerprint.

Cite this